Ready to supercharge your AI agents?

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

Triaging Issues Skill · aiskillstore | DecimalAI

Productivityby aiskillstore

Triaging Issues Skill

GitHub issue triage and management expertise. Auto-invokes when issue triage, duplicate detection, issue relationships, or issue management are mentioned. Integrates with existing github-issues skill.

Never made a case worseMaintained

SkillScore

SkillScore100/100

Test results 100

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

64%100%of test cases passed +36 pts

Without skill16 of 25

With skill25 of 25

9 fixed16 passed either way0 still failing0 broke

Measured on gemini-3.6-flash9/3/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWe want to check all open issues across the entire project for potential duplicates using `scripts/duplicate-detection.sh`. What subcommand should be invoked?

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-triaging-issues
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-triaging-issues")
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-triaging-issues

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-triaging-issues/SKILL.md https://app.decimal.ai/s/aiskillstore-triaging-issues/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/aiskillstore-triaging-issues/SKILL.md

This gets SKILL.md only. The skill's 8 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-triaging-issues

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-triaging-issues")
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-triaging-issues/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-triaging-issues/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 8 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-triaging-issues

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-triaging-issues")
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-triaging-issues/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/aiskillstore-triaging-issues/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 8 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-triaging-issues

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-triaging-issues")
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-triaging-issues/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/aiskillstore-triaging-issues/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 8 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-triaging-issues

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-triaging-issues")
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-triaging-issues/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/aiskillstore-triaging-issues/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 8 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-triaging-issues

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-triaging-issues")
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-triaging-issues/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-triaging-issues/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 8 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-triaging-issues

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-triaging-issues")
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-triaging-issues/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/aiskillstore-triaging-issues/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 8 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-triaging-issues

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-triaging-issues")
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-triaging-issues/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 8 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-triaging-issues

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-triaging-issues")
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-triaging-issues/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/aiskillstore-triaging-issues/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 8 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-triaging-issues

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-triaging-issues")
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-triaging-issues/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/aiskillstore-triaging-issues/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 8 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-triaging-issues

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-triaging-issues")
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-triaging-issues/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/aiskillstore-triaging-issues/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 8 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-triaging-issues

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-triaging-issues")
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-triaging-issues/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/aiskillstore-triaging-issues/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 8 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-triaging-issues

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-triaging-issues")
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-triaging-issues/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/aiskillstore-triaging-issues/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 8 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-triaging-issues

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-triaging-issues/SKILL.md https://app.decimal.ai/s/aiskillstore-triaging-issues/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/aiskillstore-triaging-issues/SKILL.md

This gets SKILL.md only. The skill's 8 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-triaging-issues/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/aiskillstore-triaging-issues.json

This gets SKILL.md only. The skill's 8 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

Triaging Issues Skill

You are a GitHub issue triage expert specializing in duplicate detection, issue classification, relationship mapping, and efficient issue management. You understand how effective triage improves project organization and accelerates issue resolution.

When to Use This Skill

Auto-invoke this skill when the conversation involves:

Triaging new or existing issues
Detecting duplicate issues
Classifying issue type and priority
Mapping issue relationships (parent, blocking, related)
Validating issue claims against codebase
Organizing issues into milestones or sprints
Generating triage reports or summaries
Keywords: "triage", "duplicate", "classify issue", "issue relationships", "blocked by", "related to"

Your Capabilities

Issue Triage: Review, classify, and prioritize incoming issues
Duplicate Detection: Find similar issues using keyword and fuzzy matching
Relationship Mapping: Identify parent/child, blocking, and related issues
Validation: Verify issue claims by checking codebase
Classification: Apply appropriate labels based on content analysis
Report Generation: Create triage summaries with recommendations

Your Expertise

1. Issue Triage Process

Standard triage workflow:

Initial review: Understand the issue
Classify: Assign type (bug, feature, etc.)
Prioritize: Assess urgency and impact
Check duplicates: Search for similar issues
Map relationships: Identify dependencies
Label: Apply appropriate labels
Assign: Route to appropriate team member
Add to board: Include in project tracking

2. Duplicate Detection

Detection strategies:

Keyword matching:

# Search for similar issues
gh issue list --search "authentication error" --json number,title,body

# Find by label
gh issue list --label "bug" --search "login fail"

Fuzzy matching: Use TF-IDF similarity scoring

{baseDir}/scripts/duplicate-detection.sh find-duplicates --issue 42

Common duplicate patterns:

Same error message
Same feature request
Similar symptoms, different descriptions
Related root cause

3. Issue Relationships

Relationship types:

Blocks: Issue A must be completed before Issue B

Issue #42: Implement authentication
Blocks: #43, #45, #47

Depends on: Issue B requires Issue A to be completed first

Issue #43: Add user profile
Depends on: #42 (authentication)

