agentleFS
jjanuszczakjjanuszczak/margo/skills/github-issue-manager/SKILL.md

github-issue-manager

Skill2 starsChanged 17 days agoApache-2.0View on GitHub

Create GitHub issues and development branches. Use when the user wants to start work on a bug, feature (enhancement), or documentation task and needs a structured way to track it.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 1

    Distinctive

    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:

    Create Issue & Branch: Run the manage_issue.py script to create a GitHub issue with appropriate labels and switch to a new branch.

    line 12
  2. Very specific:

    Analyze Report: Read results in .gemini/skills/github-issue-manager/evals/reports/latest_results.json.

    line 37
  3. Very specific:

    Attempt 1: If any checks FAIL (e.g., branch not created, issue missing), analyze the error and attempt to fix the issue.

    line 39
  4. Distinctive:

    Escalation: If still failing after 2 attempts, stop and present the failure report to the user.

    line 41

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “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 Manager

This skill automates the creation of GitHub issues and the setup of local development branches.

Workflow

  1. Create Issue & Branch: Run the manage_issue.py script to create a GitHub issue with appropriate labels and switch to a new branch.
    python3 .gemini/skills/github-issue-manager/scripts/manage_issue.py "Title" "Description" --type <bug|enhancement|documentation>

Instructions

  • Issue Types:
    • bug: For reporting errors or unexpected behavior.
    • enhancement: For new features or improvements.
    • documentation: For updates to READMEs, guides, or site content.
  • Branch Naming: The script generates a concise branch name in the format type/abbreviated-title.
    • enhancement maps to feature/
    • bug maps to bug/
    • documentation maps to documentation/
  • Requirements: Requires the gh (GitHub CLI) to be installed and authenticated.

Scripts

  • scripts/manage_issue.py: The core automation script.

Self-Evaluation & Correction

You MUST autonomously verify every issue management task:

  1. Run Evaluation Suite: python3 .gemini/skills/github-issue-manager/evals/runner.py <issue_type> "<title>"
  2. Analyze Report: Read results in .gemini/skills/github-issue-manager/evals/reports/latest_results.json.
  3. Self-Correction Loop:
    • Attempt 1: If any checks FAIL (e.g., branch not created, issue missing), analyze the error and attempt to fix the issue.
    • Attempt 2: One final targeted fix and re-run.
  4. Escalation: If still failing after 2 attempts, stop and present the failure report to the user.

<AVAILABLE_RESOURCES>

  • Evaluation Runner: .gemini/skills/github-issue-manager/evals/runner.py </AVAILABLE_RESOURCES>

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.