Ready to supercharge your AI agents?

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

Get Started Free →

Craft Document Management · leoyeai | DecimalAI

Documentationby leoyeai

Craft Document Management

Read and write Craft documents via the Craft Connect API.

Never made a case worse

SkillScore

SkillScore91/100

Test results 82 · Live runs 100

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

55%82%of test cases passed +27 pts

Without skill12 of 22

With skill18 of 22

6 fixed12 passed either way4 still failing0 broke

Measured on gemini-3.6-flash8/8/2026v119 comparable

Track record

Agent runs: 95; 47 in the last 30 days
Forks: 1

See one task, with and without the skill

One test taskI want to create a new folder named 'Archives' nested inside an existing folder 'fld_888' via Craft Connect API. What JSON payload structure should I send to POST $CRAFT_API_URL/folders?

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 leoyeai-craft
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("leoyeai-craft")
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 leoyeai-craft

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/leoyeai-craft/SKILL.md https://app.decimal.ai/s/leoyeai-craft/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-craft/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 leoyeai-craft

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("leoyeai-craft")
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/leoyeai-craft/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-craft/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 leoyeai-craft

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("leoyeai-craft")
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/leoyeai-craft/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-craft/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 leoyeai-craft

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("leoyeai-craft")
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/leoyeai-craft/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-craft/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 leoyeai-craft

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("leoyeai-craft")
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/leoyeai-craft/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-craft/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 leoyeai-craft

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("leoyeai-craft")
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/leoyeai-craft/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/leoyeai-craft/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 leoyeai-craft

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("leoyeai-craft")
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/leoyeai-craft/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-craft/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 leoyeai-craft

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("leoyeai-craft")
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/leoyeai-craft/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 leoyeai-craft

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("leoyeai-craft")
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/leoyeai-craft/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-craft/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 leoyeai-craft

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("leoyeai-craft")
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/leoyeai-craft/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-craft/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 leoyeai-craft

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("leoyeai-craft")
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/leoyeai-craft/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-craft/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 leoyeai-craft

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("leoyeai-craft")
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/leoyeai-craft/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-craft/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 leoyeai-craft

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("leoyeai-craft")
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/leoyeai-craft/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-craft/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 leoyeai-craft

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/leoyeai-craft/SKILL.md https://app.decimal.ai/s/leoyeai-craft/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-craft/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/leoyeai-craft/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-craft.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 8/8/2026
Source: LeoYeAI/openclaw-master-skills ↗
License: MIT

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

Craft Document Management

Operate on a Craft space via the Craft Connect REST API. Full CRUD on documents, blocks, folders, tasks, collections, and comments.

Requirements

curl — used for all API requests
CRAFT_API_URL — your Craft Connect API base URL (contains embedded link token for authentication)

Setup

Create a Craft Connect link in your Craft space (Settings → Connect → Create Link)
Copy the API base URL and store it in TOOLS.md under a Craft section:

CRAFT_API_URL=https://connect.craft.do/links/<LINK_ID>/api/v1

Read TOOLS.md before making any calls to retrieve the URL.

All calls use curl with -H "Content-Type: application/json" for writes and -H "Accept: application/json" for reads.

Important: URL-encode non-ASCII characters (e.g. Chinese) in query params.

API Reference

Connection Info

curl -s "$CRAFT_API_URL/connection"

Returns space ID, timezone, current time, and deep-link URL templates.

Discovery

# List all folders and locations
curl -s "$CRAFT_API_URL/folders"

# List documents in a location (unsorted | trash | templates | daily_notes)
curl -s "$CRAFT_API_URL/documents?location=unsorted"

# List documents in a folder
curl -s "$CRAFT_API_URL/documents?folderId=<FOLDER_ID>"

# With metadata (creation/modification dates, deep links)
curl -s "$CRAFT_API_URL/documents?location=unsorted&fetchMetadata=true"

# Date filters (ISO YYYY-MM-DD or: today, yesterday, tomorrow)
curl -s "$CRAFT_API_URL/documents?createdDateGte=2025-01-01&lastModifiedDateLte=today"

Search

# Search across ALL documents (URL-encode non-ASCII!)
curl -s "$CRAFT_API_URL/documents/search?include=<TERM>&fetchMetadata=true"

# Search within a specific document (with context blocks)
curl -s "$CRAFT_API_URL/blocks/search?blockId=<DOC_ID>&pattern=<REGEX>&beforeBlockCount=2&afterBlockCount=2"

