agentleFS
kdoddy36615kdoddy36615/bug-reviewer/.claude/skills/bug-reviewer-run/SKILL.md

bug-reviewer-run

Skill0 starsChanged 6 months agoMITView on GitHub

Launch the local bug-reviewer web UI (server.js) so the user can approve or request changes on each bug before a PR is created. Reads bugs.json, writes results.json. Use when the user says "run the reviewer", "open the review UI", "launch the reviewer", or when the orchestrator hits Step 5 of the triage flow.

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:

    After launching, say (verbatim or close):

    line 36
  2. Distinctive:

    Do not poll or check status.

    line 40
  3. Distinctive:

    Reviewer runs before commit and PR: No exceptions — see the orchestrator's sequencing rule.

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Bug Reviewer — Local UI

Spawns server.js with the populated bugs.json. The server exits automatically when the user finishes reviewing every bug.


Launch — use Bash with run_in_background: true

The Bash tool's run_in_background: true parameter triggers an automatic notification when the process exits. Use it. Do not append & and do not poll with curl.

node ~/projects/bug-reviewer/server.js bugs.json results.json

Correct invocation:

  • command: node ~/projects/bug-reviewer/server.js bugs.json results.json
  • run_in_background: true

Wrong (will fire the notification too early — when the wrapper shell exits, not when server.js exits):

node ~/projects/bug-reviewer/server.js bugs.json results.json & sleep 1 && echo done

Tell the user

After launching, say (verbatim or close):

Reviewer is up at http://localhost:3737 — open it and review. I'll be notified automatically when you're done.

Do not poll or check status. The notification fires when the server exits.


After the reviewer exits — read results.json

cat results.json | jq '.[] | {id, status}'

For any bug with "status": "feedback", the user has requested changes. Address the feedback before continuing to commit/PR. Do not move to ado-pr-create until every bug is approved.


Hard rules

  • Use run_in_background: true. Not &. Not polling.
  • Reviewer runs before commit and PR. No exceptions — see the orchestrator's sequencing rule.
  • Address feedback status bugs before proceeding. Re-run the capture if needed and re-launch the reviewer.

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.