Ready to supercharge your AI agents?

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

Traceability Matrix Generator · arabelatso | DecimalAI

Testingby arabelatso

Traceability Matrix Generator

Builds traceability matrices connecting requirements to design documents to source code implementation, tracking the complete development lifecycle.

Maintained

SkillScore

SkillScore95/100

Test results 91 · Live runs 100

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

86%91%of test cases passed +5 pts

Without skill19 of 22

With skill20 of 22

3 fixed17 passed either way0 still failing2 broke

Measured on gemini-3.6-flash9/19/2026v1

Track record

Agent runs: 39; 17 in the last 30 days

See one task, with and without the skill

One test taskWhen rendering HTML rows in an interactive traceability matrix table, what standard CSS class names are assigned to identify table rows based on their completeness status?

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 arabelatso-traceability-matrix-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.

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("arabelatso-traceability-matrix-generator")
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 arabelatso-traceability-matrix-generator

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/arabelatso-traceability-matrix-generator/SKILL.md https://app.decimal.ai/s/arabelatso-traceability-matrix-generator/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/arabelatso-traceability-matrix-generator/SKILL.md

This gets SKILL.md only. The skill's 2 other files are 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 arabelatso-traceability-matrix-generator

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("arabelatso-traceability-matrix-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.

Copy SKILL.md

Save it in your project, as

.agents/skills/arabelatso-traceability-matrix-generator/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/arabelatso-traceability-matrix-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 2 other files are 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 arabelatso-traceability-matrix-generator

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("arabelatso-traceability-matrix-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.

Copy SKILL.md

Save it in your project, as

.agents/skills/arabelatso-traceability-matrix-generator/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/arabelatso-traceability-matrix-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 2 other files are 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 arabelatso-traceability-matrix-generator

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("arabelatso-traceability-matrix-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.

Copy SKILL.md

Save it in your project, as

.agents/skills/arabelatso-traceability-matrix-generator/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/arabelatso-traceability-matrix-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].message

This gets SKILL.md only. The skill's 2 other files are 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 arabelatso-traceability-matrix-generator

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("arabelatso-traceability-matrix-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.

Copy SKILL.md

Save it in your project, as

.agents/skills/arabelatso-traceability-matrix-generator/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/arabelatso-traceability-matrix-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 2 other files are 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 arabelatso-traceability-matrix-generator

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("arabelatso-traceability-matrix-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.

Copy SKILL.md

Save it in your project, as

.agents/skills/arabelatso-traceability-matrix-generator/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/arabelatso-traceability-matrix-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 2 other files are 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 arabelatso-traceability-matrix-generator

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("arabelatso-traceability-matrix-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.

Copy SKILL.md

Save it in your project, as

.agents/skills/arabelatso-traceability-matrix-generator/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/arabelatso-traceability-matrix-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 2 other files are 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 arabelatso-traceability-matrix-generator

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("arabelatso-traceability-matrix-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.

Copy SKILL.md

Save it in your project, as

.agents/skills/arabelatso-traceability-matrix-generator/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 2 other files are 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 arabelatso-traceability-matrix-generator

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("arabelatso-traceability-matrix-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.

Copy SKILL.md

Save it in your project, as

.agents/skills/arabelatso-traceability-matrix-generator/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/arabelatso-traceability-matrix-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 2 other files are 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 arabelatso-traceability-matrix-generator

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("arabelatso-traceability-matrix-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.

Copy SKILL.md

Save it in your project, as

.agents/skills/arabelatso-traceability-matrix-generator/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/arabelatso-traceability-matrix-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 2 other files are 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 arabelatso-traceability-matrix-generator

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("arabelatso-traceability-matrix-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.

Copy SKILL.md

Save it in your project, as

.agents/skills/arabelatso-traceability-matrix-generator/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/arabelatso-traceability-matrix-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 2 other files are 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 arabelatso-traceability-matrix-generator

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("arabelatso-traceability-matrix-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.

Copy SKILL.md

Save it in your project, as

.agents/skills/arabelatso-traceability-matrix-generator/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/arabelatso-traceability-matrix-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 2 other files are 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 arabelatso-traceability-matrix-generator

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("arabelatso-traceability-matrix-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.

