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
npx -y skills add jjanuszczak/margo --skill github-issue-managerAssembled 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
- Create Issue & Branch: Run the
manage_issue.pyscript 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.enhancementmaps tofeature/bugmaps tobug/documentationmaps todocumentation/
- 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:
- Run Evaluation Suite:
python3 .gemini/skills/github-issue-manager/evals/runner.py <issue_type> "<title>" - Analyze Report: Read results in
.gemini/skills/github-issue-manager/evals/reports/latest_results.json. - 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.
- Attempt 1: If any checks
- 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
evals/
- checks/convention_check.pyruns1.8 KB
- checks/git_check.pyruns3.0 KB
- checks/github_check.pyruns2.3 KB
- config.yaml416 B
- runner.pyruns2.8 KB
scripts/
- manage_issue.pyruns2.3 KB