Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Context7 Integration Skill · aiskillstore | DecimalAI

AI/MLby aiskillstore

Context7 Integration Skill

Use when integrating Context7 (knowledge/context store) for document ingestion, semantic search, or scoped context retrieval. Triggers for: uploading documents, searching knowledge base, filtering by role/tenant, or providing AI with document-grounded context. NOT for: general database queries, file storage without context semantics, or non-document content.

Maintained

SkillScore

SkillScore70/100

Test results 70

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

17%70%of test cases passed +52 pts

Without skill4 of 23

With skill16 of 23

12 fixed4 passed either way7 still failing0 broke

Measured on gemini-3.6-flash9/2/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWrite a Python helper function `get_context7_client()` that returns a global singleton instance of Context7Client.

Without the skillMissed

With the skillPassed

Same model, same task. Answers are capped and redacted.

Use this skill

Your agent runs on

Adds every file the skill has, pinned so you can update it. No account needed.

pip install "decimalai>=0.15"
decimalai skills add aiskillstore-context7-integration
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

The same install from Python, for a notebook or a setup script.

Install

pip install "decimalai>=0.15"

Add the skill

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("aiskillstore-context7-integration")
if result.exit_code:
    raise SystemExit(result.problems)

print("Added. Start Claude Code with the command below.")

Start Claude Code with it

claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

Type these in a Claude Code session. No account or API key. It writes the skill and any files it bundles, and asks first when its safety rating isn't Passed.

Add the DecimalAI plugin, once

/plugin marketplace add decimal-labs/decimalai-claude-plugins
/plugin install decimalai@decimalai

Install this skill

/decimalai:install aiskillstore-context7-integration

The plugin needs python3 and curl on your machine.

No Python or account. Claude Code picks it up in its next session.

Save it into your project

curl -fsSL --create-dirs -o .claude/skills/aiskillstore-context7-integration/SKILL.md https://app.decimal.ai/s/aiskillstore-context7-integration/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/aiskillstore-context7-integration/SKILL.md

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Claude Code docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add aiskillstore-context7-integration

Add it to your agent

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("aiskillstore-context7-integration")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-context7-integration/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query

skill = Path(".agents/skills/aiskillstore-context7-integration/SKILL.md").read_text()
options = ClaudeAgentOptions(system_prompt=f"You are a helpful agent.\n\n{skill}", max_turns=6)

async def main():
    async for message in query(prompt="Hello!", options=options):
        print(message)

# In a notebook or async code: await main()
asyncio.run(main())

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Claude Agent SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai-agents]"
decimalai skills add aiskillstore-context7-integration

Add it to your agent

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

Install

pip install "decimalai[openai-agents]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("aiskillstore-context7-integration")
if result.exit_code:
    raise SystemExit(result.problems)

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-context7-integration/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/aiskillstore-context7-integration/SKILL.md").read_text()
agent = Agent(name="support", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

OpenAI Agents docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai]"
decimalai skills add aiskillstore-context7-integration

Add it to your agent

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

Install

pip install "decimalai[openai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("aiskillstore-context7-integration")
if result.exit_code:
    raise SystemExit(result.problems)

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-context7-integration/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/aiskillstore-context7-integration/SKILL.md").read_text()
reply = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[
        {"role": "system", "content": f"You are a helpful agent.\n\n{skill}"},
        {"role": "user", "content": "Hello!"},
    ],
).choices[0].message

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

OpenAI SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[anthropic]"
decimalai skills add aiskillstore-context7-integration

Add it to your agent

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

Install

pip install "decimalai[anthropic]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("aiskillstore-context7-integration")
if result.exit_code:
    raise SystemExit(result.problems)

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-context7-integration/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/aiskillstore-context7-integration/SKILL.md").read_text()
reply = client.messages.create(
    model="claude-haiku-5-5",
    max_tokens=4096,
    system=f"You are a helpful agent.\n\n{skill}",
    messages=[{"role": "user", "content": "Hello!"}],
)

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Anthropic docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[google-genai]"
decimalai skills add aiskillstore-context7-integration

