agentsclimarketplace

Github issue manager

Skill jjanuszczak/margo/skills/github-issue-manager

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.From its SKILL.md

Install
npx -y skills add jjanuszczak/margo --skill github-issue-manager

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
  • runs commandsInstructs the agent to run 2 commands, including `python3 .gemini/skills/github-issue-manager/scripts/manage_issue.py "Title" "Description" --type <bug|enhancement|documentation>` and 1 more.

SKILL.md

2.0 KB, 429 tokens by cl100k_base, as published. Nobody here has run it

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>

What ships with it: 6 files

12.7 KB alongside SKILL.md, 5 of them executable

scripts/

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.