agentleFS
Sign inStart free
Hey-DigaHey-Diga/dotclaude/skills/start-working-on-issue/SKILL.md

start-working-on-issue

Skill17 starsChanged 9 months agoMITView on GitHub

Start working on a GitHub issue end-to-end: fetch, analyze, implement, test, and create PR. Use when picking up a GitHub issue to work on.

  • Commits and pushes

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Read the full issue content and ALL comments using: gh issue view $ARGUMENT$ --comments

    line 15
  2. Distinctive:

    If any clarifications are needed:

    line 17
  3. Distinctive:

    Ask me for answers

    line 19
  4. Distinctive:

    Ensure consistency with existing code in the branch

    line 24
  5. Distinctive:

    Run lint (npm run lint) and tests suite (npm run test) before git commit & push

    line 25
  6. Very specific:

    Always use gh CLI for GitHub operations

    line 29
  7. Distinctive:

    Keep detailed records of all actions as PR/issue comments

    line 30
  8. Distinctive:

    Wait for explicit confirmation before proceeding with major changes

    line 31

≈ “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

GitHub Issue Workflow for Issue #$ARGUMENT$

Setup Phase

  1. Fetch latest branches: git fetch origin
  2. Get issue details
    • Fetch issue title: gh issue view $ARGUMENT$ --json title -q .title

Analysis Phase

  1. Read the full issue content and ALL comments using: gh issue view $ARGUMENT$ --comments
  2. Analyze the requirements and context thoroughly
  3. If any clarifications are needed:
    • List all questions clearly
    • Ask me for answers
    • Post both questions and answers as a comment on the github issue $ARGUMENT$

Implementation Phase

  1. Execute the plan step by step, remember to build test before the implementation and run the test suite constanly to get quick feedback.
  2. Ensure consistency with existing code in the branch
  3. Run lint (npm run lint) and tests suite (npm run test) before git commit & push
  4. Create the PR

Important Notes

  • Always use gh CLI for GitHub operations
  • Keep detailed records of all actions as PR/issue comments
  • Wait for explicit confirmation before proceeding with major changes

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