agentleFS
thefrederiksenthefrederiksen/devthrottle/.claude/skills/enter-issue/SKILL.md

enter-issue

Skill110 starsChanged 6 days agoMITView on GitHub

Create a GitHub issue from screenshots, images, text descriptions, or any combination. Use this when the user wants to file a new issue or report a bug.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 9 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a new GitHub issue based on the user's input.

    line 10
  2. Very specific:

    Read any text description or title provided in $ARGUMENTS

    line 17
  3. Distinctive:

    If the user has provided screenshot paths or image paths, read them using the Read tool to understand their content

    line 18
  4. Distinctive:

    If no title is provided, derive one from the description/images

    line 22
  5. Distinctive:

    If the description is vague, use AskUserQuestion to clarify:

    line 25
  6. Distinctive:

    If the user provided enough information, proceed without asking

    line 30
  7. Distinctive:

    If images/screenshots were provided, they need to be included in the issue

    line 33
  8. Very specific:

    Use gh issue create which supports image references in markdown

    line 34
  9. Very specific:

    Check available labels: gh label list

    line 39
  10. Distinctive:

    If no matching labels exist, create them if appropriate

    line 41
  11. Very specific:

    Always use gh CLI for GitHub operations

    line 76
  12. Distinctive:

    Use a HEREDOC for the body to preserve formatting:

    line 77
  13. Distinctive:

    If images were provided, mention that they should be manually attached via the GitHub web UI if CLI upload is not possible, and provide the …

    line 85

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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 GitHub Issue

Create a new GitHub issue based on the user's input. The input may include screenshots, images, text descriptions, error logs, or any combination.

Input: $ARGUMENTS

Instructions

  1. Gather context from the user's input:
    • Read any text description or title provided in $ARGUMENTS
    • If the user has provided screenshot paths or image paths, read them using the Read tool to understand their content
    • Common screenshot locations to check if referenced:
      • %USERPROFILE%\Pictures\Screenshots
      • %OneDrive%\Pictures\Screenshots
    • If no title is provided, derive one from the description/images
  2. Collect additional information if needed:
    • If the description is vague, use AskUserQuestion to clarify:
      • What is the expected behavior?
      • What is the actual behavior?
      • Steps to reproduce?
      • Priority/severity?
    • If the user provided enough information, proceed without asking
  3. Upload images to the issue:
    • If images/screenshots were provided, they need to be included in the issue
    • Use gh issue create which supports image references in markdown
    • For local images, upload them by referencing in the issue body — GitHub CLI handles image uploads when you use the web editor, so instead embed image paths as attachments
    • Strategy: Create the issue first, then use gh issue edit to add images if needed, OR reference images inline
  4. Determine labels:
    • Check available labels: gh label list
    • Apply appropriate labels (bug, enhancement, documentation, etc.)
    • If no matching labels exist, create them if appropriate
  5. Create the issue using GitHub CLI:
    gh issue create --title "TITLE" --body "BODY" --label "LABELS"
    • Title: Clear, concise, imperative form (e.g., "Fix crash when opening settings")
    • Body format:
      ## Description
      [Clear description of the issue]
      
      ## Screenshots
      [Any attached images]
      
      ## Steps to Reproduce (if bug)
      1. Step one
      2. Step two
      
      ## Expected Behavior
      [What should happen]
      
      ## Actual Behavior
      [What actually happens]
      
      ## Additional Context
      [Any extra info, logs, environment details]
  6. Report back:
    • Show the created issue URL
    • Show the issue number
    • Summarize what was created

Important Notes

  • Always use gh CLI for GitHub operations
  • Use a HEREDOC for the body to preserve formatting:
    gh issue create --title "Title" --body "$(cat <<'EOF'
    ## Description
    ...
    EOF
    )"
  • If images were provided, mention that they should be manually attached via the GitHub web UI if CLI upload is not possible, and provide the issue URL for easy access

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.