Copy SKILL.md

Save it in your project, as

.agents/skills/arabelatso-traceability-matrix-generator/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/arabelatso-traceability-matrix-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 2 other files are 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 arabelatso-traceability-matrix-generator

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/arabelatso-traceability-matrix-generator/SKILL.md https://app.decimal.ai/s/arabelatso-traceability-matrix-generator/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/arabelatso-traceability-matrix-generator/SKILL.md

This gets SKILL.md only. The skill's 2 other files are 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/arabelatso-traceability-matrix-generator/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/arabelatso-traceability-matrix-generator.json

This gets SKILL.md only. The skill's 2 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 9/19/2026
Source: arabelatso/skills-4-se ↗
License: Apache-2.0

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

Traceability Matrix Generator

Build comprehensive traceability matrices linking requirements → design → implementation across the software development lifecycle.

What is a Traceability Matrix?

A traceability matrix documents relationships between:

Requirements: What the system must do (user stories, specs, features)
Design: How the system will be structured (architecture, APIs, components)
Implementation: Where requirements are coded (functions, classes, modules)

Benefits:

Ensure all requirements are implemented
Identify missing implementations or tests
Support compliance and auditing
Track impact of requirement changes
Find orphaned code without requirements

Workflow

Step 1: Identify and Collect Artifacts

Gather all traceability sources from the project.

Requirements Sources:

requirements.md, REQUIREMENTS.txt
User story documents
Issue tracker exports (Jira, GitHub Issues)
Product requirement documents (PRDs)
Feature specifications

Design Sources:

DESIGN.md, architecture documents
API specifications (OpenAPI, Swagger)
Database schemas
UML diagrams, architecture diagrams
Design decision records (ADRs)

Implementation Sources:

Source code files (*.py, *.java, *.js, etc.)
Module docstrings
Function/class comments with requirement IDs
Configuration files

Checklist:

Locate requirements documents
Find design documentation
Identify source code directories
Check for existing ID/tagging conventions
Verify file access and permissions

Step 2: Extract Requirements

Parse requirements and assign unique identifiers.

Common Requirement Formats:

Markdown with IDs:

## REQ-001: User Authentication
The system shall allow users to log in with email and password.

## REQ-002: Password Reset
Users shall be able to reset forgotten passwords via email.

User Stories:

### US-123: As a user, I want to search products
So that I can find items quickly

**Acceptance Criteria:**
- Search box on homepage
- Results display in < 1 second
- Filter by category

Numbered Lists:

1. **REQ-AUTH-001**: System must support OAuth 2.0
2. **REQ-AUTH-002**: Sessions expire after 24 hours
3. **REQ-DATA-001**: Data must be encrypted at rest

Extraction Script (Python):

import re
from pathlib import Path

def extract_requirements(file_path):
    """Extract requirements with IDs from markdown file."""
    requirements = []

    with open(file_path, 'r') as f:
        content = f.read()

    # Pattern: REQ-XXX or US-XXX or similar
    pattern = r'^#+\s*([A-Z]+-[A-Z0-9-]+):\s*(.+?)$'

    for match in re.finditer(pattern, content, re.MULTILINE):
        req_id = match.group(1)
        req_title = match.group(2)

        requirements.append({
            'id': req_id,
            'title': req_title,
            'source': file_path.name,
            'type': 'requirement'
        })

    return requirements

# Usage
reqs = extract_requirements(Path('requirements.md'))
for req in reqs:
    print(f"{req['id']}: {req['title']}")

Manual Extraction:

If documents lack IDs, assign them:

Original: "Users can filter search results"
→ Assign: REQ-SEARCH-001: Users can filter search results

For detailed requirement extraction patterns, see references/extraction_patterns.md.

Step 3: Extract Design Artifacts

Identify design elements and link to requirements.

Design Linking Patterns:

Explicit References in Design Docs:

## Authentication Service (REQ-001, REQ-002)

**Architecture:**
- OAuth 2.0 provider integration (REQ-AUTH-001)
- Session management module (REQ-AUTH-002)
- Password reset workflow (REQ-002)

**API Endpoints:**
- `POST /auth/login` - Implements REQ-001
- `POST /auth/reset` - Implements REQ-002

API Specifications:

# openapi.yaml
paths:
  /auth/login:
    post:
      summary: User login endpoint
      x-requirements: [REQ-001, REQ-AUTH-001]
      description: Implements user authentication

Architecture Diagrams:

[Component Diagram]
- AuthService → Implements REQ-001, REQ-002
- UserDatabase → Supports REQ-DATA-001
- EmailService → Enables REQ-002

Extraction Example:

def extract_design_links(design_file):
    """Extract design artifacts and linked requirements."""
    design_artifacts = []

    with open(design_file, 'r') as f:
        content = f.read()

    # Find headers with requirement references
    pattern = r'^#+\s*(.+?)\s*\((.+?)\)$'

    for match in re.finditer(pattern, content, re.MULTILINE):
        artifact_name = match.group(1)
        req_refs = match.group(2)

        # Parse requirement IDs
        req_ids = re.findall(r'[A-Z]+-[A-Z0-9-]+', req_refs)

        design_artifacts.append({
            'name': artifact_name,
            'requirements': req_ids,
            'source': design_file.name,
            'type': 'design'
        })

    return design_artifacts

Step 4: Scan Implementation

Search source code for requirement references.