Add it to your agent

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

Install

pip install "decimalai[google-genai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("aiskillstore-context7-integration")
if result.exit_code:
    raise SystemExit(result.problems)

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-context7-integration/SKILL.md

Give it to your agent

from pathlib import Path
from google import genai
from google.genai import types

client = genai.Client()
skill = Path(".agents/skills/aiskillstore-context7-integration/SKILL.md").read_text()
response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Hello!",
    config=types.GenerateContentConfig(system_instruction=f"You are a helpful agent.\n\n{skill}"),
)

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Gemini API docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add aiskillstore-context7-integration

Add it to your agent

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

Install

pip install "decimalai[langchain]" langchain-openai

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("aiskillstore-context7-integration")
if result.exit_code:
    raise SystemExit(result.problems)

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-context7-integration/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/aiskillstore-context7-integration/SKILL.md").read_text()
agent = create_agent("openai:gpt-5.4-mini", tools=[], system_prompt=f"You are a helpful agent.\n\n{skill}")
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

LangChain docs

CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add aiskillstore-context7-integration

Add it to your agent

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

The same install from Python, for a notebook or a setup script. CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("aiskillstore-context7-integration")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

No DecimalAI package. CrewAI's own loader reads the folder, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-context7-integration/SKILL.md

Give it to your agent

from pathlib import Path
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                         # your own CrewAI LLM
    skills=[Path(".agents/skills")],
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

CrewAI docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[adk]"
decimalai skills add aiskillstore-context7-integration

Add it to your agent

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

Install

pip install "decimalai[adk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("aiskillstore-context7-integration")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-context7-integration/SKILL.md

Give it to your agent

from pathlib import Path
from google.adk.agents import LlmAgent

skill = Path(".agents/skills/aiskillstore-context7-integration/SKILL.md").read_text()
agent = LlmAgent(
    name="support",
    model="gemini-3.5-flash",
    instruction=lambda context: f"You are a helpful agent.\n\n{skill}",
)

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Google ADK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add aiskillstore-context7-integration

Add it to your agent

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

Install

pip install "decimalai[pydantic-ai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("aiskillstore-context7-integration")
if result.exit_code:
    raise SystemExit(result.problems)

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-context7-integration/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/aiskillstore-context7-integration/SKILL.md").read_text()
agent = Agent("openai:gpt-4o-mini", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Pydantic AI docs

Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add aiskillstore-context7-integration

Add it to your agent

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

The same install from Python, for a notebook or a setup script. Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("aiskillstore-context7-integration")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-context7-integration/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/aiskillstore-context7-integration/SKILL.md").read_text()
agent = create_deep_agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Deep Agents docs

Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add aiskillstore-context7-integration

Add it to your agent

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

The same install from Python, for a notebook or a setup script. Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("aiskillstore-context7-integration")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-context7-integration/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/aiskillstore-context7-integration/SKILL.md").read_text()
agent = Agent(client=client, instructions=f"You are a helpful agent.\n\n{skill}")
asyncio.run(agent.run("Hello!"))

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Microsoft Agent Framework docs

Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add aiskillstore-context7-integration

Add it to your agent

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

The same install from Python, for a notebook or a setup script. Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("aiskillstore-context7-integration")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-context7-integration/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/aiskillstore-context7-integration/SKILL.md").read_text()
agent = Agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent("Hello!")

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Strands docs

Adds every file the skill has, pinned so you can update it. Cursor, Copilot, Cline and Warp read this folder by themselves.

pip install "decimalai>=0.15"
decimalai skills add aiskillstore-context7-integration

No Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.

Save it into your project

curl -fsSL --create-dirs -o .agents/skills/aiskillstore-context7-integration/SKILL.md https://app.decimal.ai/s/aiskillstore-context7-integration/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-context7-integration/SKILL.md

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Cursor and other editors docs

Fetch the file and give its text to your model as instructions. No account or package needed.

Get the file

curl -fsSL https://app.decimal.ai/s/aiskillstore-context7-integration/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/aiskillstore-context7-integration.json

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 9/2/2026
Source: aiskillstore/marketplace ↗
License: Not recorded

Manage it in DecimalAI

Saved prompts and skills, pinned versions, and traces of this skill in your runs. DecimalAI does not run your agent.