# Filter search by folder or location
curl -s "$CRAFT_API_URL/documents/search?include=<TERM>&folderIds=<FOLDER_ID>"
curl -s "$CRAFT_API_URL/documents/search?include=<TERM>&location=daily_notes"

Documents

# Create document (defaults to unsorted)
curl -s -X POST "$CRAFT_API_URL/documents" \
  -H "Content-Type: application/json" \
  -d '{"documents": [{"title": "My Document"}]}'

# Create in a specific folder
curl -s -X POST "$CRAFT_API_URL/documents" \
  -H "Content-Type: application/json" \
  -d '{"documents": [{"title": "Doc"}], "destination": {"folderId": "<ID>"}}'

# Create as template
curl -s -X POST "$CRAFT_API_URL/documents" \
  -H "Content-Type: application/json" \
  -d '{"documents": [{"title": "Template"}], "destination": {"destination": "templates"}}'

# Delete (soft-delete to trash, recoverable)
curl -s -X DELETE "$CRAFT_API_URL/documents" \
  -H "Content-Type: application/json" \
  -d '{"documentIds": ["<DOC_ID>"]}'

# Move between locations
curl -s -X PUT "$CRAFT_API_URL/documents/move" \
  -H "Content-Type: application/json" \
  -d '{"documentIds": ["<ID>"], "destination": {"folderId": "<FOLDER_ID>"}}'

# Restore from trash
curl -s -X PUT "$CRAFT_API_URL/documents/move" \
  -H "Content-Type: application/json" \
  -d '{"documentIds": ["<ID>"], "destination": {"destination": "unsorted"}}'

Reading Content

# Get document content (JSON)
curl -s "$CRAFT_API_URL/blocks?id=<DOC_ID>" -H "Accept: application/json"

# Get daily note
curl -s "$CRAFT_API_URL/blocks?date=today" -H "Accept: application/json"

# Control depth (0=block only, 1=direct children, -1=all)
curl -s "$CRAFT_API_URL/blocks?id=<ID>&maxDepth=1"

# With metadata (comments, authors, timestamps)
curl -s "$CRAFT_API_URL/blocks?id=<ID>&fetchMetadata=true"

Writing Content

Two methods: markdown (recommended) and blocks JSON.

Method 1: Markdown (Recommended)

Best for most content. Craft parses markdown and auto-generates correct block types, indentation levels, and list styles.

curl -s -X POST "$CRAFT_API_URL/blocks" \
  -H "Content-Type: application/json" \
  -d '{
    "markdown": "## Heading\n\nParagraph\n\n- bullet 1\n- bullet 2",
    "position": {"position": "end", "pageId": "<DOC_ID>"}
  }'

Method 2: Blocks JSON

Use when you need explicit control over color, font, textStyle, or other properties not expressible in plain markdown.

curl -s -X POST "$CRAFT_API_URL/blocks" \
  -H "Content-Type: application/json" \
  -d '{
    "blocks": [
      {"type": "text", "textStyle": "h2", "markdown": "## Title"},
      {"type": "text", "color": "#00A3CB", "markdown": "<callout>💡 Info</callout>"}
    ],
    "position": {"position": "end", "pageId": "<DOC_ID>"}
  }'

Position Options

Position	Syntax
Append to document	`{"position": "end", "pageId": "<DOC_ID>"}`
Prepend to document	`{"position": "start", "pageId": "<DOC_ID>"}`
After a specific block	`{"position": "after", "siblingId": "<BLOCK_ID>"}`
Before a specific block	`{"position": "before", "siblingId": "<BLOCK_ID>"}`
Append to daily note	`{"position": "end", "date": "today"}`

Updating & Deleting Blocks

# Update (only provided fields change; others preserved)
curl -s -X PUT "$CRAFT_API_URL/blocks" \
  -H "Content-Type: application/json" \
  -d '{"blocks": [{"id": "<BLOCK_ID>", "markdown": "Updated", "font": "serif"}]}'

# Delete blocks (permanent!)
curl -s -X DELETE "$CRAFT_API_URL/blocks" \
  -H "Content-Type: application/json" \
  -d '{"blockIds": ["<ID1>", "<ID2>"]}'

# Move blocks between documents
curl -s -X PUT "$CRAFT_API_URL/blocks/move" \
  -H "Content-Type: application/json" \
  -d '{"blockIds": ["<ID>"], "position": {"position": "end", "pageId": "<DOC_ID>"}}'

