AgentStack
SKILL verified MIT Self-run

Github Triage

skill-andrewsrigom-agent-skills-github-triage · by andrewsrigom

Use when triaging GitHub issues or incoming bug reports. Covers fast issue review, category and state decisions, codebase context gathering, next-action recommendations, and preparing issues for implementation without jumping straight into code.

No reviews yet
0 installs
6 views
0.0% view→install

Install

$ agentstack add skill-andrewsrigom-agent-skills-github-triage

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Github Triage? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

GitHub Triage

Use this skill when the task is to sort, qualify, or prepare GitHub work.

Scope

  • reviewing new issues
  • categorizing bugs vs enhancements
  • identifying missing information
  • deciding whether an issue is ready for implementation
  • summarizing next action for maintainers or agents

Default path

  1. Read the issue body, labels, and recent comments.
  2. Restate the problem in one line.
  3. Decide whether it is:
  • bug
  • enhancement
  • question
  • duplicate or out of scope
  1. Check the codebase only enough to understand the relevant domain and likely boundary.
  2. Recommend one next state:
  • needs info
  • ready to implement
  • needs design
  • not actionable
  1. If actionable, note the likely testable behavior and affected boundary.

When to deviate

  • Investigate deeper only if the issue already looks actionable and the missing confidence is technical rather than descriptive.
  • Escalate to design instead of implementation when the issue is really a product or UX decision.
  • Close as duplicate or out of scope only when that state is defensible from the issue history or codebase context.

Guardrails

  • Do not start implementing during triage.
  • Do not over-investigate before deciding whether the issue is even valid.
  • Keep the issue durable: describe behavior, not file paths.
  • Separate “not enough information” from “not a real bug.”

Avoid

  • jumping into code changes during triage
  • over-reading the codebase before deciding whether the issue is valid
  • confusing missing information with invalid reports
  • writing triage notes that only make sense if the file layout never changes

Verification checklist

  • the issue is restated in one clear sentence
  • the category is explicit
  • missing information, if any, is concrete
  • the next state is chosen intentionally
  • if actionable, the likely boundary and testable behavior are identified

Output Shape

When answering with this skill, prefer:

  • issue summary
  • category
  • confidence level
  • missing information, if any
  • recommended next action

Good Triggers

  • triage this issue, review incoming issues, classify this bug, is this ready to implement, GitHub triage

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.