Claude Code reads files from your project, so DecimalAI config does not apply there.

On Claude Agent SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI Agents: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Anthropic: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Gemini API: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On LangChain: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On CrewAI: set DECIMAL_API_KEY and add decimalai.init(crewai=True) to record runs and skill use. The skill version stays in your repo.

On Google ADK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Pydantic AI: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Deep Agents: set DECIMAL_API_KEY and add decimalai.init(langchain=True) to record runs and skill use. The skill version stays in your repo.

On Microsoft Agent Framework: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

On Strands: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

Editors read files from your project, so DecimalAI config does not apply there.

Anywhere else: record a use with decimalai.log_skill_activation() inside a trace.

Use this skill

SKILL.md

Context7 Integration Skill

Expert integration of Context7 for document ingestion, semantic search, and role-scoped context retrieval in ERP applications.

Quick Reference

Task	Method/Endpoint
Ingest document	`context7_client.ingest_document()`
Batch ingest	`context7_client.ingest_batch()`
Search context	`context7_client.search()`
Get document	`context7_client.get_document()`
Delete document	`context7_client.delete_document()`

Project Structure

backend/
├── app/
│   ├── services/
│   │   └── context7_client.py    # Core Context7 client
│   ├── api/
│   │   └── knowledge/
│   │       └── routes.py         # Knowledge API endpoints
│   └── schemas/
│       └── knowledge.py          # Pydantic schemas
frontend/
├── hooks/
│   └── useContext7Search.ts     # Search hook
└── components/
    └── knowledge/
        └── ContextSearch.tsx    # Search component
docs/
├── policies/                     # Source documents
├── faq/                          # FAQ documents
└── procedures/                   # Procedure documents

Context7 Client

Core Client Class

# backend/app/services/context7_client.py
import os
from typing import Optional
from pydantic import BaseModel
from enum import Enum
from datetime import datetime


class DocumentType(str, Enum):
    MARKDOWN = "markdown"
    PDF = "pdf"
    HTML = "html"
    TEXT = "text"


class DocumentMetadata(BaseModel):
    """Metadata for context documents."""
    title: str
    description: Optional[str] = None
    # Role-based access
    allowed_roles: list[str] = []  # Empty = all roles
    # Organization scope
    school_id: Optional[str] = None
    # Content categorization
    module: str  # e.g., "fees", "attendance", "policies"
    category: Optional[str] = None  # e.g., "faq", "procedure", "policy"
    # Language
    language: str = "en"
    # Versioning
    version: str = "1.0"
    effective_date: Optional[datetime] = None
    expiry_date: Optional[datetime] = None
    # Source tracking
    source_file: Optional[str] = None
    source_url: Optional[str] = None


class ContextDocument(BaseModel):
    """Document in Context7."""
    id: str
    content: str
    metadata: DocumentMetadata
    chunk_id: Optional[str] = None
    similarity_score: Optional[float] = None


class Context7Client:
    """Client for Context7 knowledge store."""

    def __init__(
        self,
        api_key: Optional[str] = None,
        base_url: Optional[str] = None,
        default_namespace: str = "default",
    ):
        self.api_key = api_key or os.getenv("CONTEXT7_API_KEY")
        self.base_url = base_url or os.getenv("CONTEXT7_API_URL", "https://api.context7.com")
        self.default_namespace = default_namespace
        self._session = None

    def _get_session(self):
        """Get or create requests session."""
        if not self._session:
            import requests
            self._session = requests.Session()
            if self.api_key:
                self._session.headers.update({"Authorization": f"Bearer {self.api_key}"})
        return self._session

    def _request(
        self,
        method: str,
        endpoint: str,
        **kwargs
    ) -> dict:
        """Make API request to Context7."""
        session = self._get_session()
        response = session.request(
            method,
            f"{self.base_url}{endpoint}",
            **kwargs
        )
        response.raise_for_status()
        return response.json()

    # === INGESTION ===

    def ingest_document(
        self,
        content: str,
        metadata: DocumentMetadata,
        namespace: Optional[str] = None,
        document_id: Optional[str] = None,
    ) -> dict:
        """
        Ingest a single document into Context7.

