Agent Skills › coleam00/Archon › triage

triage

GitHub

自动为 GitHub Issue 分类打标，支持按范围筛选。通过读取 Issue 详情和代码库上下文，智能分配类型、优先级、工作量等标签，并识别重复或相关 Issue，输出整理摘要，提升 Issue 管理效率。

.claude/skills/triage/SKILL.md coleam00/Archon

Trigger Scenarios

需要批量处理 GitHub Issue 标签时请求对特定 Issue 进行归类分析时

Install

npx skills add coleam00/Archon --skill triage -g -y

More Options

Non-standard path

npx skills add https://github.com/coleam00/Archon/tree/dev/.claude/skills/triage -g -y

Use without installing

npx skills use coleam00/Archon@triage

指定 Agent (Claude Code)

npx skills add coleam00/Archon --skill triage -a claude-code -g -y

安装 repo 全部 skill

npx skills add coleam00/Archon --all -g -y

预览 repo 内 skill

npx skills add coleam00/Archon --list

SKILL.md

Frontmatter

{
    "name": "triage",
    "agent": "triage-agent",
    "context": "fork",
    "description": "Triage GitHub issues by applying type, effort, priority, and area labels.\nRuns in an isolated context to avoid polluting the main conversation with\nissue details. Delegates to a specialized triage agent with label validation hooks.\n",
    "allowed-tools": "Bash(gh *), Read, Glob, Grep",
    "argument-hint": "[unlabeled|all|N|N-M]",
    "disable-model-invocation": true
}

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

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

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