agentleFS
mir-ammir-am/skills-agents-ai-coding/skills/gh-issue/SKILL.md

gh-issue

Skill2 starsChanged 42 days agoMITView on GitHub

Create a GitHub issue for a bug or feature idea found during an agent session

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

11 rules. 0 are common, 8 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 8

    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. Distinctive:

    Ask user if this is a bug or feature request (if not already stated)

    line 13
  2. Very specific:

    Create the issue via gh issue create and return the URL

    line 16
  3. Distinctive:

    Use this skill when:

    line 20
  4. Distinctive:

    Must be inside a git repo with a GitHub remote

    line 27
  5. Very specific:

    If gh not installed → error: "Error: GitHub CLI not found.

    line 28
  6. Distinctive:

    If no GitHub remote found → error: "Error: No GitHub remote found.

    line 29
  7. Distinctive:

    If user did not specify → ask: "Is this a bug or a feature request?"

    line 34
  8. Distinctive:

    Body: use the 3-field format below

    line 41
  9. Distinctive:

    No period at end

    line 69
  10. Distinctive:

    Keep the entire body under 5 sentences total

    line 74
  11. Very specific:

    No GitHub remote → "Error: No GitHub remote found.

    line 81

“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

What I do

  • Ask user if this is a bug or feature request (if not already stated)
  • Draft a concise, AI-agent-readable title and body from session context
  • Apply bug or enhancement label (GitHub creates it if missing)
  • Create the issue via gh issue create and return the URL

When to use me

Use this skill when:

  • User discovers a bug or has a feature idea during a session
  • User wants to log it as a GitHub issue without losing the session context

Prerequisites

  • GitHub CLI (gh) must be installed and authenticated
  • Must be inside a git repo with a GitHub remote
  • If gh not installed → error: "Error: GitHub CLI not found. Install: https://cli.github.com/"
  • If no GitHub remote found → error: "Error: No GitHub remote found. Is this a GitHub repository?"

Workflow

  1. Determine issue type
    • If user did not specify → ask: "Is this a bug or a feature request?"
    • Map to label: bug → bug, feature request → enhancement
  2. Draft the issue from session context
    • Title: short, imperative, ≤60 chars
      • Bug examples: Fix null pointer in auth handler, Handle empty state in user list
      • Feature examples: Add dark mode toggle to settings, Support CSV export for reports
    • Body: use the 3-field format below
    • Label: bug or enhancement
  3. Validate prerequisites
    gh auth status
    git remote get-url origin
  4. Create the issue
    gh issue create --title "<title>" --label "<bug|enhancement>" --body "<body>"
  5. Return the issue URL to the user

Issue Body Format

**Type:** Bug | Feature Request
**Context:** <1-2 sentences — what was happening in the session when this was found>
**Description:** <What needs to be done, written concisely for an AI agent to act on later>

Title Guidelines

  • Imperative mood, present tense (e.g. "Fix", "Add", "Support", "Handle")
  • ≤60 characters
  • No period at end
  • Specific enough for an AI agent to understand the scope without extra context

Body Guidelines

  • Keep the entire body under 5 sentences total
  • Context: what triggered this — what the agent/user was doing when the issue was discovered
  • Description: actionable and self-contained — an AI agent should be able to open this issue cold and know what to do

Error Handling

  • gh not installed → "Error: GitHub CLI not found. Install: https://cli.github.com/"
  • No GitHub remote → "Error: No GitHub remote found. Is this a GitHub repository?"
  • Not authenticated → "Error: Not authenticated with GitHub. Run: gh auth login"
  • Insufficient context to draft the issue → ask the user to describe it in 1-2 sentences

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.