Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Specification generator - 7 phase document chain producing product brief, PRD, architecture, epics, and issues with Codex review gates.
SkillScore64/100
Test results 64
3/3 safety checks passed
9%64%of test cases passed +55 pts
Passed 14 of 22 test cases with the skill, and 2 of 22 without it.
12 fixed2 passed either way8 still failing0 broke
Adds every file the skill has, pinned so you can update it. No account needed.
pip install "decimalai>=0.15"
decimalai skills add spec-generator
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"The same install from Python, for a notebook or a setup script.
pip install "decimalai>=0.15"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("spec-generator")
if result.exit_code:
raise SystemExit(result.problems)
print("Added. Start Claude Code with the command below.")claude --plugin-dir "$(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.
/plugin marketplace add decimal-labs/decimalai-claude-plugins
/plugin install decimalai@decimalai/decimalai:install spec-generatorThe plugin needs python3 and curl on your machine.
No Python or account. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/spec-generator/SKILL.md https://app.decimal.ai/s/spec-generator/SKILL.md.claude/skills/spec-generator/SKILL.mdThis gets SKILL.md only. The skill's 4 other files are not included.
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.
pip install "decimalai[claude-agent-sdk]"
decimalai skills add spec-generatorimport 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.
pip install "decimalai[claude-agent-sdk]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("spec-generator")
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.
.agents/skills/spec-generator/SKILL.mdimport asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query
skill = Path(".agents/skills/spec-generator/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 4 other files are not included.
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.
pip install "decimalai[openai-agents]"
decimalai skills add spec-generatorfrom 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.
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.
pip install "decimalai[openai-agents]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("spec-generator")
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.
.agents/skills/spec-generator/SKILL.mdfrom pathlib import Path
from agents import Agent, Runner
skill = Path(".agents/skills/spec-generator/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 4 other files are not included.
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.
pip install "decimalai[openai]"
decimalai skills add spec-generatorimport 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.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.
pip install "decimalai[openai]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("spec-generator")
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.
.agents/skills/spec-generator/SKILL.mdfrom pathlib import Path
from openai import OpenAI
client = OpenAI()
skill = Path(".agents/skills/spec-generator/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].messageThis gets SKILL.md only. The skill's 4 other files are not included.
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.
pip install "decimalai[anthropic]"
decimalai skills add spec-generatorimport 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()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.
pip install "decimalai[anthropic]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("spec-generator")
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.
.agents/skills/spec-generator/SKILL.mdfrom pathlib import Path
import anthropic
client = anthropic.Anthropic()
skill = Path(".agents/skills/spec-generator/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 4 other files are not included.
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.
pip install "decimalai[google-genai]"
decimalai skills add spec-generatorfrom 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)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.
pip install "decimalai[google-genai]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("spec-generator")
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.
.agents/skills/spec-generator/SKILL.mdfrom pathlib import Path
from google import genai
from google.genai import types
client = genai.Client()
skill = Path(".agents/skills/spec-generator/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 4 other files are not included.
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.
pip install "decimalai[langchain]" langchain-openai
decimalai skills add spec-generatorfrom 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!"}]})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.
pip install "decimalai[langchain]" langchain-openaifrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("spec-generator")
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.
.agents/skills/spec-generator/SKILL.mdfrom pathlib import Path
from langchain.agents import create_agent
skill = Path(".agents/skills/spec-generator/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 4 other files are not included.
CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add spec-generatorimport 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.
pip install "decimalai>=0.16" "crewai>=1.15.27"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("spec-generator")
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.
.agents/skills/spec-generator/SKILL.mdfrom 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 4 other files are not included.
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.
pip install "decimalai[adk]"
decimalai skills add spec-generatorfrom 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.
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.
pip install "decimalai[adk]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("spec-generator")
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.
.agents/skills/spec-generator/SKILL.mdfrom pathlib import Path
from google.adk.agents import LlmAgent
skill = Path(".agents/skills/spec-generator/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 4 other files are not included.