Code Annotation Patterns:

Docstrings (Python):

def authenticate_user(email, password):
    """Authenticate user credentials.

    Implements: REQ-001, REQ-AUTH-001

    Args:
        email: User email address
        password: User password

    Returns:
        Authentication token if successful
    """
    # Implementation...

Comments (Java):

/**
 * User authentication service
 * @implements REQ-001 User login
 * @implements REQ-AUTH-001 OAuth support
 */
public class AuthenticationService {
    // Implementation...
}

Comments (JavaScript):

/**
 * Password reset functionality
 * Implements: REQ-002
 */
function resetPassword(email) {
    // Implementation...
}

Scanning Script:

def scan_code_for_requirements(code_dir):
    """Scan source code for requirement references."""
    implementations = []

    for file_path in Path(code_dir).rglob('*.py'):
        with open(file_path, 'r') as f:
            content = f.read()

        # Find requirement references in comments/docstrings
        matches = re.finditer(
            r'(?:Implements?|Satisfies|Covers):\s*([A-Z]+-[A-Z0-9-]+(?:,\s*[A-Z]+-[A-Z0-9-]+)*)',
            content,
            re.IGNORECASE
        )

        for match in matches:
            req_ids = [r.strip() for r in match.group(1).split(',')]

            # Find containing function/class
            lines_before = content[:match.start()].split('\n')
            for i in range(len(lines_before) - 1, -1, -1):
                if 'def ' in lines_before[i] or 'class ' in lines_before[i]:
                    code_element = lines_before[i].strip()
                    break
            else:
                code_element = "Unknown"

            implementations.append({
                'file': str(file_path),
                'element': code_element,
                'requirements': req_ids,
                'type': 'implementation'
            })

    return implementations

For comprehensive code scanning patterns, see references/code_scanning.md.

Step 5: Build the Traceability Matrix

Combine all extracted data into a structured matrix.

Data Structure:

traceability_matrix = {
    'REQ-001': {
        'requirement': {
            'id': 'REQ-001',
            'title': 'User Authentication',
            'source': 'requirements.md'
        },
        'design': [
            {
                'name': 'Authentication Service',
                'source': 'design.md'
            }
        ],
        'implementation': [
            {
                'file': 'auth/service.py',
                'element': 'def authenticate_user()'
            }
        ]
    },
    # ... more requirements
}

Building Script:

def build_traceability_matrix(requirements, design_artifacts, implementations):
    """Build complete traceability matrix."""
    matrix = {}

    # Initialize with requirements
    for req in requirements:
        matrix[req['id']] = {
            'requirement': req,
            'design': [],
            'implementation': []
        }

    # Link design artifacts
    for design in design_artifacts:
        for req_id in design.get('requirements', []):
            if req_id in matrix:
                matrix[req_id]['design'].append(design)

    # Link implementations
    for impl in implementations:
        for req_id in impl.get('requirements', []):
            if req_id in matrix:
                matrix[req_id]['implementation'].append(impl)

    return matrix

Step 6: Generate Output Formats

Export matrix in multiple formats for different audiences.

Markdown Table:

# Traceability Matrix

| Requirement | Title | Design | Implementation | Status |
|-------------|-------|--------|----------------|--------|
| REQ-001 | User Authentication | Authentication Service | auth/service.py::authenticate_user() | ✓ Complete |
| REQ-002 | Password Reset | Auth Service | auth/service.py::reset_password() | ✓ Complete |
| REQ-003 | Data Encryption | - | - | ⚠ Missing |

Generation Script:

def generate_markdown_table(matrix):
    """Generate markdown traceability table."""
    lines = [
        "# Traceability Matrix\n",
        "| Requirement | Title | Design | Implementation | Status |",
        "|-------------|-------|--------|----------------|--------|"
    ]

    for req_id, data in sorted(matrix.items()):
        req = data['requirement']
        design = ', '.join([d['name'] for d in data['design']]) or '-'
        impl = ', '.join([f"{i['file']}::{i['element']}" for i in data['implementation']]) or '-'