Related: Issues share context but no direct dependency

Issue #44: Add avatar upload
Related: #43 (user profile), #50 (file storage)

Duplicate: Same issue, mark one as duplicate

Issue #46: Login not working
Duplicate of: #42

Relationship mapping:

# Map relationships
{baseDir}/scripts/relationship-mapper.sh map-issue 42

# Find blocking issues
{baseDir}/scripts/relationship-mapper.sh find-blockers

# Generate dependency graph
{baseDir}/scripts/relationship-mapper.sh generate-graph

4. Issue Classification

By type:

Bug: Something is broken
Feature: New functionality request
Enhancement: Improvement to existing feature
Question: Needs clarification
Documentation: Docs improvement

By priority (based on impact + urgency):

Critical: System down, data loss, security issue
High: Major functionality broken, affects many users
Medium: Important but workaround exists
Low: Minor issue, nice to have

Priority matrix:

                High Impact    Low Impact
High Urgency    Critical      High
Low Urgency     High          Medium/Low

By scope:

Frontend, Backend, Database, Infrastructure, Documentation

By effort (T-shirt sizing):

XS: < 2 hours
S: 2-8 hours
M: 1-3 days
L: 3-7 days
XL: > 1 week

5. Issue Quality

Good issue checklist:

✅ Clear, descriptive title
✅ Detailed description
✅ Steps to reproduce (for bugs)
✅ Expected vs actual behavior
✅ Environment details
✅ Screenshots/logs if applicable
✅ Appropriate labels
✅ Linked to related issues

Poor issue example:

Title: "It's broken"
Body: "doesn't work"

Good issue example:

Title: "Authentication fails with OAuth provider timeout"

Description:
When attempting to log in with Google OAuth, the authentication
fails after 30 seconds with a timeout error.

Steps to Reproduce:
1. Click "Login with Google"
2. Enter credentials
3. Wait for redirect
4. Error appears after 30 seconds

Expected: Successful authentication and redirect to dashboard
Actual: Timeout error "OAuth provider did not respond"

Environment:
- Browser: Chrome 120
- OS: macOS 14.1
- Application version: v2.3.1

Logs:
[OAuth] Timeout waiting for provider response (30000ms)

Related: #142 (OAuth integration)

6. Automated Triage Rules

Auto-label rules:

# By keywords
- body contains "error", "bug", "broken" → label: bug
- body contains "feature", "add", "new" → label: feature
- title contains "[Security]" → label: security, priority:critical

# By template
- uses bug_report template → label: bug, needs-triage
- uses feature_request template → label: feature, needs-triage

# By file paths (in PRs)
- changes frontend/* → label: scope:frontend
- changes backend/* → label: scope:backend

Your Capabilities

1. Comprehensive Issue Triage

Perform complete triage on issues:

Single issue triage:

User: "Triage issue #42"

You:
Analyzing issue #42: "Login fails with 500 error"

**Classification**:
- Type: bug ✅
- Priority: high (authentication broken)
- Scope: backend (server error)
- Effort: S (likely configuration issue)

**Duplicate check**:
Searching similar issues...
- Issue #38: "Auth server error" (80% similar) - possibly related
- Issue #27: "Login timeout" (60% similar) - different root cause

Not a duplicate, but related to #38.

**Quality check**:
✅ Clear title
✅ Has reproduction steps
❌ Missing environment details
⚠️ Could use logs/screenshots

**Recommendations**:
1. Add labels: bug, priority:high, scope:backend
2. Add comment requesting server logs
3. Link to related issue #38
4. Assign to @backend-team
5. Add to "Bug Triage" board

Apply these recommendations? [y/n]

2. Duplicate Detection

Find and merge duplicate issues:

Find duplicates:

User: "Check if #42 is a duplicate"

You:
Searching for duplicates of #42: "Authentication error"...

**Potential duplicates found**:

1. Issue #38: "Auth fails with 401" (95% match) ⚠️ HIGH
   - Same error code
   - Same component (authentication)
   - Same symptoms
   - Created 3 days earlier
   - Already has investigation in progress

   **Recommendation**: Mark #42 as duplicate of #38

2. Issue #27: "Login timeout" (65% match)
   - Similar area (login)
   - Different error (timeout vs 401)
   - Likely different root cause

   **Recommendation**: Link as related, not duplicate

**Action**:
```bash
gh issue close 42 --reason "duplicate" --comment "Duplicate of #38"
gh issue comment 38 --body "Also reported in #42"

Execute? [y/n]


### 3. Relationship Mapping

Map dependencies between issues:

**Create relationship map**:
```markdown
User: "Show relationships for issue #42"

You:
Mapping relationships for #42: "Implement JWT authentication"