        Args:
            content: Document content (markdown, HTML, or text)
            metadata: Document metadata with tags and access control
            namespace: Optional namespace (defaults to default_namespace)
            document_id: Optional document ID for idempotent updates

        Returns:
            Ingestion result with document ID
        """
        payload = {
            "content": content,
            "metadata": metadata.model_dump(),
            "document_id": document_id,
            "namespace": namespace or self.default_namespace,
        }

        return self._request("POST", "/v1/documents", json=payload)

    def ingest_batch(
        self,
        documents: list[tuple[str, DocumentMetadata]],
        namespace: Optional[str] = None,
        batch_size: int = 10,
    ) -> dict:
        """
        Ingest multiple documents in batches.

        Args:
            documents: List of (content, metadata) tuples
            namespace: Optional namespace
            batch_size: Number of documents per batch

        Returns:
            Batch ingestion result with success/failure counts
        """
        results = {"successful": 0, "failed": 0, "documents": []}
        namespace = namespace or self.default_namespace

        for i in range(0, len(documents), batch_size):
            batch = documents[i:i + batch_size]
            batch_payload = [
                {
                    "content": content,
                    "metadata": metadata.model_dump(),
                    "namespace": namespace,
                }
                for content, metadata in batch
            ]

            try:
                response = self._request(
                    "POST",
                    "/v1/documents/batch",
                    json={"documents": batch_payload}
                )
                results["successful"] += len(batch)
                results["documents"].extend(response.get("documents", []))
            except Exception as e:
                results["failed"] += len(batch)
                # Log failed batch for retry

        return results

    def ingest_from_file(
        self,
        file_path: str,
        metadata: DocumentMetadata,
        namespace: Optional[str] = None,
    ) -> dict:
        """
        Ingest a document from a file.

        Args:
            file_path: Path to file (markdown, PDF, or HTML)
            metadata: Document metadata
            namespace: Optional namespace

        Returns:
            Ingestion result
        """
        # Determine document type from extension
        ext = os.path.splitext(file_path)[1].lower()

        if ext == ".md":
            with open(file_path, "r", encoding="utf-8") as f:
                content = f.read()
            doc_type = DocumentType.MARKDOWN
        elif ext == ".pdf":
            content = self._extract_pdf_text(file_path)
            doc_type = DocumentType.PDF
        elif ext in [".html", ".htm"]:
            with open(file_path, "r", encoding="utf-8") as f:
                content = f.read()
            content = self._strip_html(content)
            doc_type = DocumentType.HTML
        else:
            # Default to text
            with open(file_path, "r", encoding="utf-8") as f:
                content = f.read()
            doc_type = DocumentType.TEXT

        # Update metadata with source file
        metadata.source_file = file_path

        return self.ingest_document(content, metadata, namespace)

    def _extract_pdf_text(self, file_path: str) -> str:
        """Extract text from PDF file."""
        try:
            import PyPDF2
            with open(file_path, "rb") as f:
                reader = PyPDF2.PdfReader(f)
                text = "\n".join(page.extract_text() for page in reader.pages)
            return text
        except ImportError:
            raise ImportError("PyPDF2 required for PDF ingestion: pip install PyPDF2")

    def _strip_html(self, html: str) -> str:
        """Strip HTML tags from content."""
        import re
        clean = re.compile("<.*?>")
        return re.sub(clean, "", html)

    # === RETRIEVAL ===

    def search(
        self,
        query: str,
        namespace: Optional[str] = None,
        filters: Optional[dict] = None,
        max_chunks: int = 5,
        min_similarity: float = 0.7,
        user_role: Optional[str] = None,
        school_id: Optional[str] = None,
    ) -> list[ContextDocument]:
        """
        Search for relevant context documents.