        # Determine status
        if data['design'] and data['implementation']:
            status = '✓ Complete'
        elif data['design'] or data['implementation']:
            status = '⚠ Partial'
        else:
            status = '❌ Missing'

        lines.append(f"| {req_id} | {req['title']} | {design} | {impl} | {status} |")

    return '\n'.join(lines)

CSV Export:

import csv

def generate_csv(matrix, output_file):
    """Generate CSV traceability matrix."""
    with open(output_file, 'w', newline='') as f:
        writer = csv.writer(f)

        # Header
        writer.writerow([
            'Requirement ID',
            'Title',
            'Source',
            'Design Artifacts',
            'Implementation Files',
            'Status'
        ])

        # Data rows
        for req_id, data in sorted(matrix.items()):
            req = data['requirement']
            design_str = '; '.join([d['name'] for d in data['design']])
            impl_str = '; '.join([f"{i['file']}" for i in data['implementation']])

            if data['design'] and data['implementation']:
                status = 'Complete'
            elif data['design'] or data['implementation']:
                status = 'Partial'
            else:
                status = 'Missing'

            writer.writerow([
                req_id,
                req['title'],
                req['source'],
                design_str,
                impl_str,
                status
            ])

HTML Interactive Visualization:

def generate_html_visualization(matrix, output_file):
    """Generate interactive HTML traceability matrix."""
    html = """
<!DOCTYPE html>
<html>
<head>
    <title>Traceability Matrix</title>
    <style>
        table { border-collapse: collapse; width: 100%; }
        th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }
        th { background-color: #4CAF50; color: white; }
        tr:nth-child(even) { background-color: #f2f2f2; }
        .complete { color: green; }
        .partial { color: orange; }
        .missing { color: red; }
        .filter { margin: 20px 0; }
    </style>
</head>
<body>
    <h1>Traceability Matrix</h1>

    <div class="filter">
        <label>Filter by status:</label>
        <select id="statusFilter" onchange="filterTable()">
            <option value="all">All</option>
            <option value="complete">Complete</option>
            <option value="partial">Partial</option>
            <option value="missing">Missing</option>
        </select>
    </div>

    <table id="matrixTable">
        <thead>
            <tr>
                <th>Requirement</th>
                <th>Title</th>
                <th>Design</th>
                <th>Implementation</th>
                <th>Status</th>
            </tr>
        </thead>
        <tbody>
"""

    for req_id, data in sorted(matrix.items()):
        req = data['requirement']
        design = '<br>'.join([d['name'] for d in data['design']]) or '-'
        impl = '<br>'.join([f"{i['file']}" for i in data['implementation']]) or '-'

        if data['design'] and data['implementation']:
            status_class = 'complete'
            status_text = '✓ Complete'
        elif data['design'] or data['implementation']:
            status_class = 'partial'
            status_text = '⚠ Partial'
        else:
            status_class = 'missing'
            status_text = '❌ Missing'

        html += f"""
            <tr class="{status_class}">
                <td>{req_id}</td>
                <td>{req['title']}</td>
                <td>{design}</td>
                <td>{impl}</td>
                <td class="{status_class}">{status_text}</td>
            </tr>
"""

    html += """
        </tbody>
    </table>

    <script>
        function filterTable() {
            var filter = document.getElementById('statusFilter').value;
            var rows = document.querySelectorAll('#matrixTable tbody tr');

            rows.forEach(function(row) {
                if (filter === 'all' || row.classList.contains(filter)) {
                    row.style.display = '';
                } else {
                    row.style.display = 'none';
                }
            });
        }
    </script>
</body>
</html>
"""

    with open(output_file, 'w') as f:
        f.write(html)

Step 7: Analyze and Report Gaps

Identify incomplete traceability and generate recommendations.

Gap Analysis:

def analyze_gaps(matrix):
    """Identify gaps in traceability."""
    gaps = {
        'missing_design': [],      # Requirements without design
        'missing_implementation': [], # Requirements without code
        'complete': [],            # Fully traced requirements
        'orphaned_code': []        # Code without requirements (if tracked)
    }

    for req_id, data in matrix.items():
        req = data['requirement']

        if not data['design'] and not data['implementation']:
            # Completely untraced
            gaps['missing_design'].append(req_id)
            gaps['missing_implementation'].append(req_id)
        elif not data['design']:
            gaps['missing_design'].append(req_id)
        elif not data['implementation']:
            gaps['missing_implementation'].append(req_id)
        else:
            gaps['complete'].append(req_id)