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.
pip install "decimalai[pydantic-ai]"
decimalai skills add spec-generatorfrom 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.
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.
pip install "decimalai[pydantic-ai]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("spec-generator")
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.
.agents/skills/spec-generator/SKILL.mdfrom pathlib import Path
from pydantic_ai import Agent
skill = Path(".agents/skills/spec-generator/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 4 other files are not included.
Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" deepagents
decimalai skills add spec-generatorimport 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.
pip install "decimalai>=0.16" deepagentsfrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("spec-generator")
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.
.agents/skills/spec-generator/SKILL.mdfrom pathlib import Path
from deepagents import create_deep_agent
skill = Path(".agents/skills/spec-generator/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 4 other files are not included.
Its own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" agent-framework
decimalai skills add spec-generatorimport 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.
pip install "decimalai>=0.16" agent-frameworkfrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("spec-generator")
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.
.agents/skills/spec-generator/SKILL.mdimport asyncio
from pathlib import Path
from agent_framework import Agent
skill = Path(".agents/skills/spec-generator/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 4 other files are not included.
Strands' own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" strands-agents
decimalai skills add spec-generatorfrom 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.
pip install "decimalai>=0.16" strands-agentsfrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("spec-generator")
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.
.agents/skills/spec-generator/SKILL.mdfrom pathlib import Path
from strands import Agent
skill = Path(".agents/skills/spec-generator/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 4 other files are not included.
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 spec-generatorNo Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.
curl -fsSL --create-dirs -o .agents/skills/spec-generator/SKILL.md https://app.decimal.ai/s/spec-generator/SKILL.md.agents/skills/spec-generator/SKILL.mdThis gets SKILL.md only. The skill's 4 other files are not included.
Give its text to your model as instructions. No account or package needed.
This gets SKILL.md only. The skill's 4 other files are not included.
Raw files: /s/spec-generator/SKILL.md · /s/spec-generator.json
Fetch the file and give its text to your model as instructions. No account or package needed.
curl -fsSL https://app.decimal.ai/s/spec-generator/SKILL.mdcurl -fsSL https://app.decimal.ai/s/spec-generator.jsonThis gets SKILL.md only. The skill's 4 other files are not included.
You don't need a DecimalAI account.
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.
Structured specification document generator producing a complete specification package (Product Brief, PRD, Architecture, Epics) through 6 sequential phases with multi-CLI analysis and interactive refinement. Document generation only - execution handoff to existing workflows (lite-plan, plan, req-plan).
Phase 0: Specification Study (Read specs/ + templates/ - mandatory prerequisite)
|
Phase 1: Discovery -> spec-config.json + discovery-context.json
| (includes spec_type selection)
Phase 1.5: Req Expansion -> refined-requirements.json (interactive discussion + CLI gap analysis)
| (-y auto mode: auto-expansion, skip interaction)
Phase 2: Product Brief -> product-brief.md + glossary.json (multi-CLI parallel analysis)
|
Phase 3: Requirements (PRD) -> requirements/ (_index.md + REQ-*.md + NFR-*.md)
| (RFC 2119 keywords, data model definitions)
Phase 4: Architecture -> architecture/ (_index.md + ADR-*.md, multi-CLI review)
| (state machine, config model, error handling, observability)
Phase 5: Epics & Stories -> epics/ (_index.md + EPIC-*.md)
|
Phase 6: Readiness Check -> readiness-report.md + spec-summary.md
| (terminology + scope consistency validation)
├── Pass (>=80%): Handoff to execution workflows
├── Review (60-79%): Handoff with caveats
└── Fail (<60%): Phase 6.5 Auto-Fix (max 2 iterations)
|
Phase 6.5: Auto-Fix -> Updated Phase 2-5 documents
|
└── Re-run Phase 6 validation
-y flag enables full auto modespec-config.json tracks completed phases; -c flag resumes from last checkpointDo NOT skip: Before performing any operations, you must completely read the following documents. Proceeding without reading the specifications will result in outputs that do not meet quality standards.
