agentleFS
ericwood8ericwood8/skills/github-issue-creator/SKILL.md

github-issue-creator

Skill1 starsChanged 13 days agoMITView on GitHub

Use when the user pastes an error or log, describes a bug informally, shares a screenshot or voice-dictated notes, or asks to file or open a GitHub issue. Turns the input into a clean structured issue and opens it with `gh issue create`.

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use pr-creator.

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.
  • GoogleSkill

    pr-creator

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 1

    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:

    Be crisp: No filler — every line should add information a triager needs.

    line 59

“Common” is measured: kept by at least 6 in 10 of the 12 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 Creator

Turn messy input into a crisp GitHub issue, then open it with gh — don't just draft a file nobody reads.

Process

  1. Extract structure from chaos. Pull reproduction steps, error text, and expected-vs-actual behavior out of casual language, even from a stream-of-consciousness voice note or a raw stack trace paste.
  2. Infer missing context from the conversation or repo (project name, affected file, recent commit, git remote) instead of asking the user to restate what's already known — but don't invent details nothing implies.
  3. Draft the issue with the template below and show it to the user before creating anything.
  4. Create it with gh issue create --repo <owner/repo> --title "..." --body "$(cat <<'EOF' ... EOF)" only after the user confirms the draft. Opening an issue is visible to everyone watching the repo, so don't skip the confirmation step even if the request sounded like a go-ahead.

Issue Template

## Summary
[One-line description]

## Environment
- **Repo/Component**:
- **OS/Version**: (if relevant)

## Reproduction Steps
1. ...

## Expected Behavior
...

## Actual Behavior
...

## Error Details

[error text/stack trace, if applicable]


## Impact
[Critical/High/Medium/Low + why]

## Additional Context
...

Drop sections that don't apply — a one-line typo fix doesn't need "Reproduction Steps," and a feature request doesn't need "Actual Behavior."

Severity Guide

  • Critical — service/app down, data loss, security issue
  • High — major feature broken, no workaround
  • Medium — feature impaired, workaround exists
  • Low — minor or cosmetic

Guidelines

  • Be crisp. No filler — every line should add information a triager needs.
  • Redact sensitive data. Swap real secrets, tokens, connection strings, customer names, or internal-only URLs for placeholders like [REDACTED] before the issue goes anywhere public.
  • Images/GIFs: reference inline as ![description](attachment-name.png). If the user has a local screenshot, they attach it via the GitHub web UI after creation (gh issue create doesn't upload images) — say so rather than silently dropping the reference.
  • If the target repo isn't obvious from the working directory or conversation, ask which repo before drafting — don't guess at owner/repo.

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.