        Args:
            query: Search query (semantic search)
            namespace: Namespace to search in
            filters: Additional metadata filters
            max_chunks: Maximum number of chunks to return
            min_similarity: Minimum similarity score threshold
            user_role: User's role for access control
            school_id: User's school ID for multi-tenancy

        Returns:
            List of relevant document chunks
        """
        # Build search payload with access control
        payload = {
            "query": query,
            "namespace": namespace or self.default_namespace,
            "max_chunks": max_chunks,
            "min_similarity": min_similarity,
            "filters": filters or {},
        }

        # Add role-based filtering
        if user_role:
            payload["filters"]["allowed_roles"] = [user_role, "all"]

        # Add tenant filtering
        if school_id:
            payload["filters"]["school_id"] = school_id

        response = self._request("POST", "/v1/search", json=payload)

        return [
            ContextDocument(
                id=doc.get("id"),
                content=doc.get("content", ""),
                metadata=DocumentMetadata(**doc.get("metadata", {})),
                chunk_id=doc.get("chunk_id"),
                similarity_score=doc.get("similarity_score"),
            )
            for doc in response.get("documents", [])
        ]

    def get_document(
        self,
        document_id: str,
        namespace: Optional[str] = None,
    ) -> Optional[ContextDocument]:
        """
        Get a specific document by ID.

        Args:
            document_id: Document ID
            namespace: Namespace

        Returns:
            Document or None if not found
        """
        try:
            response = self._request(
                "GET",
                f"/v1/documents/{document_id}",
                params={"namespace": namespace or self.default_namespace}
            )
            return ContextDocument(
                id=response.get("id"),
                content=response.get("content", ""),
                metadata=DocumentMetadata(**response.get("metadata", {})),
            )
        except Exception:
            return None

    def delete_document(
        self,
        document_id: str,
        namespace: Optional[str] = None,
    ) -> bool:
        """
        Delete a document from Context7.

        Args:
            document_id: Document ID
            namespace: Namespace

        Returns:
            True if deleted successfully
        """
        try:
            self._request(
                "DELETE",
                f"/v1/documents/{document_id}",
                params={"namespace": namespace or self.default_namespace}
            )
            return True
        except Exception:
            return False

    # === MANAGEMENT ===

    def list_documents(
        self,
        namespace: Optional[str] = None,
        module: Optional[str] = None,
        limit: int = 100,
    ) -> list[dict]:
        """
        List documents in a namespace.

        Args:
            namespace: Namespace to list
            module: Filter by module
            limit: Maximum number of results

        Returns:
            List of document summaries
        """
        params = {
            "namespace": namespace or self.default_namespace,
            "limit": limit,
        }
        if module:
            params["module"] = module

        response = self._request("GET", "/v1/documents", params=params)
        return response.get("documents", [])

    def get_stats(self, namespace: Optional[str] = None) -> dict:
        """Get statistics for a namespace."""
        response = self._request(
            "GET",
            "/v1/stats",
            params={"namespace": namespace or self.default_namespace}
        )
        return response


# Singleton instance
_context7_client: Optional[Context7Client] = None


def get_context7_client() -> Context7Client:
    """Get or create Context7 client singleton."""
    global _context7_client
    if _context7_client is None:
        _context7_client = Context7Client()
    return _context7_client

Context Shaping Utilities

# backend/app/services/context_shaper.py
from typing import list
from backend.app.services.context7_client import ContextDocument


class ContextShaper:
    """Shape and format retrieved context for AI prompts."""

    MAX_TOKENS = 4000  # Reserve space for prompt
    CHUNK_HEADER = "### Source: {title}"
    FOOTER = "\n\n---\n*Source: {source}*"

    def shape_for_prompt(
        self,
        documents: list[ContextDocument],
        query: str,
        max_chunks: int = 5,
        include_sources: bool = True,
    ) -> str:
        """
        Shape retrieved documents into prompt-safe format.