| Document | Purpose | Priority |
|---|---|---|
| specs/document-standards.md | Document format, frontmatter, naming conventions | P0 - Must read before execution |
| specs/quality-gates.md | Per-phase quality gate criteria and scoring | P0 - Must read before execution |
| Document | Purpose |
|---|---|
| templates/product-brief.md | Product brief document template |
| templates/requirements-prd.md | PRD document template |
| templates/architecture-doc.md | Architecture document template |
| templates/epics-template.md | Epic/Story document template |
Input Parsing:
|- Parse $ARGUMENTS: extract idea/topic, flags (-y, -c, -m)
|- Detect mode: new | continue
|- If continue: read spec-config.json, resume from first incomplete phase
|- If new: proceed to Phase 1
Phase 1: Discovery & Seed Analysis
|- Ref: phases/01-discovery.md
|- Generate session ID: SPEC-{slug}-{YYYY-MM-DD}
|- Parse input (text or file reference)
|- Gemini CLI seed analysis (problem, users, domain, dimensions)
|- Codebase exploration (conditional, if project detected)
|- Spec type selection: service|api|library|platform (interactive, -y defaults to service)
|- User confirmation (interactive, -y skips)
|- Output: spec-config.json, discovery-context.json (optional)
Phase 1.5: Requirement Expansion & Clarification
|- Ref: phases/01-5-requirement-clarification.md
|- CLI gap analysis: completeness scoring, missing dimensions detection
|- Multi-round interactive discussion (max 5 rounds)
| |- Round 1: present gap analysis + expansion suggestions
| |- Round N: follow-up refinement based on user responses
|- User final confirmation of requirements
|- Auto mode (-y): CLI auto-expansion without interaction
|- Output: refined-requirements.json
Phase 2: Product Brief
|- Ref: phases/02-product-brief.md
|- 3 parallel CLI analyses: Product (Gemini) + Technical (Codex) + User (Claude)
|- Synthesize perspectives: convergent themes + conflicts
|- Generate glossary.json (terminology from product brief + CLI analysis)
|- Interactive refinement (-y skips)
|- Output: product-brief.md (from template), glossary.json
Phase 3: Requirements / PRD
|- Ref: phases/03-requirements.md
|- Gemini CLI: expand goals into functional + non-functional requirements
|- Generate acceptance criteria per requirement
|- RFC 2119 behavioral constraints (MUST/SHOULD/MAY)
|- Core entity data model definitions
|- Glossary injection for terminology consistency
|- User priority sorting: MoSCoW (interactive, -y auto-assigns)
|- Output: requirements/ directory (_index.md + REQ-*.md + NFR-*.md, from template)
Phase 4: Architecture
|- Ref: phases/04-architecture.md
|- Gemini CLI: core components, tech stack, ADRs
|- Codebase integration mapping (conditional)
|- State machine generation (ASCII diagrams for lifecycle entities)
|- Configuration model definition (fields, types, defaults, constraints)
|- Error handling strategy (per-component classification + recovery)
|- Observability specification (metrics, logs, health checks)
|- Spec type profile injection (templates/profiles/{type}-profile.md)
|- Glossary injection for terminology consistency
|- Codex CLI: architecture challenge + review
|- Interactive ADR decisions (-y auto-accepts)
|- Output: architecture/ directory (_index.md + ADR-*.md, from template)
Phase 5: Epics & Stories
|- Ref: phases/05-epics-stories.md
|- Gemini CLI: requirement grouping into Epics, MVP subset tagging
|- Story generation: As a...I want...So that...
