agentleFS
Sign inStart free
frostneyfrostney/knips/.agents/skills/create-issue/SKILL.md

create-issue

Skill1 starsChanged 54 days agoMITView on GitHub

Investigates and creates a project-aligned GitHub issue from a tagline or short description, using the repository's template, evidence, and labels. Use when the user runs /create-issue or asks to file a GitHub issue.

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 47 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When grill-with-docs or grill-me is registered, run its actual user-question loop before drafting.

    line 23
  2. Distinctive:

    Stop before drafting when the request conflicts with project vision, is a duplicate, or needs material facts that cannot be established.

    line 26
  3. Distinctive:

    Before posting, resolve the authenticated GitHub username and exact model name from the current GitHub account and agent environment.

    line 30
  4. Distinctive:

    Run the registered grill skill and incorporate the result.

    line 46
  5. Distinctive:

    Create the issue with the available GitHub tooling and return its URL.

    line 70

“Common” is measured: kept by at least 6 in 10 of the 47 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 issue

Turn the user's input into an implementation-ready issue grounded in the current repository, then create it after the required review boundary.

Gates

  • Investigate before drafting: read the applicable project instructions and vision, search open and closed issues for duplicates of the outcome as well as the mechanism, and inspect the affected code, tests, and docs.
  • When grill-with-docs or grill-me is registered, run its actual user-question loop before drafting. Prefer grill-with-docs. If neither is available, note that once and continue.
  • Stop before drafting when the request conflicts with project vision, is a duplicate, or needs material facts that cannot be established. For a duplicate, return the existing issue and stop without asking whether to file the same request anyway or mutate the existing issue.
  • Before posting, resolve the authenticated GitHub username and exact model name from the current GitHub account and agent environment. Stop if either is unavailable; never guess or substitute a generic label.

Automatic mode

Automatic mode applies only when the original prompt says automatic or explicitly requests it. Complete every gate, then choose the template, title, labels, and body from project evidence and create the issue without draft approval. Material ambiguity or risk disables automatic mode.

Workflow

  1. Discover the repository's issue templates and existing label conventions.
  2. Investigate the request using the gates above. Ground any progress claim in evidence gathered this run.
  3. Run the registered grill skill and incorporate the result.
  4. Draft against the matching template. Keep only decision-, implementation-, and verification-relevant content:
    • a specific plain-language title;
    • problem, current and expected behavior, scope, constraints, and required behavior;
    • reproduction and regression expectations for bugs;
    • user/test impact, likely affected area, and related work where relevant.
  5. For UI/UX work, add the affected states, current and expected visual evidence, accessibility expectations, responsive/theme scope, and applicable design system components or tokens. Upload local screenshots and videos with gh issue create --attach '<file>#<alt text>' (or gh issue edit and gh issue comment with the same flag); never commit evidence media to the repository. Put non-media evidence such as probe output inside a collapsed <details> block.
  6. Choose only existing labels unless the user asks to create one.
  7. Show the proposed title, labels, and body unless the user waived review or automatic mode applies.

  8. End the issue body with this visually separate GitHub Note, replacing both values with the exact identities resolved for this run:

    [!NOTE] Created on behalf of @username using ModelName.

  9. Create the issue with the available GitHub tooling and return its URL.

Lead with the outcome. Omit boilerplate, repeated summaries, and a narration of the workflow.

Download now (ZIP)

  • Other versions56 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 2

    1. frostney/pascal-mcp-sdk★ 291% same
    2. frostney/known-good-route★ 044% same

    Wrote their own version · 54

    1. penpot/penpot★ 62ksame name
    2. videojs/video.js★ 40ksame name
    3. yugabyte/yugabyte-db★ 11ksame name
    4. antiwork/gumroad★ 10ksame name
    5. gitkraken/vscode-gitlens★ 9.9ksame name
    6. camunda/camunda★ 4.3ksame name
    7. robustmq/robustmq★ 1.8ksame name
    8. aws-powertools/powertools-lambda-typescript★ 1.8ksame name
    9. classroomio/classroomio★ 1.7ksame name
    10. tikv/pd★ 1.2ksame name

    44 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use create-release, merge-pr and 2 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.
    • MicrosoftSkill

      create-release

      Prepare BC-Bench release notes for review. Use when creating a release, screening merged PRs since the previous version tag for changes that may affect evaluation results, matching recent GitHub release notes, or reporting the agent harness and development tool versions shipped by a release.

      Also in 4 projects that use this

    • TermiX-officialSkill

      merge-pr

      Merge a GitHub PR via squash after /preparepr. Use when asked to merge a ready PR. Do not push to main or modify code. Ensure the PR ends in MERGED state and clean up worktrees after success.

      Also in 3 projects that use this

    • SentrySkill

      write-docs

      Create or update documentation pages for the Abacus docs site. Use when adding new documentation, updating existing pages, or ensuring docs stay in sync with code changes. Ensures pages follow Starlight patterns and build correctly.

      Also in 3 projects that use this

    • DockerSkill

      review-pr

      Review one or more incoming Docker documentation pull requests as a maintainer. Independently validate technical claims, assess editorial fit and information architecture, choose a verdict, and draft exact inline or PR-wide feedback behind a confirmation gate. Use for requests such as "review PR 123", "is this PR correct?", "does this information belong here?", "validate this PR", or "help review backlog PRs". Do not use to maintain or fix a PR you own; use maintain-pr for that.

      Also in 9 projects that use this

  • In this repository19 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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.

Check your setup, free