Fetch GitHub issues and use LLM judgment to prioritize them based on importance, clarity, delegation potential, and urgency. Helps identify what to work on next.
Fetch GitHub issues, apply intelligent analysis, and visualize priorities.
# 1. Fetch issues (saves to triage-data.json)
./scripts/fetch-issues.sh owner/repo
# 2. Launch dashboard in browser
./scripts/serve.sh
This skill combines deterministic data fetching with LLM judgment:
triage-data.jsonThe script handles data retrieval; you provide the intelligence that only an LLM can offer.
The fetch script outputs JSON in this structure:
{
"metadata": {
"repository": "owner/repo",
"generated": "2025-12-27T01:00:00Z",
"total_issues": 42
},
"issues": [
{
"number": 123,
"title": "Issue title",
"body": "Full issue body...",
"body_preview": "First 500 chars...",
"labels": [{"name": "bug", "color": "d73a4a"}],
"label_names": ["bug"],
"age_days": 7,
"days_since_update": 2,
"comment_count": 5,
"is_assigned": false,
"url": "https://github.com/...",
"scores": {
"delegation": null,
"importance": null,
"urgency": null,
"clarity": null,
"effort": null,
"priority": null
},
"analysis": null
}
]
}
For each issue, evaluate these criteria and assign scores (1-5):
Can this be delegated to an AI coding agent like Copilot?
| Score | Meaning |
|---|---|
| 5 | Perfect for AI: clear scope, well-defined acceptance criteria, isolated change |
| 4 | Good for AI: mostly clear, may need minor clarification |
| 3 | Partial AI assist: AI can help but human judgment needed |
| 2 | Difficult for AI: ambiguous requirements, needs design decisions |
| 1 | Human only: requires context, stakeholder input, or creative direction |
How important is this to the project's success?
| Score | Meaning |
|---|---|
| 5 | Critical: security issue, data loss, major feature broken |
| 4 | High: significant user impact, blocking other work |
| 3 | Medium: meaningful improvement, affects subset of users |
| 2 | Low: nice-to-have, minor polish |
| 1 | Minimal: trivial or questionable value |
How time-sensitive is this?
| Score | Meaning |
|---|---|
| 5 | Immediate: production down, security vulnerability |
| 4 | This week: deadline approaching, blocking release |
| 3 | Soon: should be addressed but not time-critical |
| 2 | Eventually: backlog item, no pressure |
| 1 | Someday/maybe: could be closed or deferred indefinitely |
How well-defined is the issue?
| Score | Meaning |
|---|---|
| 5 | Crystal clear: steps to reproduce, expected vs actual, acceptance criteria |
| 4 | Good: mostly clear, minor questions |
| 3 | Adequate: understandable but needs some investigation |
| 2 | Vague: unclear scope, missing context |
| 1 | Confused: contradictory, rambling, or no actionable request |
How much work is this likely to be?
| Score | Meaning |
|---|---|
| 5 | Trivial: < 30 minutes, one-line fix |
| 4 | Small: few hours, single file/component |
| 3 | Medium: day or two, multiple files |
| 2 | Large: week+, significant refactoring |
| 1 | Epic: major feature, needs breakdown |
Priority = (Importance × 3) + (Urgency × 2) + (Clarity × 1.5) + (Delegation × 1) + (Effort × 0.5)
Max score: 40 | High priority: ≥30 | Medium: 20-29 | Low: <20
./scripts/fetch-issues.sh owner/repo to fetch issues./scripts/serve.sh to launch the dashboard in the browsertriage-data.json and displays interactive visualizations./scripts/fetch-issues.sh owner/repo./scripts/serve.sh (opens http://localhost:8080/dashboard.html)The viewer.html provides:
When analyzing issues, output updates in this format:
{
"number": 123,
"scores": {
"delegation": 5,
"importance": 2,
"urgency": 2,
"clarity": 5,
"effort": 5,
"priority": 24.5
},
"analysis": "Trivial docs fix. Perfect for AI delegation - exact change specified."
}
Or provide a summary report alongside the JSON updates.
issue-triage/
├── SKILL.md # This file
├── dashboard.html # Full analytics dashboard
├── viewer.html # Simple issue viewer
├── scripts/
│ ├── fetch-issues.sh # Data fetching script
│ └── serve.sh # Local server + browser launch
└── triage-data.json # Generated data (git-ignored)
gh CLI first