        Args:
            documents: Retrieved document chunks
            query: Original search query
            max_chunks: Maximum chunks to include
            include_sources: Include source citations

        Returns:
            Formatted context string
        """
        chunks = documents[:max_chunks]

        sections = []
        for i, doc in enumerate(chunks):
            header = f"## Chunk {i + 1}"
            if doc.metadata.title:
                header += f": {doc.metadata.title}"

            section = header
            section += f"\n\n{self._format_content(doc.content)}"

            if include_sources and doc.metadata.source_file:
                section += self.FOOTER.format(source=doc.metadata.source_file)

            sections.append(section)

        context = "\n\n".join(sections)

        # Ensure context fits in token limit
        context = self._truncate_to_token_limit(context, self.MAX_TOKENS)

        return context

    def _format_content(self, content: str) -> str:
        """Format content for readability."""
        # Normalize whitespace
        lines = content.split("\n")
        lines = [line.strip() for line in lines if line.strip()]
        return "\n".join(lines)

    def _truncate_to_token_limit(self, text: str, max_tokens: int) -> str:
        """Truncate text to fit within token limit."""
        # Rough estimate: 4 characters per token
        max_chars = max_tokens * 4

        if len(text) <= max_chars:
            return text

        # Truncate and add note
        truncated = text[:max_chars - 50]
        truncated = truncated.rsplit("\n", 1)[0]  # Don't cut mid-line
        truncated += "\n\n*... (context truncated for length)*"

        return truncated

    def format_for_chat(
        self,
        documents: list[ContextDocument],
        user_role: str,
    ) -> str:
        """
        Format context for chat widget display.

        Args:
            documents: Retrieved documents
            user_role: User's role for messaging

        Returns:
            User-friendly formatted context
        """
        if not documents:
            return "No relevant information found."

        formatted = []
        for doc in documents:
            if doc.metadata.title:
                formatted.append(f"**{doc.metadata.title}**")
            formatted.append(doc.content[:500])  # Limit per chunk
            formatted.append("")

        return "\n".join(formatted)


# Singleton
context_shaper = ContextShaper()

API Routes

# backend/app/api/knowledge/routes.py
from fastapi import APIRouter, Depends, HTTPException, status
from typing import Optional
from pydantic import BaseModel

from app.services.context7_client import (
    get_context7_client,
    DocumentMetadata,
    Context7Client,
)
from app.services.context_shaper import get_context_shaper, ContextShaper
from app.auth.jwt import get_current_user


router = APIRouter(prefix="/knowledge", tags=["knowledge"])


class IngestRequest(BaseModel):
    """Request to ingest a document."""
    content: str
    title: str
    description: Optional[str] = None
    module: str
    category: Optional[str] = None
    allowed_roles: list[str] = []
    school_id: Optional[str] = None


class SearchRequest(BaseModel):
    """Request to search knowledge base."""
    query: str
    module: Optional[str] = None
    max_chunks: int = 5
    min_similarity: float = 0.7


class SearchResponse(BaseModel):
    """Search response with shaped context."""
    documents: list[dict]
    context: str  # Shaped for prompt


@router.post("/ingest")
async def ingest_document(
    request: IngestRequest,
    current_user = Depends(get_current_user),
    client: Context7Client = Depends(get_context7_client),
) -> dict:
    """
    Ingest a document into the knowledge base.

    Requires admin or content-manager role.
    """
    # Check permissions
    if "admin" not in current_user.roles and "content-manager" not in current_user.roles:
        raise HTTPException(
            status_code=status.HTTP_403_FORBIDDEN,
            detail="Insufficient permissions to ingest documents",
        )

    # Build metadata
    metadata = DocumentMetadata(
        title=request.title,
        description=request.description,
        allowed_roles=request.allowed_roles or ["all"],
        school_id=request.school_id or current_user.school_id,
        module=request.module,
        category=request.category,
    )

    # Ingest
    result = client.ingest_document(
        content=request.content,
        metadata=metadata,
    )

    return {"status": "ingested", "document_id": result.get("id")}


@router.post("/search", response_model=SearchResponse)
async def search_knowledge(
    request: SearchRequest,
    current_user = Depends(get_current_user),
    client: Context7Client = Depends(get_context7_client),
    shaper: ContextShaper = Depends(get_context_shaper),
) -> SearchResponse:
    """
    Search the knowledge base.

