agentleFS
lgtm-hqlgtm-hq/ai-skills/skills/issue/SKILL.md

issue

Skill1 starsChanged 10 days agoMITView on GitHub

Create GitHub issues with proper formatting, labels, and AI implementation prompts. Use when asked to create an issue, report a bug, or request a feature.

50 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use browse, scout and 5 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • CodeWithBehnamSkill

    browse

    Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence.

    Also in 3 projects that use this

  • lukeleekrSkill

    scout

    GitHub 레포 스카우터. 내 Claude Code + Codex App 환경을 분석하여 필요한 GitHub 레포를 자동 추천하거나, 키워드로 GitHub을 검색합니다. "scout", "스카우트", "깃헙 탐방", "레포 추천", "repo search" 등의 키워드에 반응합니다.

    Also in 3 projects that use this

  • sunnyclinches44Skill

    explain

    Explains code using real-world analogies and ASCII diagrams

    Also in 4 projects that use this

  • VercelSkill

    deploy

    Deploy applications to Vercel. Use when the user says "deploy", "deploy to Vercel", "push to production", "deploy my app", or "go live".

    Also in 4 projects that use this

  • kt057Skill

    check

    lint, typecheck, test を一括実行して結果をサマリーする

    Also in 3 projects that use this

  • Microsoft AzureSkill

    reflect

    Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes. Use after user corrections ("no", "wrong"), praise ("perfect", "exactly"), or when discovering edge cases. Complements .squad/agents/{agent}/history.md and .squad/decisions.md.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 48 edited versions we read keep these.

  • 6

    Distinctive

    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
  1. Distinctive:

    Create well-structured GitHub issues following repository conventions.

    line 8
  2. Distinctive:

    Use semantic prefixes matching conventional commits:

    line 12
  3. Distinctive:

    When asked to create an issue:

    line 136
  4. Distinctive:

    Gather requirements: - Ask clarifying questions if needed

    line 138
  5. Very specific:

    Review existing issues: - Check for duplicates with gh issue list

    line 139
  6. Distinctive:

    Comment before closing: Every closed issue gets a comment explaining _why_ it's closed and linking to whatever supersedes it (issue, PR, or …

    line 169
  7. Very specific:

    Don't: gh issue close 42 with no comment.

    line 172
  8. Distinctive:

    Repurpose before minting: When scope evolves, prefer retargeting an existing issue number over closing it and opening a new one — it …

    line 178

“Common” is measured: kept by at least 6 in 10 of the 48 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 Creation

Create well-structured GitHub issues following repository conventions.

Issue Title Format

Use semantic prefixes matching conventional commits:

feat(scope): short description    # New feature
fix(scope): short description     # Bug fix
docs(scope): short description    # Documentation
chore(scope): short description   # Maintenance
refactor(scope): short description # Code refactoring
perf(scope): short description    # Performance improvement

Issue Body Structure

For Feature Requests

## Summary

One paragraph describing the feature and its value.

## Problem

What problem does this solve? What's the current limitation?

## Proposed Solution

Detailed description with:

- Code examples showing desired behavior
- ASCII diagrams or mockups if applicable
- Configuration examples

## Implementation Notes

- Key files to modify
- Dependencies or prerequisites
- Potential challenges

## Benefits

- Bullet points of user/developer benefits

For Bug Reports

## Summary

One paragraph describing the bug.

## Problem

What's happening vs what should happen?
Include:

- Steps to reproduce
- Error messages or screenshots
- Environment details if relevant

## Proposed Solution

How to fix it (if known).

## References

- Links to related issues, docs, or resources

Labels

Apply appropriate labels based on issue type:

Issue TypeLabels
New featureenhancement
Bug fixbug
Documentationdocumentation
Security issuebug, security
CI/CD relatedci
New tool (lintro)enhancement, new tool

AI Implementation Prompt

For issues that involve code changes, add a comment with an AI implementation prompt:

## AI Implementation Prompt

Use this prompt in a new agent session to implement this feature:

\```
[Concise implementation instructions including:]

## Requirements

### 1. [First Component]

- What to create/modify
- Code examples

### 2. [Second Component]

- What to create/modify
- Code examples

## Files to Modify

- `/path/to/file.py` - description of changes

## Tests

- Test requirements (pytest style, NO test classes)
- Use assertpy, fixtures

## Before Submitting

- Run `uv run lintro chk` - must pass
- Run `uv run lintro fmt` - must pass
- Run `uv run pytest` - must pass
  \```

Usage

When asked to create an issue:

  1. Gather requirements - Ask clarifying questions if needed
  2. Review existing issues - Check for duplicates with gh issue list
  3. Create the issue:

    gh issue create \
      --title "feat(scope): description" \
      --label "enhancement" \
      --body "$(cat <<'EOF'
    ## Summary
    ...
    EOF
    )"
  4. Add AI prompt comment (for implementation issues):

    gh issue comment <issue-number> --body "$(cat <<'EOF'
    ## AI Implementation Prompt
    ...
    EOF
    )"
  5. Return the issue URL to the user

Backlog Stewardship

Rules for managing an existing backlog, not just creating new issues.

  • Comment before closing. Every closed issue gets a comment explaining why it's closed and linking to whatever supersedes it (issue, PR, or commit).
    • Don't: gh issue close 42 with no comment.
    • Do: gh issue comment 42 --body "Superseded by #57, merged in a1b2c3d." then gh issue close 42.
  • "Done" means merged to main. Work that exists only on a branch is not done. Never close an issue because a branch has the fix — reopen or repurpose the issue instead until it lands on main.
  • Repurpose before minting. When scope evolves, prefer retargeting an existing issue number over closing it and opening a new one — it preserves history and discussion.
  • Placeholder convention for duplicates. For issues that are redundant or would only duplicate another: prefer closing with a supersession comment (see above) when the issue has useful comments, an implementation prompt, or a useful body (repro steps, scoped feature spec, acceptance criteria) — do not wipe history that other links or workflows may still need. Only convert to a placeholder (empty body, title placeholder, comments cleared) when the issue has no useful body and no useful discussion to preserve and you are explicitly reserving the number for reuse.
  • Never churn the backlog silently. Announce close/reopen/create/edit changes as you make them — the backlog should stay visible, not shift underneath readers.
  • Keep content correct. Issues must carry accurate scope and follow the /issue format above. When an assessment (audit, review, incident) surfaces a real gap — bug, security issue, tech debt — add a spec-formatted, labeled issue for it rather than leaving it undocumented.
  • Dependency-update issues/PRs (Renovate, Dependabot): follow the dependency-triage rule in the stand-general skill.

Examples

Good Issue Titles

  • feat(cli): add watch mode for continuous linting
  • fix(parser): handle empty input without crashing
  • docs(readme): add installation instructions for Windows
  • refactor(core): simplify plugin loading logic

Bad Issue Titles

  • Add feature (no scope, not descriptive)
  • Bug (not descriptive)
  • Update code (vague, no scope)
  • Fixed the thing (past tense, vague)

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.