agentleFS
Sign inStart free
madanlalitmadanlalit/agentskills/explain-gh-issue/SKILL.md

explain-gh-issue

Skill1 starsChanged 5 months agoMITView on GitHub

Explains, summarizes, and triages GitHub issues. Triggers on URLs, issue IDs (e.g. "#123"), or requests like "explain this issue".

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Look past the title and labels.

    line 11
  2. Distinctive:

    Local relevance: Search the repo for referenced files, symbols, or error strings.

    line 27
  3. Distinctive:

    Keep it short. If nothing is actionable, say so and explain why.

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Goal

Look past the title and labels. Surface the real problem, the actual status (not just open/closed), and one concrete next step. Signal over completeness.

Tools

  • scripts/check_gh.sh — validates gh CLI auth
  • scripts/fetch_issue.sh <owner/repo> <number> — fetches issue as plain text
    • --comments-tail N — last N comments only (default: all; use for threads >20)
    • --include-linked-prs — pull linked PR metadata (recommended for closed issues)

Heuristics

  • Filter noise. Skip "+1", "same here", emoji-only, and bot comments. Signal lives in OP, maintainer replies, and comments with code or repros.
  • Labels lie. "Bug" doesn't mean it's a bug. "Closed" doesn't mean fixed — verify via close reason, linked PRs, and the last substantive comment.
  • Find the resolution. For closed issues, state what resolved it: merged PR, wontfix, workaround, or duplicate. Don't leave this implicit.
  • Surface hidden context. Task lists signal epics. Images can't be read — note they exist. Linked issues/PRs are the real dependency graph.
  • Maintainer voice wins. "By design" or "tracked in #X" overrides user interpretation. Self-assignment or info requests signal active triage — flag them.
  • Local relevance. Search the repo for referenced files, symbols, or error strings. Tie the summary to code the user can act on.

Output Shape

Adapt to context, but always include:

  • Core problem in 1-2 sentences (not the title — the actual problem)
  • Status with evidence (not just the label — why it's in that state)
  • Missing/ambiguous — repro steps, environment, or decisions that block action
  • Next step — a specific file, command, or label change, not vague advice

Keep it short. If nothing is actionable, say so and explain why.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free