agentleFS
leekleek/agent-skills/skills/fix-github-issues/SKILL.md

fix-github-issues

Skill5 starsChanged 10 days agoMITView on GitHub

Verify, triage, fix, and close review-bot GitHub issues one finding at a time.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Project context: Read .agents/github-review.md when the repo has one.

    line 16
  2. Very specific:

    Verify each line, delegate a set of more than 5, and run the second pass against the project's auto-dismiss and never-dismiss lists before …

    line 51
  3. Distinctive:

    Run that test file against the repo's configured test database when you can.

    line 72
  4. Distinctive:

    If you later find a misclassified finding, reopen the issue with a correction note.

    line 116
  5. Very specific:

    Remove nothing before this step.

    line 123

≈ “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

Fix GitHub Issues

Work the open issues that a review bot filed. Each issue is a container of findings: some are legit, some stale, some wrong. Every finding earns its own verdict from the code on the default branch, never from the issue's headline. An issue closes only when no legit finding is left in it, and a fix counts only once it reaches the default branch.

Project context. Read .agents/github-review.md when the repo has one. Its sections ## Review bots (with the bot's issue label), ## Auto-dismiss, ## Never dismiss, and ## Stack facts (what the bots get wrong) hold this repo's facts; a missing section means the default here. Then follow the repo's AGENTS.md / CLAUDE.md rules for tests, lint, cache clears, and a dirty tree.

1. Build the working set

Find the default branch (written <default> below), run git fetch origin, and verify everything against origin/<default>, not a local branch. List every open issue with the bot label (or the ones the user named), newest first. The calls, and the check that the list is not cut off at its limit, are in references/mechanics.md.

Walk order is newest to oldest, but let evidence reorder it. A newer diff that introduced a defect an older issue already flagged makes the older finding LEGIT, and you fix both in one commit chain. A newer commit that fixed an older finding makes that finding STALE: cite the sha.

Completion criterion: every open issue in scope is listed, newest first, with fewer issues than the limit.

2. Classify every finding

For each issue, read its body and every comment (note any "fixed in <sha>" or "false positive" from earlier runs). Read the commits it reviewed. Then write one line per finding:

Finding N: [STALE | AUTO-DISMISS | HALLUCINATION | LEGIT] — <one-line evidence>
  • Finding 1: STALE — fixed in bf707fde3, see app/Foo.php:42
  • Finding 3: HALLUCINATION — rg 'BarPolicy::class' returns 0; symbol does not exist
  • Finding 4: LEGIT — app/Auth.php:88 still uses < instead of <=, exploitable on token boundary

Verify each line, delegate a set of more than 5, and run the second pass against the project's auto-dismiss and never-dismiss lists before any code, all by Verify findings, with origin/<default> as the ref. You re-read the LEGIT code for the fix anyway.

Completion criterion: every finding in the working set has a line, and the second pass is done.

3. Fix the legit ones

Work on a new branch fix/issues-<run> from origin/<default>, always in a worktree (Branch or worktree). The main checkout stays on the branch the run found it on, including when that tree is clean.

Per LEGIT finding: make the minimal change, with no drive-by refactors. Prove it per the tdd skill's What needs a test: a test for behaviour, run that test file green; verify for a presentation change. A user message to stop the tests ends test commands for the rest of the run: the last focused result stands, and the commits continue. Commit each fix on its own (Conventional Commits, explicit staging). Put fixes #NNN only on the commit that resolves the issue's last legit finding, so the issue closes at the right moment.

Run that test file against the repo's configured test database when you can. A run that needs its own database names and registers it by Scratch databases.

A LEGIT finding you cannot fix (a secret rotation, infra, a human decision) keeps the issue OPEN; step 5 names the blocker.

Completion criterion: every fixable LEGIT finding has a commit on fix/issues-<run>, with a green test where it needs one, and every unfixable one is named.

4. Land the fixes

An issue closes only when its fixes #NNN commit reaches <default>, so a local commit fixes nothing yet. Show the user the commits and the issues each one closes, say where they will go, and land them without asking: push to <default> by default; open a pull request instead when branch protection or the repo's rules forbid direct pushes. A user instruction in the input or the conversation ("open a PR", "keep them local") overrides both. The commands are in Land.

Once they are landed, the main checkout is still the branch recorded at the start (The checkout stays). The fix branch stays in its worktree. Do the same check if the run stops early.

Completion criterion: the commits are on <default>, in an open pull request, or kept local by the user's instruction, and git branch --show-current in the main checkout is still the starting branch.

5. Post a disposition

Post one comment per issue in the working set, with one bullet per finding (calls in Disposition and close):

- Finding 1 (X): fixed in <sha>
- Finding 2 (Y): stale — superseded by <sha>
- Finding 3 (Z): auto-dismiss — <category>
- Finding 4 (W): hallucination — symbol does not exist at claimed location
  • Fixed on <default>: the push closed it; post the comment after.
  • Nothing legit: post the comment, then close the issue.
  • Fix in an open pull request or kept local: the issue stays open; the comment says where the fix is.
  • A LEGIT finding you cannot fix: the issue stays open; the comment names the blocker.

If you later find a misclassified finding, reopen the issue with a correction note.

Completion criterion: every issue has its comment, and gh issue view N --json state agrees with it.

6. Clean up

Remove nothing before this step. Then clean up what you created by laravel-herd-worktrees' What is left rule (Clean up): a worktree and its databases whose fixes are on <default> (or that fixed nothing) go without asking; a refused worktree, and one whose fixes are in an open pull request or kept local, go into the one question. What stays stays registered, for repository-cleanup.

Completion criterion: everything removable is removed, any question is answered, or you created nothing. Report the tally: fixed, stale, auto-dismiss, hallucination, and blocked. Name each fix not yet on <default>, and each worktree or database kept. Mark the blocked count and each kept item ⚠️; no other marks.

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.