    return gaps

def generate_gap_report(gaps):
    """Generate gap analysis report."""
    report = ["# Traceability Gap Analysis\n"]

    report.append(f"## Summary")
    report.append(f"- ✓ Complete: {len(gaps['complete'])} requirements")
    report.append(f"- ⚠ Missing Design: {len(gaps['missing_design'])} requirements")
    report.append(f"- ⚠ Missing Implementation: {len(gaps['missing_implementation'])} requirements\n")

    if gaps['missing_design']:
        report.append("## Requirements Without Design")
        for req_id in gaps['missing_design']:
            report.append(f"- {req_id}")
        report.append("")

    if gaps['missing_implementation']:
        report.append("## Requirements Without Implementation")
        for req_id in gaps['missing_implementation']:
            report.append(f"- {req_id}")
        report.append("")

    report.append("## Recommendations")
    if gaps['missing_design']:
        report.append("- Create design documents for undesigned requirements")
    if gaps['missing_implementation']:
        report.append("- Implement missing requirements or update requirement status")

    return '\n'.join(report)

Coverage Metrics:

def calculate_coverage(matrix):
    """Calculate traceability coverage metrics."""
    total = len(matrix)
    with_design = sum(1 for data in matrix.values() if data['design'])
    with_impl = sum(1 for data in matrix.values() if data['implementation'])
    complete = sum(1 for data in matrix.values()
                   if data['design'] and data['implementation'])

    return {
        'total_requirements': total,
        'design_coverage': (with_design / total * 100) if total > 0 else 0,
        'implementation_coverage': (with_impl / total * 100) if total > 0 else 0,
        'complete_coverage': (complete / total * 100) if total > 0 else 0
    }

Complete Example

from pathlib import Path

# Step 1: Collect artifacts
req_file = Path('requirements.md')
design_file = Path('design.md')
code_dir = Path('src/')

# Step 2-4: Extract data
requirements = extract_requirements(req_file)
design_artifacts = extract_design_links(design_file)
implementations = scan_code_for_requirements(code_dir)

# Step 5: Build matrix
matrix = build_traceability_matrix(requirements, design_artifacts, implementations)

# Step 6: Generate outputs
with open('traceability.md', 'w') as f:
    f.write(generate_markdown_table(matrix))

generate_csv(matrix, 'traceability.csv')
generate_html_visualization(matrix, 'traceability.html')

# Step 7: Analyze gaps
gaps = analyze_gaps(matrix)
coverage = calculate_coverage(matrix)

print(f"Coverage: {coverage['complete_coverage']:.1f}% complete")
print(generate_gap_report(gaps))

Tips

Establish ID conventions early: Use consistent prefixes (REQ-, US-, FEAT-)
Automate where possible: Use scripts for large codebases
Keep matrix updated: Regenerate when requirements or code changes
Tag code consistently: Enforce requirement references in code reviews
Start simple: Begin with requirements→implementation, add design later
Use version control: Track matrix changes alongside code changes
Integrate with CI/CD: Auto-generate matrix on commits

Common Use Cases

Compliance Auditing:

Demonstrate all requirements are implemented
Provide evidence for regulatory reviews
Track safety-critical requirement coverage

Impact Analysis:

Identify affected code when requirements change
Find which tests need updating
Assess scope of feature modifications

Quality Assurance:

Verify implementation completeness
Ensure no orphaned code
Track requirement fulfillment

References

For detailed information:

references/extraction_patterns.md - Requirement parsing patterns for various formats
references/code_scanning.md - Code annotation conventions and scanning techniques

When it activates

Automatically, when a task matches. Use when you need to verify implementation completeness, ensure all requirements are implemented in code, generate compliance documentation, audit requirement coverage, identify orphaned code, or create traceability reports for stakeholders. Supports parsing requirements from Markdown, Word, and PDFs; extracting design from architecture docs and API

About this skill

Automatic

QA & Test Engineering pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/27/2026

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

arabelatso / skills-4-se

skills/traceability-matrix-generator/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/27/2026Version v1Bundled 2 files

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

Related skills

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

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

Traceability Matrix Generator

What is a Traceability Matrix?

Workflow

Step 1: Identify and Collect Artifacts

Step 2: Extract Requirements

Step 3: Extract Design Artifacts

Step 4: Scan Implementation

Step 5: Build the Traceability Matrix

Step 6: Generate Output Formats

Step 7: Analyze and Report Gaps

Complete Example

Tips

Common Use Cases

References

When it activates

SkillSafety

Source

Related skills

More in the registry