agentleFS
phnx-labsphnx-labs/rush-mcp/skills/fix-a-bug/SKILL.md

fix-a-bug

Skill0 starsChanged 4 days agoMITView on GitHub

Have a Rush cloud agent reproduce a bug, fix it and open a pull request with a test. Use when someone shares an error, a stack trace, a failing test or CI run, or a bug report or issue and wants it fixed in a repository.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. xai-org/xai-cookbook★ 637same name
    2. oleg-vasilyev/FoolProof★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Start it: Call create_session with the repository (or the branch the bug is on) as repo, a fresh UUID you write yourself as request_id, and …

    line 13

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Fix a bug with Rush

  1. Gather what the agent needs. The session cannot see this conversation or the person's machine, so collect: the repository, the exact error or stack trace, how to trigger it, what should happen instead, and any file, commit or CI link already suspected. Paste an issue's text rather than only its link. Ask one question if the repository or the symptom is missing.
  2. Start it. Call create_session with the repository (or the branch the bug is on) as repo, a fresh UUID you write yourself as request_id, and a task like: "Fix this bug. <symptom, error, steps>. First reproduce it and write a test that fails because of it. Then fix the cause, not the symptom, and run the test suite. Open a pull request that explains the cause, the fix and the test, and do not merge it. If you cannot reproduce it, stop and report what you tried." Leave out "do not merge" only when the person asked for a merge.
  3. Wait with wait_for_sessions (timeout_seconds: 50) until it settles; a fix takes several minutes.
  4. Report. From get_session: the cause in a sentence or two, the pull request link (a merge request on gitlab.com), and whether the new test failed before the fix and passes after. get_session_changes with include_diff shows the change when the person wants to read it here. If it could not reproduce the bug, give what it tried and ask for the missing detail.
  5. Iterate in the same session. Review comments or a red check go back with send_session_message ("CI fails on lint: fix it and push"), so the agent keeps its computer and context and updates the same pull request.

Refusals: see hand-off-a-task under "When Rush refuses".

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.