Tasks

# List tasks (scopes: inbox, active, upcoming, logbook, document)
curl -s "$CRAFT_API_URL/tasks?scope=active"
curl -s "$CRAFT_API_URL/tasks?scope=document&documentId=<DOC_ID>"

# Create task in inbox
curl -s -X POST "$CRAFT_API_URL/tasks" \
  -H "Content-Type: application/json" \
  -d '{"tasks": [{"markdown": "Task text", "taskInfo": {"scheduleDate": "tomorrow"}, "location": {"type": "inbox"}}]}'

# Create task in daily note
curl -s -X POST "$CRAFT_API_URL/tasks" \
  -H "Content-Type: application/json" \
  -d '{"tasks": [{"markdown": "Task", "taskInfo": {"scheduleDate": "2025-01-20", "deadlineDate": "2025-01-22"}, "location": {"type": "dailyNote", "date": "today"}}]}'

# Create task in a document
curl -s -X POST "$CRAFT_API_URL/tasks" \
  -H "Content-Type: application/json" \
  -d '{"tasks": [{"markdown": "Task", "location": {"type": "document", "documentId": "<DOC_ID>"}}]}'

# Complete task
curl -s -X PUT "$CRAFT_API_URL/tasks" \
  -H "Content-Type: application/json" \
  -d '{"tasksToUpdate": [{"id": "<TASK_ID>", "taskInfo": {"state": "done"}}]}'

# Delete task
curl -s -X DELETE "$CRAFT_API_URL/tasks" \
  -H "Content-Type: application/json" \
  -d '{"idsToDelete": ["<TASK_ID>"]}'

Folders

# Create folder (root level)
curl -s -X POST "$CRAFT_API_URL/folders" \
  -H "Content-Type: application/json" \
  -d '{"folders": [{"name": "New Folder"}]}'

# Create nested folder
curl -s -X POST "$CRAFT_API_URL/folders" \
  -H "Content-Type: application/json" \
  -d '{"folders": [{"name": "Sub", "parentFolderId": "<PARENT_ID>"}]}'

# Delete folder (docs move to parent or Unsorted)
curl -s -X DELETE "$CRAFT_API_URL/folders" \
  -H "Content-Type: application/json" \
  -d '{"folderIds": ["<FOLDER_ID>"]}'

# Move folder
curl -s -X PUT "$CRAFT_API_URL/folders/move" \
  -H "Content-Type: application/json" \
  -d '{"folderIds": ["<ID>"], "destination": "root"}'
# or: "destination": {"parentFolderId": "<ID>"}

Collections (Structured Databases)

Collections are like Notion databases — structured tables with typed columns.

# List all collections
curl -s "$CRAFT_API_URL/collections"

# Create collection in a document
curl -s -X POST "$CRAFT_API_URL/collections" \
  -H "Content-Type: application/json" \
  -d '{
    "schema": {
      "name": "Tasks",
      "contentPropDetails": {"name": "Title"},
      "properties": [
        {"name": "Status", "type": "singleSelect", "options": [{"name": "Todo"}, {"name": "In Progress"}, {"name": "Done"}]},
        {"name": "Priority", "type": "singleSelect", "options": [{"name": "High"}, {"name": "Medium"}, {"name": "Low"}]},
        {"name": "Due Date", "type": "date"}
      ]
    },
    "position": {"position": "end", "pageId": "<DOC_ID>"}
  }'

# Get schema (use json-schema-items format to learn the property keys!)
curl -s "$CRAFT_API_URL/collections/<COL_ID>/schema?format=json-schema-items"
# ⚠️ IMPORTANT: schema returns auto-generated keys like "", "_2", "_3", "_4"
# You MUST read the schema first to know the correct keys for items

# Get items
curl -s "$CRAFT_API_URL/collections/<COL_ID>/items"

# Add items (use schema keys, NOT "title"!)
# First GET the schema to find the contentProp key (e.g. "_4" for title)
curl -s -X POST "$CRAFT_API_URL/collections/<COL_ID>/items" \
  -H "Content-Type: application/json" \
  -d '{"items": [{"<CONTENT_KEY>": "Item Title", "properties": {"<STATUS_KEY>": "Todo", "<PRIORITY_KEY>": "High"}}]}'