|- Dependency mapping (Mermaid)
|- Interactive validation (-y skips)
|- Output: epics/ directory (_index.md + EPIC-*.md, from template)
Phase 6: Readiness Check
|- Ref: phases/06-readiness-check.md
|- Cross-document validation (completeness, consistency, traceability)
|- Quality scoring per dimension
|- Terminology consistency validation (glossary compliance)
|- Scope containment validation (PRD <= Brief scope)
|- Output: readiness-report.md, spec-summary.md
|- Handoff options: lite-plan, req-plan, plan, issue:new, export only, iterate
Phase 6.5: Auto-Fix (conditional, triggered when Phase 6 score < 60%)
|- Ref: phases/06-5-auto-fix.md
|- Parse readiness-report.md for Error/Warning items
|- Group issues by originating Phase (2-5)
|- Re-generate affected sections via CLI with error context
|- Re-run Phase 6 validation
|- Max 2 iterations, then force handoff
|- Output: Updated Phase 2-5 documents
Complete: Full specification package ready for execution
Phase 6 → Handoff Bridge (conditional, based on user selection):
├─ lite-plan: Extract first MVP Epic description → direct text input
├─ plan / req-plan: Create WFS session + .brainstorming/ bridge files
│ ├─ guidance-specification.md (synthesized from spec outputs)
│ ├─ feature-specs/feature-index.json (Epic → Feature mapping)
│ └─ feature-specs/F-{num}-{slug}.md (one per Epic)
├─ issue:new: Create issues per Epic
└─ context-search-agent auto-discovers .brainstorming/
→ context-package.json.brainstorm_artifacts populated
→ action-planning-agent consumes: guidance_spec (P1) → feature_index (P2)
// Session ID generation
const slug = topic.toLowerCase().replace(/[^a-z0-9\u4e00-\u9fff]+/g, '-').slice(0, 40);
const date = new Date().toISOString().slice(0, 10);
const sessionId = `SPEC-${slug}-${date}`;
const workDir = `.workflow/.spec/${sessionId}`;
Bash(`mkdir -p "${workDir}"`);
.workflow/.spec/SPEC-{slug}-{YYYY-MM-DD}/
├── spec-config.json # Session configuration + phase state
├── discovery-context.json # Codebase exploration results (optional)
├── refined-requirements.json # Phase 1.5: Confirmed requirements after discussion
├── glossary.json # Phase 2: Terminology glossary for cross-doc consistency
├── product-brief.md # Phase 2: Product brief
├── requirements/ # Phase 3: Detailed PRD (directory)
│ ├── _index.md # Summary, MoSCoW table, traceability, links
│ ├── REQ-NNN-{slug}.md # Individual functional requirement
│ └── NFR-{type}-NNN-{slug}.md # Individual non-functional requirement
├── architecture/ # Phase 4: Architecture decisions (directory)
│ ├── _index.md # Overview, components, tech stack, links
│ └── ADR-NNN-{slug}.md # Individual Architecture Decision Record
├── epics/ # Phase 5: Epic/Story breakdown (directory)
│ ├── _index.md # Epic table, dependency map, MVP scope
│ └── EPIC-NNN-{slug}.md # Individual Epic with Stories
├── readiness-report.md # Phase 6: Quality report
└── spec-summary.md # Phase 6: One-page executive summary
spec-config.json serves as core state file:
{
"session_id": "SPEC-xxx-2026-02-11",
"seed_input": "User input text",
"input_type": "text",
"timestamp": "ISO8601",
"mode": "interactive",
"complexity": "moderate",
"depth": "standard",
"focus_areas": [],
"spec_type": "service",
"iteration_count": 0,
"iteration_history": [],
"seed_analysis": {
"problem_statement": "...",
"target_users": [],
"domain": "...",
"constraints": [],
"dimensions": []
},
"has_codebase": false,
"refined_requirements_file": "refined-requirements.json",
"phasesCompleted": [
{ "phase": 1, "name": "discovery", "output_file": "spec-config.json", "completed_at": "ISO8601" },
{ "phase": 1.5, "name": "requirement-clarification", "output_file": "refined-requirements.json", "discussion_rounds": 2, "completed_at": "ISO8601" },
{ "phase": 3, "name": "requirements", "output_dir": "requirements/", "output_index": "requirements/_index.md", "file_count": 8, "completed_at": "ISO8601" }
]
}
Resume mechanism: -c|--continue flag reads spec-config.json.phasesCompleted, resumes from first incomplete phase.