    Returns shaped context suitable for AI prompts.
    """
    # Search with role and tenant filtering
    documents = client.search(
        query=request.query,
        filters={"module": request.module} if request.module else {},
        max_chunks=request.max_chunks,
        min_similarity=request.min_similarity,
        user_role=current_user.role,
        school_id=current_user.school_id,
    )

    # Shape for prompt
    context = shaper.shape_for_prompt(
        documents=documents,
        query=request.query,
        max_chunks=request.max_chunks,
    )

    return SearchResponse(
        documents=[
            {
                "id": doc.id,
                "title": doc.metadata.title,
                "content": doc.content[:200],
                "similarity": doc.similarity_score,
            }
            for doc in documents
        ],
        context=context,
    )


@router.get("/modules")
async def list_modules(
    current_user = Depends(get_current_user),
    client: Context7Client = Depends(get_context7_client),
) -> dict:
    """List available knowledge modules."""
    documents = client.list_documents(
        limit=1000,
    )

    modules = set()
    for doc in documents:
        if doc.get("metadata", {}).get("school_id") in [None, current_user.school_id]:
            modules.add(doc.get("metadata", {}).get("module"))

    return {"modules": sorted(modules)}

Frontend Hook

// frontend/hooks/useContext7Search.ts
import { useState, useCallback } from "react";

interface SearchResult {
  id: string;
  title: string;
  content: string;
  similarity: number;
}

interface SearchOptions {
  module?: string;
  maxChunks?: number;
}

export function useContext7Search() {
  const [results, setResults] = useState<SearchResult[]>([]);
  const [context, setContext] = useState<string>("");
  const [loading, setLoading] = useState(false);
  const [error, setError] = useState<string | null>(null);

  const search = useCallback(async (
    query: string,
    options: SearchOptions = {}
  ) => {
    setLoading(true);
    setError(null);

    try {
      const response = await fetch("/api/v1/knowledge/search", {
        method: "POST",
        headers: {
          "Content-Type": "application/json",
        },
        body: JSON.stringify({
          query,
          module: options.module,
          max_chunks: options.maxChunks || 5,
        }),
      });

      if (!response.ok) {
        throw new Error("Search failed");
      }

      const data = await response.json();

      setResults(data.documents);
      setContext(data.context);
    } catch (err) {
      setError(err instanceof Error ? err.message : "Search failed");
      setResults([]);
      setContext("");
    } finally {
      setLoading(false);
    }
  }, []);

  const clear = useCallback(() => {
    setResults([]);
    setContext("");
    setError(null);
  }, []);

  return {
    search,
    clear,
    results,
    context,
    loading,
    error,
  };
}

Document Organization

docs/
├── policies/
│   ├── attendance-policy.md
│   ├── fee-refund-policy.md
│   └── grading-policy.md
├── procedures/
│   ├── student-registration.md
│   ├── fee-payment.md
│   └── transcript-request.md
├── faq/
│   ├── fees-faq.md
│   ├── attendance-faq.md
│   └── grades-faq.md
└── handbooks/
    ├── student-handbook.md
    └── parent-handbook.md

Metadata Examples

# Fee policy document
DocumentMetadata(
    title="Fee Refund Policy",
    description="Guidelines for fee refunds and cancellations",
    module="fees",
    category="policy",
    allowed_roles=["admin", "accountant", "parent", "student"],
    school_id="school_001",
    language="en",
    source_file="docs/policies/fee-refund-policy.md",
)

# Student FAQ
DocumentMetadata(
    title="Fee Payment FAQ",
    description="Common questions about fee payment",
    module="fees",
    category="faq",
    allowed_roles=["student", "parent"],
    school_id="school_001",
    language="en",
    source_file="docs/faq/fees-faq.md",
)

# Staff procedure
DocumentMetadata(
    title="Student Registration Procedure",
    description="Step-by-step guide for registering new students",
    module="registration",
    category="procedure",
    allowed_roles=["admin", "registrar"],
    school_id="school_001",
    language="en",
    source_file="docs/procedures/student-registration.md",
)

Quality Checklist

No PII ingestion: Sensitive documents reviewed before upload
Query bounds: max_chunks, min_similarity prevent excessive results
Error handling: Graceful fallback when context unavailable
Source attribution: Clear indication when answers are document-based
Multi-tenancy: school_id filtering prevents cross-tenant access
Role filtering: allowed_roles field controls access
Token limits: Context truncation prevents prompt overflow