**Dependencies** (blocks this issue):
None - can start immediately ✅

**Blocks** (this issue blocks):
- #43: Add user profile (needs auth first)
- #45: Implement password reset (needs auth system)
- #47: Add OAuth providers (extends auth)

**Related**:
- #38: Auth error (bug to fix in implementation)
- #50: Session management (complementary feature)

**Duplicate tracking**:
- #46: "Need login system" (duplicate, closed)

**Dependency graph**:

[#42 JWT Auth]
      ↓
┌─────┼─────┐
↓     ↓     ↓

[#43] [#45] [#47] Profile Reset OAuth

Related: #38 (bug), #50 (session)


**Impact analysis**:
- Completing #42 unblocks 3 issues
- High priority due to blocking nature
- Estimated effort: L (5-7 days)

4. Batch Triage

Triage multiple issues efficiently:

Triage all unlabeled:

User: "Triage all unlabeled issues"

You:
Found 23 unlabeled issues. Processing...

**Issue #42**: "Login fails with 500 error"
  Classified: bug, priority:high, scope:backend

**Issue #43**: "Add dark mode"
  Classified: feature, priority:medium, scope:frontend

**Issue #44**: "Update README"
  Classified: documentation, priority:low

**Issue #45**: "Slow query performance"
  Classified: bug, priority:high, scope:database

... [progress: 23/23]

**Summary**:
- Bugs: 12 (8 high, 3 medium, 1 low)
- Features: 8 (2 high, 4 medium, 2 low)
- Documentation: 3 (all low)

**Actions taken**:
- Applied 69 labels
- Found 4 duplicates (closed)
- Added 18 issues to "Triage Board"
- Assigned 8 high-priority issues to teams

✅ Triage complete!

5. Issue Quality Improvement

Help improve issue quality:

Request more information:

User: "Issue #42 is vague, request more details"

You:
Adding comment to issue #42...

────────────────────────────────────────
Thanks for reporting this issue!

To help us investigate, could you please provide:

**For bug reports**:
1. **Steps to reproduce**: Exact steps to trigger the issue
2. **Expected behavior**: What should happen
3. **Actual behavior**: What actually happens
4. **Environment**:
   - Browser/OS version
   - Application version
   - Any relevant configuration

**Logs/Screenshots**:
Please include any error messages, console logs, or screenshots that might help.

**Related Issues**:
Have you seen this issue before? Are there any related issues?

Adding label: `needs-more-info`
────────────────────────────────────────

✅ Comment added

Workflow Patterns

Pattern 1: New Issue Triage

Trigger: New issue created

Workflow:

Read issue title and body
Classify type, priority, scope
Check for duplicates
Assess quality (complete information?)
Apply labels
Find relationships
Add to appropriate board
Assign if priority is high
Add comment if info needed

Pattern 2: Duplicate Resolution

Trigger: "Check for duplicates" or suspected duplicate

Workflow:

Extract keywords from issue
Search existing issues (open and closed)
Calculate similarity scores
Rank potential duplicates
Present findings with confidence levels
If high confidence: suggest closing as duplicate
Update both issues with cross-references
Transfer relevant information

Pattern 3: Relationship Mapping

Trigger: "Show dependencies" or complex issue

Workflow:

Parse issue for mentioned issue numbers
Check for blocking/blocked-by indicators
Find related issues by labels/keywords
Generate dependency graph
Identify critical path
Highlight blocking issues
Suggest resolution order

Pattern 4: Batch Processing

Trigger: "Triage all..." or "Process issues with..."

Workflow:

Query issues matching criteria
For each issue:
- Classify and label
- Check duplicates
- Check quality
- Apply standard actions
Generate summary report
Highlight issues needing attention

Helper Scripts

Issue Helpers

{baseDir}/scripts/issue-helpers.sh:

# Bulk triage
bash {baseDir}/scripts/issue-helpers.sh triage-batch --filter "is:open no:label"

# Find stale issues
bash {baseDir}/scripts/issue-helpers.sh find-stale --days 90

# Close duplicates
bash {baseDir}/scripts/issue-helpers.sh close-duplicate 42 --original 38

# Add bulk labels
bash {baseDir}/scripts/issue-helpers.sh bulk-label --filter "is:bug" --label "needs-triage"

Duplicate Detection

{baseDir}/scripts/duplicate-detection.sh:

# Find duplicates for specific issue
bash {baseDir}/scripts/duplicate-detection.sh find-duplicates --issue 42

# Scan all open issues for duplicates
bash {baseDir}/scripts/duplicate-detection.sh scan-all

# Check similarity between two issues
bash {baseDir}/scripts/duplicate-detection.sh compare 42 38

Relationship Mapper

{baseDir}/scripts/relationship-mapper.sh:

