agentleFS
Hey-DigaHey-Diga/dotclaude/skills/gh-issue/SKILL.md

gh-issue

Skill17 starsChanged 9 months agoMITView on GitHub

Create a new GitHub issue for a feature, bug, or chore. Use when you have an idea, bug report, or task that needs a GitHub issue with analysis and solution options.

11 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

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Look at relevant code files to understand current implementation

    line 14
  2. Distinctive:

    Ask me questions about anything unclear:

    line 18
  3. Distinctive:

    Wait for my answers before continuing.

    line 25
  4. Distinctive:

    Create an issue with this structure:

    line 28
  5. Distinctive:

    Wait for my approval.

    line 71
  6. Distinctive:

    Check actual code before suggesting solutions

    line 82
  7. Distinctive:

    Use specific file names and paths

    line 83

“Common” is measured: kept by at least 6 in 10 of the 10 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

Create New GitHub Issue for Feature

Input

Feature/Bug/Chore idea: $ARGUMENT$

Step 1: Analysis

  • Analyze the feature/bug/chore idea provided
  • Look at relevant code files to understand current implementation
  • Identify what needs clarification

Step 2: Clarification

Ask me questions about anything unclear:

  • User scenarios
  • Edge cases
  • Integration requirements
  • Performance needs
  • Dependencies

Wait for my answers before continuing.

Step 3: Draft Issue

Create an issue with this structure:

Problem Statement

What problem does this solve? What are current limitations?

User Value

What specific benefits will users get? Give concrete examples.

Definition of Done

  • Implementation complete with edge cases handled
  • Unit tests added (>80% coverage)
  • Integration tests for main flows
  • Documentation updated
  • Code review approved
  • CI/CD passes
  • Manual testing complete

Manual Testing Checklist

  • Basic flow: [specific steps]
  • Edge case testing: [specific scenarios]
  • Error handling: [error scenarios to test]
  • Integration: [test with existing features]

Potential Solutions

Option 1: [Name]

  • Description: How it works
  • Pros: Benefits
  • Cons: Drawbacks
  • Files to modify: [list specific files]

Option 2: [Name]

[Same format as Option 1]

Recommended Approach

Which option and why

Technical Notes

  • Affected files: [list from code analysis]
  • Dependencies: [any external/team dependencies]

Step 4: Review

Show me the complete issue draft and ask: "Is this ready to create? Any changes needed?"

Wait for my approval.

Step 5: Create Issue

After approval, run:

gh issue create --title "[Feature/bug/chore] YOUR_TITLE_HERE" --body "YOUR_ISSUE_CONTENT_HERE"

Tell me the issue number and URL when done.

Remember

  • Check actual code before suggesting solutions
  • Use specific file names and paths
  • Make testing steps concrete and actionable
  • Focus on user benefits, not technical details
  • Triage and use the correct term in the issue:it's a feature, a bug or a chore?

Key improvements:
1. **Removed nested markdown** - The triple backticks inside the prompt were likely causing parsing issues
2. **Simplified structure** - Clearer step-by-step format
3. **Separated commands** - Split the issue creation and project assignment into two commands (gh CLI doesn't support --project flag in create command)
4. **Clearer placeholders** - YOUR_TITLE_HERE and YOUR_ISSUE_CONTENT_HERE are more obvious to replace
5. **Removed complex formatting** - Simplified the markdown structure to avoid parsing conflicts
6. **Direct instructions** - More imperative language that's easier to follow

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.