Integration Points

Skill	Integration
`@jwt-auth`	Extract role and school_id from JWT for access control
`@api-client`	API calls for ingest/search endpoints
`@chatkit-widget`	Provide context for AI-powered chat
`@fastapi-app`	Register knowledge API routes
`@error-handling`	Handle context retrieval errors gracefully

Multi-Tenancy

# Per-school namespace isolation
class Context7Client:
    # ...

    def search(self, query: str, school_id: str, **kwargs) -> list[ContextDocument]:
        # Always filter by school_id
        return super().search(
            query,
            school_id=school_id,
            filters={"school_id": school_id},
            **kwargs
        )

    def ingest_document(
        self,
        content: str,
        metadata: DocumentMetadata,
        school_id: str,
        **kwargs
    ) -> dict:
        # Always set school_id on metadata
        metadata.school_id = school_id
        return super().ingest_document(content, metadata, **kwargs)

Batch Ingestion Script

# scripts/ingest_docs.py
#!/usr/bin/env python3
"""Batch ingest documentation into Context7."""
import os
import sys
from pathlib import Path

# Add project to path
sys.path.insert(0, str(Path(__file__).parent.parent))

from app.services.context7_client import Context7Client, DocumentMetadata


def ingest_directory(
    dir_path: str,
    module: str,
    category: str,
    school_id: str,
    allowed_roles: list[str],
):
    """Ingest all documents in a directory."""
    client = Context7Client()
    dir_path = Path(dir_path)

    for file_path in dir_path.rglob("*.md"):
        print(f"Ingesting: {file_path}")

        metadata = DocumentMetadata(
            title=file_path.stem.replace("-", " ").title(),
            module=module,
            category=category,
            school_id=school_id,
            allowed_roles=allowed_roles,
            source_file=str(file_path),
        )

        try:
            client.ingest_from_file(str(file_path), metadata)
            print(f"  ✓ Ingested")
        except Exception as e:
            print(f"  ✗ Failed: {e}")


if __name__ == "__main__":
    import argparse

    parser = argparse.ArgumentParser(description="Batch ingest documents")
    parser.add_argument("--dir", required=True, help="Directory to ingest")
    parser.add_argument("--module", required=True, help="Document module")
    parser.add_argument("--category", required=True, help="Document category")
    parser.add_argument("--school-id", required=True, help="School ID")
    parser.add_argument("--roles", default="all", help="Comma-separated allowed roles")

    args = parser.parse_args()

    ingest_directory(
        args.dir,
        args.module,
        args.category,
        args.school_id,
        args.roles.split(","),
    )

Error Handling

# backend/app/services/context7_client.py

class Context7Error(Exception):
    """Base exception for Context7 errors."""
    pass


class Context7SearchError(Context7Error):
    """Error during context search."""
    pass


class Context7IngestError(Context7Error):
    """Error during document ingestion."""
    pass


# Usage in search
def search(self, *args, **kwargs) -> list[ContextDocument]:
    try:
        return self._search_impl(*args, **kwargs)
    except Exception as e:
        raise Context7SearchError(f"Search failed: {e}") from e


# Frontend fallback
function useContext7Search() {
  const { search, results, loading, error } = useContext7Search();

  // Fallback to general response if context fails
  const handleSearch = async (query: string) => {
    try {
      await search(query);
    } catch {
      // Use generic response
      setResults([]);
      setContext("");
    }
  };

  return { search: handleSearch, results, loading, error };
}

About this skill

Automatic

AI Engineer pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

aiskillstore / marketplace

skills/awais68/context7-integration/SKILL.md

View on GitHub ↗

Imported 8/10/2026Version v1Bundled 1 file · scripts

Illustrative Want to see what aiskillstore/context7-integration would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Related skills

Skills that do similar work, with their headline benchmark lift.

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

Context7 Integration Skill

Quick Reference

Project Structure

Context7 Client

Core Client Class

Context Shaping Utilities

API Routes

Frontend Hook

Document Organization

Metadata Examples

Quality Checklist

Integration Points

Multi-Tenancy

Batch Ingestion Script

Error Handling

SkillSafety

Source

Related skills

More in the registry