# Update items
curl -s -X PUT "$CRAFT_API_URL/collections/<COL_ID>/items" \
  -H "Content-Type: application/json" \
  -d '{"itemsToUpdate": [{"id": "<ITEM_ID>", "properties": {"<STATUS_KEY>": "Done"}}]}'

# Delete items
curl -s -X DELETE "$CRAFT_API_URL/collections/<COL_ID>/items" \
  -H "Content-Type: application/json" \
  -d '{"idsToDelete": ["<ITEM_ID>"]}'

# Update schema (replaces entirely — include ALL fields you want to keep)
curl -s -X PUT "$CRAFT_API_URL/collections/<COL_ID>/schema" \
  -H "Content-Type: application/json" \
  -d '{"schema": { ... }}'

Comments

curl -s -X POST "$CRAFT_API_URL/comments" \
  -H "Content-Type: application/json" \
  -d '{"comments": [{"blockId": "<BLOCK_ID>", "content": "Comment text"}]}'

File Upload

curl -s -X POST "$CRAFT_API_URL/upload?position=end&pageId=<DOC_ID>" \
  -H "Content-Type: application/octet-stream" \
  --data-binary @file.png

Position params: position (start|end|before|after) + pageId/date/siblingId.

Block Types & Formatting

Headings

# H1 Title          → textStyle: "h1"
## H2 Subtitle      → textStyle: "h2"
### H3 Heading      → textStyle: "h3"
#### H4 Strong      → textStyle: "h4"

Inline Styles

**bold**, *italic*, ~strikethrough~, `inline code`
[link text](https://url)
$(a+b)^2$                    ← inline equation

Highlights (9 solid + 5 gradient)

<highlight color="COLOR">text</highlight>

Solid: yellow, blue, red, green, purple, pink, mint, cyan, gray Gradient: gradient-blue, gradient-purple, gradient-red, gradient-yellow, gradient-brown

Lists

- bullet item           → listStyle: "bullet"
1. numbered item        → listStyle: "numbered"
- [ ] todo task         → listStyle: "task", taskInfo.state: "todo"
- [x] completed task    → listStyle: "task", taskInfo.state: "done"
+ toggle (collapsible)  → listStyle: "toggle"

Toggle (Collapsible) Lists — CRITICAL

Children MUST be indented 2 spaces to nest inside a toggle:

+ Parent toggle
  - Child 1 (hidden when collapsed)
  - Child 2
  + Nested toggle
    - Deep child

Use markdown mode only. indentationLevel in blocks JSON is silently ignored on insert.

Blockquote

> Quoted text

Produces block with decorations: ["quote"].

Dividers / Lines

Blocks JSON with lineStyle:

{"type": "line", "lineStyle": "extraLight", "markdown": "***"}
{"type": "line", "lineStyle": "light", "markdown": "****"}
{"type": "line", "lineStyle": "regular", "markdown": "*****"}
{"type": "line", "lineStyle": "strong", "markdown": "******"}

Markdown mode: --- produces extraLight by default.

Code Blocks

Markdown mode:

```python
def hello():
    print("Hello")
```

Blocks JSON (requires rawCode!):

{"type": "code", "language": "python", "rawCode": "def hello():\n    print('Hello')", "markdown": "```python\ndef hello():\n    print('Hello')\n```"}

Math Formula (TeX)

{"type": "code", "language": "math_formula", "rawCode": "x = \\frac{-b \\pm \\sqrt{b^2 - 4ac}}{2a}", "markdown": "```math_formula\nx = \\frac{-b \\pm \\sqrt{b^2 - 4ac}}{2a}\n```"}

Inline equation in markdown: $(a+b)^2 = a^2 + 2ab + b^2$

Tables

Markdown mode:

| Col A | Col B |
| --- | --- |
| val 1 | val 2 |

Images

Blocks JSON:

{"type": "image", "url": "https://example.com/photo.jpg", "markdown": "![Alt](https://example.com/photo.jpg)"}

Craft re-hosts the image and returns a https://r.craft.do/ URL.

Rich URL (Link Preview)

{"type": "richUrl", "url": "https://www.youtube.com/watch?v=..."}

Page / Card (Sub-pages)

{"type": "page", "textStyle": "page", "markdown": "Sub-page Title"}
{"type": "page", "textStyle": "card", "markdown": "Card Title"}

Then insert content inside using the returned page ID as pageId.