# Map relationships for issue
bash {baseDir}/scripts/relationship-mapper.sh map-issue 42

# Find blocking issues
bash {baseDir}/scripts/relationship-mapper.sh find-blockers

# Generate full dependency graph
bash {baseDir}/scripts/relationship-mapper.sh generate-graph --format dot > deps.dot

Issue Validation

{baseDir}/scripts/validate-issue.py:

# Validate issue quality
python {baseDir}/scripts/validate-issue.py check 42

# Batch validate
python {baseDir}/scripts/validate-issue.py check-batch --filter "is:open"

# Generate quality report
python {baseDir}/scripts/validate-issue.py report

Templates

Response Templates

{baseDir}/templates/issue-response-templates.md:

Need more info
Duplicate issue
Fixed in version
Won't fix
Thanks for reporting
Feature request acknowledgment

Issue Templates

{baseDir}/templates/bug-report-template.md: Standard bug report template with all required fields

{baseDir}/templates/feature-request-template.md: Feature request template with use case and requirements

References

{baseDir}/references/issue-lifecycle-guide.md: Complete guide to issue lifecycle from creation to closure

Integration Points

With organizing-with-labels

Auto-apply labels during triage:

Type labels based on classification
Priority labels based on impact assessment
Scope labels based on affected areas

With managing-projects

Add triaged issues to boards:

High priority → Sprint board
Bugs → Bug triage board
Features → Feature backlog

With reviewing-pull-requests

Link PRs to issues:

Verify PR closes related issues
Check if PR addresses issue requirements
Update issue status when PR merges

Common Use Cases

Use Case 1: Daily Triage

User: "Triage today's new issues"

You:
Found 5 new issues created today:

**Issue #42**: bug, priority:high, assigned to @backend-team ✅
**Issue #43**: feature, priority:medium, added to backlog ✅
**Issue #44**: duplicate of #38, closed ✅
**Issue #45**: needs-more-info, commented ⏳
**Issue #46**: documentation, priority:low ✅

Summary: 4 triaged, 1 awaiting info

Use Case 2: Find Duplicates

User: "Find all duplicate issues"

You:
Scanning 156 open issues...

Found 8 potential duplicate groups:

**Group 1**: Authentication errors (3 issues)
- #42, #46, #51 (95% similarity)
- Recommend: Keep #42 (oldest), close others

**Group 2**: Dark mode requests (2 issues)
- #43, #49 (90% similarity)
- Recommend: Keep #43 (more detailed), close #49

Close all duplicates? [y/n]

Use Case 3: Dependency Analysis

User: "What can we work on next?"

You:
Analyzing issue dependencies...

**Ready to start** (no blockers):
- #42: JWT authentication (priority:high, 5d effort)
- #50: Session management (priority:medium, 3d effort)
- #52: Update docs (priority:low, 1d effort)

**Blocked** (waiting on dependencies):
- #43: User profile (blocked by #42)
- #45: Password reset (blocked by #42)

**Recommended order**:
1. #42 (unblocks 2 other issues)
2. #50 (parallel with #42)
3. #43, #45 (after #42 completes)

Important Notes

Triage promptly: New issues should be triaged within 24 hours
Be thorough: Check duplicates carefully before closing
Be respectful: Always thank reporters, even for duplicates
Document decisions: Explain why issues are closed/labeled
Track relationships: Dependencies matter for planning
Quality over speed: Better to triage well than triage fast

Error Handling

Common issues:

Issue not found → Check issue number
Permission denied → Need triage access
Duplicate false positive → Review similarity criteria
Missing information → Request politely

When you encounter issue triage operations, use this expertise to help users manage issues effectively!

About this skill

Automatic

Project Management 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/triaging-issues/SKILL.md

View on GitHub ↗

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

Illustrative Want to see what aiskillstore/triaging-issues 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.

mergisi/github-issue-triageTriage GitHub issues: label by type/priority, ask for repro on bugs, close obvious duplicates with a link to the canonical thread.Close match+57 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

Triaging Issues Skill

When to Use This Skill

Your Capabilities

Your Expertise

1. Issue Triage Process

2. Duplicate Detection

3. Issue Relationships

4. Issue Classification

5. Issue Quality

6. Automated Triage Rules

Your Capabilities

1. Comprehensive Issue Triage

2. Duplicate Detection

4. Batch Triage

5. Issue Quality Improvement

Workflow Patterns

Pattern 1: New Issue Triage

Pattern 2: Duplicate Resolution

Pattern 3: Relationship Mapping

Pattern 4: Batch Processing

Helper Scripts

Issue Helpers

Duplicate Detection

Relationship Mapper

Issue Validation

Templates

Response Templates

Issue Templates

References

Integration Points

With organizing-with-labels

With managing-projects

With reviewing-pull-requests

Common Use Cases

Use Case 1: Daily Triage

Use Case 2: Find Duplicates

Use Case 3: Dependency Analysis

Important Notes

Error Handling

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry