Ready to supercharge your AI agents?

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

Analyzing Component Quality · aiskillstore | DecimalAI

Agent Toolingby aiskillstore

Analyzing Component Quality

Expert at analyzing the quality and effectiveness of Claude Code components (agents, skills, commands, hooks). Assumes component is already technically valid. Evaluates description clarity, tool permissions, auto-invoke triggers, security, and usability to provide quality scores and improvement suggestions.

Maintained

SkillScore

SkillScore77/100

Test results 77

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

45%77%of test cases passed +32 pts

Without skill10 of 22

With skill17 of 22

9 fixed8 passed either way3 still failing2 broke

Measured on gemini-3.6-flash9/3/2026v118 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWhich file in `{baseDir}/references/` contains the full comprehensive standards breakdown for evaluating agents, skills, commands, and hooks?

Without the skillMissed

With the skillPassed

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

Use this skill

Your agent runs on

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

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

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

Install

pip install "decimalai>=0.15"

Add the skill

from decimalai import skillpkg

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

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

Start Claude Code with it

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

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

Add the DecimalAI plugin, once

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

Install this skill

/decimalai:install aiskillstore-analyzing-component-quality

The plugin needs python3 and curl on your machine.

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

Save it into your project

curl -fsSL --create-dirs -o .claude/skills/aiskillstore-analyzing-component-quality/SKILL.md https://app.decimal.ai/s/aiskillstore-analyzing-component-quality/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/aiskillstore-analyzing-component-quality/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 aiskillstore-analyzing-component-quality

Add it to your agent

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

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

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

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

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

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

Install

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

Add it to your agent

from decimalai import skillpkg

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

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

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

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

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-analyzing-component-quality/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/aiskillstore-analyzing-component-quality/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 aiskillstore-analyzing-component-quality

Add it to your agent

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

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

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

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

Install

pip install "decimalai[openai-agents]"

Add it to your agent

from decimalai import skillpkg

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

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

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

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-analyzing-component-quality/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/aiskillstore-analyzing-component-quality/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 aiskillstore-analyzing-component-quality

Add it to your agent

import json

from openai import OpenAI
from decimalai.openai import agent_config

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


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


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

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

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

Install

pip install "decimalai[openai]"

Add it to your agent

from decimalai import skillpkg

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

import json

from openai import OpenAI
from decimalai.openai import agent_config

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


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


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

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-analyzing-component-quality/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/aiskillstore-analyzing-component-quality/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 aiskillstore-analyzing-component-quality

Add it to your agent

import anthropic
from decimalai.anthropic import agent_config

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

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

Install

pip install "decimalai[anthropic]"

Add it to your agent

from decimalai import skillpkg

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

import anthropic
from decimalai.anthropic import agent_config

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-analyzing-component-quality/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/aiskillstore-analyzing-component-quality/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 aiskillstore-analyzing-component-quality

Add it to your agent

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

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


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


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

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

Install

pip install "decimalai[google-genai]"

Add it to your agent

from decimalai import skillpkg

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

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

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


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


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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-analyzing-component-quality/SKILL.md

Give it to your agent

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

client = genai.Client()
skill = Path(".agents/skills/aiskillstore-analyzing-component-quality/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 aiskillstore-analyzing-component-quality

Add it to your agent

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

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

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

Install

pip install "decimalai[langchain]" langchain-openai

Add it to your agent

from decimalai import skillpkg

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

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

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-analyzing-component-quality/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/aiskillstore-analyzing-component-quality/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 aiskillstore-analyzing-component-quality

Add it to your agent

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

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

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

Install

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

Add it to your agent

from decimalai import skillpkg

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

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-analyzing-component-quality/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 aiskillstore-analyzing-component-quality

Add it to your agent

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

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

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

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

Install

pip install "decimalai[adk]"

Add it to your agent

from decimalai import skillpkg

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

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

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

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-analyzing-component-quality/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/aiskillstore-analyzing-component-quality/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 aiskillstore-analyzing-component-quality

Add it to your agent

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

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

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

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

Install

pip install "decimalai[pydantic-ai]"

Add it to your agent

from decimalai import skillpkg

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

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

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

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-analyzing-component-quality/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/aiskillstore-analyzing-component-quality/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 aiskillstore-analyzing-component-quality

Add it to your agent

import decimalai.deepagents
from deepagents import create_deep_agent

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

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

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

Install

pip install "decimalai>=0.16" deepagents

Add it to your agent

from decimalai import skillpkg

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

import decimalai.deepagents
from deepagents import create_deep_agent

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-analyzing-component-quality/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/aiskillstore-analyzing-component-quality/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 aiskillstore-analyzing-component-quality

Add it to your agent

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

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

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

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

Install

pip install "decimalai>=0.16" agent-framework

Add it to your agent

from decimalai import skillpkg

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

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-analyzing-component-quality/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/aiskillstore-analyzing-component-quality/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 aiskillstore-analyzing-component-quality

Add it to your agent

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

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

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

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

Install

pip install "decimalai>=0.16" strands-agents

Add it to your agent

from decimalai import skillpkg

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

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

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-analyzing-component-quality/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/aiskillstore-analyzing-component-quality/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 aiskillstore-analyzing-component-quality

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

Save it into your project

curl -fsSL --create-dirs -o .agents/skills/aiskillstore-analyzing-component-quality/SKILL.md https://app.decimal.ai/s/aiskillstore-analyzing-component-quality/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-analyzing-component-quality/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/aiskillstore-analyzing-component-quality/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/aiskillstore-analyzing-component-quality.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 9/3/2026
Source: aiskillstore/marketplace ↗
License: Not recorded

Manage it in DecimalAI

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Use this skill

SKILL.md

Analyzing Component Quality

You are an expert at analyzing the quality and effectiveness of Claude Code plugin components. This skill provides systematic quality evaluation beyond technical validation.

Important Assumptions

This skill assumes components have already passed technical validation:

YAML frontmatter is valid
Required fields are present
Naming conventions are followed
File structure is correct

This skill focuses on QUALITY, not correctness.

Your Expertise

You specialize in:

Evaluating description clarity and specificity
Analyzing tool permission appropriateness
Assessing auto-invoke trigger effectiveness
Reviewing security implications
Measuring usability and developer experience
Identifying optimization opportunities

When to Use This Skill

Claude should automatically invoke this skill when:

Claude-component-builder creates or enhances a component
User asks "is this agent/skill good quality?"
Reviewing components for effectiveness
Optimizing existing components
Before publishing components to marketplace
During component audits

Quality Dimensions

1. Description Clarity (1-5)

What it measures: How well the description communicates purpose and usage

Excellent (5/5):

Specific about when to invoke
Clear capability statements
Well-defined triggers
Concrete examples

Poor (1/5):

Vague or generic
No clear triggers
Ambiguous purpose
Missing context

Example Analysis:

❌ Bad: "Helps with testing"
✓ Good: "Expert at writing Jest unit tests. Auto-invokes when user writes JavaScript functions or mentions 'test this code'."

2. Tool Permissions (1-5)

What it measures: Whether tool access follows principle of least privilege

Excellent (5/5):

Minimal necessary tools
Each tool justified
No dangerous combinations
Read-only when possible

Poor (1/5):

Excessive permissions
Unjustified Write/Bash access
Security risks
Overly broad access

Example Analysis:

❌ Bad: allowed-tools: Read, Write, Edit, Bash, Grep, Glob, Task
     (Why does a research skill need Write and Bash?)

✓ Good: allowed-tools: Read, Grep, Glob
     (Research only needs to read and search)

Special Case - Task Tool in Agents:

❌ Critical: Agent with Task tool
     (Subagents cannot spawn other subagents - Task won't work)

   Fix: Remove Task from agents, or convert to skill if orchestration needed

3. Auto-Invoke Triggers (1-5)

What it measures: How effectively the component will activate when needed

Excellent (5/5):

Specific, unambiguous triggers
Low false positive rate
Catches all relevant cases
Clear boundary conditions

Poor (1/5):

Too vague to match
Will trigger incorrectly
Misses obvious cases
Conflicting with other components

Example Analysis:

❌ Bad: "Use when user needs help"
     (Too vague, when don't they need help?)

✓ Good: "Auto-invokes when user asks 'how does X work?', 'where is Y implemented?', or 'explain the Z component'"
     (Specific phrases that clearly indicate intent)

4. Security Review (1-5)

What it measures: Security implications of the component

Excellent (5/5):

Minimal necessary permissions
Input validation considered
No dangerous patterns
Safe defaults
Security best practices

Poor (1/5):

Unrestricted tool access
No input validation
Dangerous command patterns
Security vulnerabilities

Example Analysis:

❌ Bad: Bash tool with user input directly in commands
     (Risk of command injection)

✓ Good: Read-only tools with validated inputs
     (Minimal attack surface)

5. Usability (1-5)

What it measures: Developer experience when using the component

Excellent (5/5):

Clear documentation
Usage examples
Helpful error messages
Good variable naming
Intuitive behavior

Poor (1/5):

Confusing documentation
No examples
Unclear behavior
Poor naming
Unexpected side effects

Example Analysis:

❌ Bad: No examples, unclear parameters
✓ Good: Multiple usage examples, clear parameter descriptions

Quality Analysis Framework

Step 1: Read Component

# Read the component file
Read agent/skill/command file

# Identify component type
- Agent: *.md in agents/
- Skill: SKILL.md in skills/*/
- Command: *.md in commands/
- Hook: hooks.json

Step 2: Score Each Dimension

Rate 1-5 for each quality dimension:

## Quality Scores

- **Description Clarity**: X/5 - [Specific reason]
- **Tool Permissions**: X/5 - [Specific reason]
- **Auto-Invoke Triggers**: X/5 - [Specific reason] (if applicable)
- **Security**: X/5 - [Specific reason]
- **Usability**: X/5 - [Specific reason]

**Overall Quality**: X.X/5 (average)

Step 3: Identify Specific Issues

## Issues Identified

### 🔴 Critical (Must Fix)
- [Issue 1: Description and impact]
- [Issue 2: Description and impact]

### 🟡 Important (Should Fix)
- [Issue 1: Description and impact]
- [Issue 2: Description and impact]

### 🟢 Minor (Nice to Have)
- [Issue 1: Description and impact]

Step 4: Provide Concrete Improvements

## Improvement Suggestions

### 1. [Improvement Title]
**Priority**: Critical/Important/Minor
**Current**: [What exists now]
**Suggested**: [What should be instead]
**Why**: [Rationale]
**Impact**: [How this improves quality]

Before:
```yaml
description: Helps with code

After:

description: Expert at analyzing code quality using ESLint, Prettier, and static analysis. Auto-invokes when user finishes writing code or asks 'is this code good?'


## Component-Specific Analysis

### For Agents

Focus on:
- When should this agent be invoked vs. doing inline?
- Are tools appropriate for the agent's mission?
- **Does agent have Task tool?** (Critical: subagents cannot spawn subagents)
- Does description make invocation criteria clear?
- Is the agent focused enough (single responsibility)?
- If orchestration is needed, should this be a skill instead?

### For Skills

Focus on:
- Are auto-invoke triggers specific and unambiguous?
- Will this activate at the right times?
- Is the skill documentation clear about when it activates?
- Does it have appropriate `{baseDir}` usage for resources?

### For Commands

Focus on:
- Is the command description clear about what it does?
- Are arguments well-documented?
- Is the prompt specific and actionable?
- Does it have clear success criteria?

### For Hooks

Focus on:
- Are matchers specific enough?
- Will the hook trigger appropriately?
- Is the hook type (prompt/command) appropriate?
- Are there security implications?

## Quality Scoring Guidelines

### Overall Quality Interpretation

- **4.5-5.0**: Excellent - Ready for marketplace
- **4.0-4.4**: Good - Minor improvements recommended
- **3.0-3.9**: Adequate - Important improvements needed
- **2.0-2.9**: Poor - Significant issues to address
- **1.0-1.9**: Critical - Major overhaul required

## Scripts Available

Located in `{baseDir}/scripts/`:

### `quality-scorer.py`
Automated quality scoring based on heuristics:
```bash
python {baseDir}/scripts/quality-scorer.py path/to/component.md

Output:

Automated quality scores (1-5) for each dimension
Flagged issues (missing examples, vague descriptions, etc.)
Comparison to quality standards

`effectiveness-analyzer.py`

Analyzes how effective the component will be:

python {baseDir}/scripts/effectiveness-analyzer.py path/to/SKILL.md

Output:

Auto-invoke trigger analysis (specificity, coverage)
Tool permission analysis (necessity, security)
Expected activation rate (high/medium/low)

`optimization-detector.py`

Identifies optimization opportunities:

python {baseDir}/scripts/optimization-detector.py path/to/component

Output:

Suggested simplifications
Performance considerations
Resource usage optimization

References Available

Located in {baseDir}/references/:

quality-standards.md: Comprehensive quality standards for all component types
best-practices-guide.md: Best practices for writing effective components
security-checklist.md: Security considerations for component design
usability-guidelines.md: Guidelines for developer experience

Quality Report Template

# Component Quality Analysis

**Component**: [Name]
**Type**: [Agent/Skill/Command/Hook]
**Location**: [File path]
**Date**: [Analysis date]

## Executive Summary

[1-2 sentence overall assessment]

**Overall Quality Score**: X.X/5 ([Excellent/Good/Adequate/Poor/Critical])

## Quality Scores

| Dimension | Score | Assessment |
|-----------|-------|------------|
| Description Clarity | X/5 | [Brief note] |
| Tool Permissions | X/5 | [Brief note] |
| Auto-Invoke Triggers | X/5 | [Brief note] |
| Security | X/5 | [Brief note] |
| Usability | X/5 | [Brief note] |

## Detailed Analysis

### Description Clarity (X/5)

**Strengths**:
- [What's good]

**Issues**:
- [What needs improvement]

**Recommendation**:
[Specific improvement]

### Tool Permissions (X/5)

**Current Tools**: [List]

**Analysis**:
- [Tool 1]: [Justified/Unnecessary]
- [Tool 2]: [Justified/Unnecessary]

**Recommendation**:
[Suggested tool list with rationale]

### Auto-Invoke Triggers (X/5)

**Current Triggers**:
> [Quote from description]

**Analysis**:
- Specificity: [High/Medium/Low]
- Coverage: [Complete/Partial/Missing]
- False Positive Risk: [Low/Medium/High]

**Recommendation**:
[Improved trigger description]

### Security (X/5)

**Risk Assessment**: [Low/Medium/High]

**Concerns**:
- [Concern 1]
- [Concern 2]

**Recommendation**:
[Security improvements]

### Usability (X/5)

**Developer Experience**:
- Documentation: [Clear/Unclear]
- Examples: [Present/Missing]
- Intuitiveness: [High/Low]

**Recommendation**:
[Usability improvements]

## Issues Summary

### 🔴 Critical Issues
1. [Issue with specific location and fix]
2. [Issue with specific location and fix]

### 🟡 Important Issues
1. [Issue with suggestion]
2. [Issue with suggestion]

### 🟢 Minor Issues
1. [Issue with suggestion]

## Improvement Suggestions

### Priority 1: [Title]
**Current**:
```[yaml/markdown]
[Current content]

Suggested:

[Improved content]

Rationale: [Why this improves quality] Impact: [Expected improvement in score]

Priority 2: [Title]

[Same format]

Strengths

[What this component does well]
[Good design decisions]

Recommended Actions

[Highest priority action]
[Next priority action]
[Additional improvements]

Predicted Impact

If all critical and important issues are addressed:

Current Quality: X.X/5
Projected Quality: X.X/5
Improvement: +X.X points

Conclusion

[Final assessment and recommendation: approve as-is, improve before use, or significant rework needed]


## Examples

### Example 1: Analyzing a Skill

**Input**: `skills/researching-best-practices/SKILL.md`

**Analysis**:
```markdown
# Quality Analysis: researching-best-practices

**Overall Quality**: 4.2/5 (Good)

## Quality Scores

- Description Clarity: 5/5 - Excellent, specific triggers
- Tool Permissions: 4/5 - Good, but includes Task unnecessarily
- Auto-Invoke Triggers: 5/5 - Very specific phrases
- Security: 5/5 - Read-only tools, safe
- Usability: 4/5 - Good docs, could use more examples

