agentleFS
AFK-surfAFK-surf/OpenBridge/.agents/skills/gh-issue-fix-flow/SKILL.md

gh-issue-fix-flow

Skill430 starsChanged 6 months agoMITView on GitHub

End-to-end GitHub issue fix workflow using gh, local code changes, builds/tests, and git push. Use when asked to take an issue number, inspect the issue via gh, implement a fix, run XcodeBuildMCP builds/tests, commit with a closing message, and push.

  • Commits and pushes

3 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 6 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

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

    Use gh issue view <id> --repo <owner/repo> --comments to get the full issue context.

    line 16
  2. Very specific:

    If the repo is unclear, run gh repo view --json nameWithOwner to confirm.

    line 17
  3. Very specific:

    Use rg -n to locate likely files and entry points.

    line 22
  4. Very specific:

    Read the relevant code paths with sed -n or rg -n context.

    line 23
  5. Distinctive:

    Follow repo-specific conventions (AGENTS/CLAUDE instructions).

    line 24
  6. Distinctive:

    Keep changes aligned with existing architecture and style.

    line 29
  7. Distinctive:

    Add tests when behavior changes and test coverage is practical.

    line 30
  8. Distinctive:

    Use XcodeBuildMCP for required builds/tests:

    line 34
  9. Distinctive:

    If macOS tests fail due to deployment target mismatches, run the equivalent iOS simulator tests.

    line 38
  10. Distinctive:

    Check for unrelated changes with git status --short.

    line 43
  11. Very specific:

    Commit with a closing message: Fix … (closes #<issue>).

    line 45

≈ “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

Gh Issue Fix Flow

Overview

Resolve a GitHub issue from intake through fix, validation, and push using gh, local edits, XcodeBuildMCP, and git.

Workflow

1) Intake and issue context

  1. Use gh issue view <id> --repo <owner/repo> --comments to get the full issue context.
  2. If the repo is unclear, run gh repo view --json nameWithOwner to confirm.
  3. Capture reproduction steps, expected behavior, and any maintainer notes.

2) Locate the code path

  1. Use rg -n to locate likely files and entry points.
  2. Read the relevant code paths with sed -n or rg -n context.
  3. Follow repo-specific conventions (AGENTS/CLAUDE instructions).

3) Implement the fix

  1. Edit the minimal set of files.
  2. Keep changes aligned with existing architecture and style.
  3. Add tests when behavior changes and test coverage is practical.

4) Build and test

  1. Use XcodeBuildMCP for required builds/tests:
    • Set defaults once: mcp__XcodeBuildMCP__session-set-defaults.
    • Build: mcp__XcodeBuildMCP__build_macos or mcp__XcodeBuildMCP__build_sim.
    • Tests: prefer targeted schemes (e.g., mcp__XcodeBuildMCP__test_sim).
  2. If macOS tests fail due to deployment target mismatches, run the equivalent iOS simulator tests.
  3. Report warnings or failures; do not hide them.

5) Commit and push

  1. Check for unrelated changes with git status --short.
  2. Stage only the fix (exclude unrelated files).
  3. Commit with a closing message: Fix … (closes #<issue>).
  4. Push with git push.

6) Report back

  1. Summarize what changed and where.
  2. Provide test results (including failures).
  3. Note any follow-ups or blocked items.

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.