Skip to main content
Agent skill

Triage

Triage GitHub issues by applying type, effort, priority, and area labels. Runs in an isolated context to avoid polluting the main conversation with issue details. Delegates to a specialized triage agent with label validation hooks.

Get started

Get the complete skill folder, including its scripts and reference files.

When to use this skill

Use Triage when an AI agent needs a reusable SKILL.md workflow for this job: Triage GitHub issues by applying type, effort, priority, and area labels. Runs in an isolated context to avoid polluting the main conversation with issue details. Delegates to a specialized triage agent with label validation hooks.

When not to use it

Skip Triage when the task is outside the coding category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.

How to install

Where will you use it?

Install scope
Claude Code folder setup
mkdir -p ~/.claude/skills/triage
# Save SKILL.md to ~/.claude/skills/triage/SKILL.md
  1. Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/triage/SKILL.md. For a shared project, commit the folder at .claude/skills/triage/ instead.
  2. Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
  3. For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.

Full install guide for Claude, Cursor, and Codex →

Try a starter prompt

After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.

Starter prompt
Use the Triage skill for this task: Use Triage when this documented workflow matches the task. Confirm any required inputs or files before making changes.

What supports this recommendation?

70/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.

Documentation
77/100
Practical detail
68/100
Source evidence
63/100
Source signals
70/100
Model compatibility evidence
  • claudeinferred

    The skill text mentions Claude or a closely associated term. This is keyword-derived compatibility; no hands-on model test is recorded.

  • chatgptuntested

    No model-specific signal or recorded compatibility test was found.

  • geminiuntested

    No model-specific signal or recorded compatibility test was found.

  • copilotuntested

    No model-specific signal or recorded compatibility test was found.

  • llamauntested

    No model-specific signal or recorded compatibility test was found.

  • perplexityuntested

    No model-specific signal or recorded compatibility test was found.

  • mistraluntested

    No model-specific signal or recorded compatibility test was found.

  • grokuntested

    No model-specific signal or recorded compatibility test was found.

Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.

What this skill does

# Triage GitHub Issues

Triage issues for this repository by applying appropriate labels.

## Repository Context

- **Current repo**: !`gh repo view --json nameWithOwner -q .nameWithOwner 2>/dev/null || echo "unknown"` - **Open issues**: !`gh issue list --state open --json number --jq 'length' 2>/dev/null || echo "?"` - **Existing labels**: !`gh label list --json name -q '.[].name' 2>/dev/null | head -20 || echo "none found"`

---

## Scope

Determine which issues to triage based on the arguments: **$ARGUMENTS**

| Argument | Behavior | |----------|----------| | (empty) | Only unlabeled issues (default) | | `unlabeled` | Only issues without any labels | | `all` | All open issues | | `N` | Specific issue (e.g., `67`) | | `N-M` | Range of issues inclusive (e.g., `60-67`) |

## Process

1. **Fetch available labels** — run `gh label list --json name,description` to understand the label taxonomy. Labels are organized into type, effort, priority, and area categories.

2. **Fetch target issues** — based on the scope above. For each issue, fetch the full body: ```bash gh issue view {number} --json number,title,body,labels ```

3. **For each issue**: - Read the title and full body carefully - If needed, explore the codebase (`Glob`, `Grep`, `Read`) to understand the affected code - Classify: one type, one effort, one priority, one or more areas - Track relationships with other issues (duplicates, related, blocking) - Apply labels: ```bash gh issue edit {number} --add-label "type,effort/level,P#,area.domain" ``` - Skip issues that already have complete labeling (type + effort + priority + area) - For partially labeled issues, only add missing label categories

4. **Output a triage summary**:

``` ## Triage Summary

| Issue | Title | Labels Applied | Reasoning | |-------|-------|----------------|-----------| | #67 | ... | bug, effort/low, P1, core.config | ... |

**Totals:** - Issues triaged: X - Already labeled (skipped): Y - By priority: P0(n), P1(n), P2(n), P3(n)

## Relationships Discovered

| Issues | Relationship | Notes | |--------|--------------|-------| | #61, #62 | Related | Both involve config/logging UX | ```

## Rules

- **Don't hardcode labels** — always fetch current labels first, they may change - **Respect existing labels** — don't remove labels, only add missing ones - **Check issue body** — titles alone aren't enough context - **Use the codebase** — if understanding a relationship requires seeing how modules connect, look - **When uncertain, note it** — flag ambiguous issues in the summary rather than guessing

Intended uses

  • Use Triage when this documented workflow matches the task.

Implementation notes

  • Review the source instructions and adapt inputs before running the workflow.

Try it, then tell us how it went

A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.