## Issues Identified

### 🟡 Important
- Includes Task tool but doesn't explain why
- Could benefit from usage examples in description

## Improvement Suggestions

### Remove Task Tool
**Current**: `allowed-tools: Read, Grep, Glob, WebSearch, WebFetch, Task`
**Suggested**: `allowed-tools: Read, Grep, Glob, WebSearch, WebFetch`
**Why**: Skill doesn't need to delegate to agents; it is the expert
**Impact**: Improves security score from 4/5 to 5/5

### Add Usage Example
**Add to description**:
```yaml
Example usage: When user asks "What's the best way to handle errors in React 2025?",
this skill activates and provides current best practices with code examples.

Why: Helps users understand when and how skill activates Impact: Improves usability from 4/5 to 5/5


### Example 2: Analyzing an Agent

**Input**: `agents/investigator.md`

**Analysis**:
```markdown
# Quality Analysis: investigator

**Overall Quality**: 3.8/5 (Adequate)

## Quality Scores

- Description Clarity: 3/5 - Somewhat vague
- Tool Permissions: 3/5 - Includes Task (circular)
- Security: 5/5 - No security concerns
- Usability: 4/5 - Well-documented

## Issues Identified

### 🟡 Important
- Description doesn't clearly state when to invoke agent vs. using skills directly
- Includes Task tool creating potential circular delegation
- Mission statement could be more specific

## Improvement Suggestions

### Clarify Invocation Criteria
**Current**: "Use when you need deep investigation..."
**Suggested**: "Invoke when investigation requires multiple phases, synthesizing 10+ files, or comparing implementations across codebases. For simple 'how does X work' questions, use skills directly."
**Why**: Prevents over-delegation to agent
**Impact**: Improves clarity from 3/5 to 5/5

### Remove Task Tool
**Current**: `tools: Read, Grep, Glob, WebSearch, WebFetch, Task`
**Suggested**: `tools: Read, Grep, Glob, WebSearch, WebFetch`
**Why**: Agents shouldn't delegate to other agents (circular)
**Impact**: Improves tool permissions from 3/5 to 5/5

Your Role

When analyzing component quality:

Assume validity: Component has passed technical validation
Focus on effectiveness: Will this component work well in practice?
Be specific: Quote exact issues and provide exact improvements
Score objectively: Use the 1-5 scale consistently
Prioritize issues: Critical > Important > Minor
Provide examples: Show before/after for each suggestion
Consider context: Marketplace components need higher standards
Think holistically: How does this fit in the ecosystem?

Important Reminders

Quality ≠ Correctness: Valid components can still be low quality
Subjective but principled: Use framework consistently
Constructive feedback: Focus on improvement, not criticism
Actionable suggestions: Every issue needs a concrete fix
Context matters: Standards vary by use case (internal vs. marketplace)
User perspective: Analyze from component user's viewpoint

Your analysis helps create more effective, secure, and usable Claude Code components.

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 v4 — 8/10/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

aiskillstore / marketplace

skills/c0ntr0lledcha0s/analyzing-component-quality/SKILL.md

View on GitHub ↗

Imported 8/10/2026Version v1Bundled 2 files · scripts

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

Other skills for the same job

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

aiskillstore/improving-componentsExpert at automatically applying improvements to Claude Code components based on quality analysis. Enhances descriptions, optimizes tool permissions, strengthens security, and improves usability. Works in conjunction with analyzing-component-quality skill.Close match+23 pts pass-rate lift

Related skills

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

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

Analyzing Component Quality

Important Assumptions

Your Expertise

When to Use This Skill

Quality Dimensions

1. Description Clarity (1-5)

2. Tool Permissions (1-5)

3. Auto-Invoke Triggers (1-5)

4. Security Review (1-5)

5. Usability (1-5)

Quality Analysis Framework

Step 1: Read Component

Step 2: Score Each Dimension

Step 3: Identify Specific Issues

Step 4: Provide Concrete Improvements

effectiveness-analyzer.py

optimization-detector.py

References Available

Quality Report Template

Priority 2: [Title]

Strengths

Recommended Actions

Predicted Impact

Conclusion

Your Role

Important Reminders

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry

`effectiveness-analyzer.py`

`optimization-detector.py`