| Document | Purpose | When to Use |
|---|---|---|
| phases/01-discovery.md | Seed analysis and session setup | Phase start |
| templates/profiles/ | Spec type profiles | Spec type selection |
| specs/document-standards.md | Frontmatter format for spec-config.json | Config generation |
| Document | Purpose | When to Use |
|---|---|---|
| phases/01-5-requirement-clarification.md | Interactive requirement discussion workflow | Phase start |
| specs/quality-gates.md | Quality criteria for refined requirements | Validation |
| Document | Purpose | When to Use |
|---|---|---|
| phases/02-product-brief.md | Multi-CLI analysis orchestration | Phase start |
| templates/product-brief.md | Document template | Document generation |
| specs/glossary-template.json | Glossary schema | Glossary generation |
| Document | Purpose | When to Use |
|---|---|---|
| phases/03-requirements.md | PRD generation workflow | Phase start |
| templates/requirements-prd.md | Document template | Document generation |
| Document | Purpose | When to Use |
|---|---|---|
| phases/04-architecture.md | Architecture decision workflow | Phase start |
| templates/architecture-doc.md | Document template | Document generation |
| Document | Purpose | When to Use |
|---|---|---|
| phases/05-epics-stories.md | Epic/Story decomposition | Phase start |
| templates/epics-template.md | Document template | Document generation |
| Document | Purpose | When to Use |
|---|---|---|
| phases/06-readiness-check.md | Cross-document validation | Phase start |
| specs/quality-gates.md | Quality scoring criteria | Validation |
| Document | Purpose | When to Use |
|---|---|---|
| phases/06-5-auto-fix.md | Auto-fix workflow for readiness issues | When Phase 6 score < 60% |
| specs/quality-gates.md | Iteration exit criteria | Validation |
| Issue | Solution Document |
|---|---|
| Phase execution failed | Refer to the relevant Phase documentation |
| Output does not meet expectations | specs/quality-gates.md |
| Document format issues | specs/document-standards.md |
| Phase | Error | Blocking? | Action |
|---|---|---|---|
| Phase 1 | Empty input | Yes | Error and exit |
| Phase 1 | CLI seed analysis fails | No | Use basic parsing fallback |
| Phase 1.5 | Gap analysis CLI fails | No | Skip to user questions with basic prompts |
| Phase 1.5 | User skips discussion | No | Proceed with seed_analysis as-is |
| Phase 1.5 | Max rounds reached (5) | No | Force confirmation with current state |
| Phase 2 | Single CLI perspective fails | No | Continue with available perspectives |
| Phase 2 | All CLI calls fail | No | Generate basic brief from seed analysis |
| Phase 3 | Gemini CLI fails | No | Use codex fallback |
| Phase 4 | Architecture review fails | No | Skip review, proceed with initial analysis |
| Phase 5 | Story generation fails | No | Generate epics without detailed stories |
| Phase 6 | Validation CLI fails | No | Generate partial report with available data |
| Phase 6.5 | Auto-fix CLI fails | No | Log failure, proceed to handoff with Review status |
| Phase 6.5 | Max iterations reached | No | Force handoff, report remaining issues |
Gemini -> Codex -> Claude -> degraded mode (local analysis only)
Automatically, when a task matches. Triggers on generate spec, create specification, spec generator, workflow:spec.
Skills that do similar work, with their headline benchmark lift.
From the same source and nearby in the catalogue.