agentleFS
Sign inStart free
ArcQian-bitArcQian-bit/codex-real-engineer-skills/skills/issue-sherpa/SKILL.md

issue-sherpa

Skill1 starsChanged 5 months agoMITView on GitHub

Triage GitHub issues, bug reports, feature requests, and vague tasks into reproducible, scoped engineering work. Use when Codex needs to classify an issue, extract acceptance criteria, propose labels, draft a maintainer reply, or turn an issue into an implementation plan. Do not use for reviewing already-written PR diffs or publishing comments unless the user asks.

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:

    Read the issue, linked discussion, screenshots, logs, and relevant repo docs.

    line 12
  2. Distinctive:

    Write acceptance criteria as observable outcomes.

    line 16
  3. Distinctive:

    When asked to reply, produce a draft unless the user explicitly asks to post it.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Issue Sherpa

Turn fuzzy issue text into work a maintainer can trust.

Workflow

  1. Read the issue, linked discussion, screenshots, logs, and relevant repo docs.
  2. Classify the request: bug, feature, docs, maintenance, question, or needs reproduction.
  3. Extract facts separately from assumptions.
  4. Build a reproduction or discovery plan for bugs. If a repro is impossible, name the missing artifact.
  5. Write acceptance criteria as observable outcomes.
  6. Propose the smallest useful implementation slice and verification command.

Draft Maintainer Reply

When asked to reply, produce a draft unless the user explicitly asks to post it. Include:

  • Summary of the issue in one sentence.
  • What is known.
  • What is needed, if anything.
  • Next action and verification.

Triage Checklist

  • Environment/version present?
  • Expected and actual behavior distinct?
  • Reproduction steps concrete?
  • Logs or screenshots actionable?
  • Duplicates or related issues checked?
  • User impact and severity clear?
  • Scope small enough for one PR?

Output

Prefer:

Classification:
Impact:
Repro plan:
Acceptance criteria:
Implementation slice:
Verification:
Suggested labels:
Draft reply:

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