Callouts (Colored Blocks)

Require blocks JSON with color:

{"type": "text", "color": "#00A3CB", "markdown": "<callout>💡 Info</callout>"}

Common colors: #00A3CB (blue/info), #FF3B30 (red/warning), #34C759 (green/success), #FF9500 (orange/caution), #9862E8 (purple), #003382 (deep blue), #006744 (deep green), #864d00 (brown), #ef052a (bright red), #9ea4aa (gray).

Callouts support inline styles inside: <callout>**bold** and <highlight color="yellow">highlight</highlight></callout>

Fonts

Set via font in blocks JSON: (default), serif, mono, rounded.

Caption

{"type": "text", "textStyle": "caption", "markdown": "<caption>Small annotation</caption>"}

Task Blocks in Documents

{"type": "text", "listStyle": "task", "taskInfo": {"state": "todo"}, "markdown": "- [ ] Task"}

States: todo, done, canceled — NOT "completed".

Combination Example

{
  "type": "text",
  "font": "rounded",
  "textStyle": "h3",
  "color": "#9862E8",
  "markdown": "<callout>### ✨ Purple rounded heading callout</callout>"
}

Choosing Insert Method

Need	Use	Why
Text, lists, headings	Markdown	Clean, auto-detects types
Toggle lists with children	Markdown	Only way to get indentation right
Code blocks, tables	Either	Markdown is simpler; JSON needs `rawCode`
Colored callouts	Blocks JSON	Need `color` property
Custom fonts	Blocks JSON	Need `font` property
Captions	Blocks JSON	Need `textStyle: "caption"`
Images, richUrl, pages	Blocks JSON	Need `type` field
Line styles	Blocks JSON	Need `lineStyle`
Math formulas	Blocks JSON	Need `language: "math_formula"` + `rawCode`
Mixed content	Split calls	Combine markdown + blocks JSON

Gotchas & Lessons Learned

Toggle indentation: markdown mode with 2-space indent is the only way. indentationLevel in blocks JSON is silently ignored on insert.
Task state values: todo | done | canceled. NOT completed.
Position after/before: use siblingId (not blockId).
Position end/start: use pageId or date.
Code blocks in JSON mode: require rawCode field. Without it you get a validation error.
Collection item keys: the API docs say title but the real field name is the auto-generated contentProp key from the schema (e.g. _4). Always GET /collections/<id>/schema?format=json-schema-items first to discover the correct keys.
URL-encode search terms: Chinese and special characters in query params must be URL-encoded or curl returns 400.
Accept header: use application/json for reads. text/markdown may 502.
Document delete is soft: goes to trash, restorable via move. Block delete is permanent.
Large inserts: one POST can insert many blocks. Prefer fewer larger writes to avoid rate limits.
Image re-hosting: Craft downloads external images and re-hosts them at https://r.craft.do/. Your original URL is replaced.
Collections are experimental: the API may change. Always read the schema before writing items.

When it activates

Automatically, when a task matches. Use when the user asks to create, read, update, or search Craft documents, manage tasks, write daily notes, organize folders, work with collections (structured databases), or format rich content. Covers all block types including toggles, callouts, tables, code, highlights, math formulas, images, cards, and styled text. NOT for general note-taking to local files or unrelated document editors. Requires: CRAFT_API_URL (Craft Connect API base

About this skill

Automatic

Knowledge Management pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

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

LeoYeAI / openclaw-master-skills

skills/craft-connect/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 1 file

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

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

sundial-org/craftManage Craft notes, documents, and tasks via CLI. Use when the user asks to add notes, create documents, manage tasks, search their Craft documents, or work with daily notes. Craft is a note-taking app for macOS/iOS.Close match+77 pts pass-rate lift

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

Craft Document Management

Requirements

Setup

API Reference

Connection Info

Discovery

Search

Documents

Reading Content

Writing Content

Method 1: Markdown (Recommended)

Method 2: Blocks JSON

Position Options

Updating & Deleting Blocks

Tasks

Folders

Collections (Structured Databases)

Comments

File Upload

Block Types & Formatting

Headings

Inline Styles

Highlights (9 solid + 5 gradient)

Lists

Toggle (Collapsible) Lists — CRITICAL

Blockquote

Dividers / Lines

Code Blocks

Math Formula (TeX)

Tables

Images

Rich URL (Link Preview)

Page / Card (Sub-pages)

Callouts (Colored Blocks)

Fonts

Caption

Task Blocks in Documents

Combination Example

Choosing Insert Method

Gotchas & Lessons Learned

When it activates

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry