agentleFS
Sign inStart free
TangleMLTangleML/tangle-ui/.claude/skills/pr-description/SKILL.md

pr-description

Skill104 starsChanged 9 days agoApache-2.0View on GitHub

Draft or rewrite pull request titles and descriptions in plain language using the repository template. Use when preparing a new PR description or updating an existing one.

94 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ao-desktop-dev, bug-triage and 10 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.
  • agentlab-inSkill

    ao-desktop-dev

    Launch, restart, or troubleshoot the real AO Electron desktop app from this repository; run a checkout against isolated or real local AO data; combine PR branches for local UI review; and diagnose stale Electron processes, port conflicts, or preload bridge mismatches. Use whenever asked to run, open, show, or visually verify AO frontend changes in the actual desktop app rather than ao preview, dev:web, or mock data.

    Also in 4 projects that use this

  • jMertaSkill

    bug-triage

    Use when the user reports a bug, regression, runtime error, failing build, or broken test and wants reproduction, diagnosis, root-cause analysis, or an authorized fix. Isolates the shared cause and verifies the smallest relevant change.

    Also in 4 projects that use this

  • GitHubSkill

    commit-message

    Generate conventional commit messages - use when creating commits, writing commit messages, or asking for git commit help

    Also in 9 projects that use this

  • saffron-healthSkill

    address-review

    Address PR review comments systematically. Use when responding to code review feedback on a pull request.

    Also in 3 projects that use this

  • NVIDIASkill

    writing-docs

    Use when adding or changing user-facing behavior or documentation in Megatron-Energon, or when creating new .py, .sh or .md files that need license headers.

    Also in 3 projects that use this

  • Sagargupta16Skill

    dependency-audit

    Audit project dependencies for security vulnerabilities, licensing issues, maintenance health, and optimization opportunities. Use it during regular security audits (monthly or quarterly); before a major release when you want to ensure the dependency tree is clean; when evaluating whether to adopt or replace a dependency; after a security advisory affects one of your dependencies; when your install times or bundle sizes have grown noticeably.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 89 edited versions we read keep these.

  • 11

    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:

    Use the repository PR template for section order and prompts.

    line 8
  2. Distinctive:

    Read the changes against the actual base branch and enough surrounding code to understand the behavior before and after.

    line 14
  3. Distinctive:

    Keep each section short. A small change may need only a sentence per section.

    line 25
  4. Distinctive:

    Avoid file inventories, jargon, repeated points, and the history of the work.

    line 26
  5. Distinctive:

    Do not invent user-facing problems for internal work or add unsupported claims.

    line 29
  6. Distinctive:

    Use a closing issue reference only when this PR actually resolves the issue.

    line 30
  7. Distinctive:

    Start with numbered UI steps using real screen and control names and visible expected results.

    line 34
  8. Distinctive:

    Do not replace UI steps with commands merely because the UI was not tested.

    line 36
  9. Distinctive:

    When there is no meaningful UI route, explain why and give the smallest useful commands or other steps, including what success looks like.

    line 39
  10. Distinctive:

    Write testing instructions directly, without a preamble saying they are suggestions or were not run for the description.

    line 41
  11. Distinctive:

    Keep drafts in chat unless the user authorizes creating or updating the PR.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 89 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

PR Descriptions

Use the repository PR template for section order and prompts. Keep the description understandable to someone who does not write code and has not seen the conversation.

Establish the facts

  • Read the changes against the actual base branch and enough surrounding code to understand the behavior before and after. Do not rely on commit messages alone.
  • For an existing PR, read its current description. Preserve useful screenshots, test evidence, issue links, and dependencies.
  • For a stack, describe only this PR's changes against its actual parent and name any dependency. Do not claim behavior delivered only by another PR.

Write the description

  • Give the title and opening explanation a clear purpose in everyday language. Explain who benefits, what happens today, and what will happen after the change.
  • Keep each section short. A small change may need only a sentence per section. Avoid file inventories, jargon, repeated points, and the history of the work.
  • Include technical details when they help reviewers understand behavior, a tradeoff, or an important limitation. Explain unfamiliar terms.
  • Do not invent user-facing problems for internal work or add unsupported claims. Use a closing issue reference only when this PR actually resolves the issue.

Make testing concrete

  • Start with numbered UI steps using real screen and control names and visible expected results. Include relevant existing behavior that should still work. Do not replace UI steps with commands merely because the UI was not tested.
  • Assume the normal frontend and backend are already running. Mention only extra services or unusual setup, and call out when verification needs no backend.
  • When there is no meaningful UI route, explain why and give the smallest useful commands or other steps, including what success looks like.
  • Write testing instructions directly, without a preamble saying they are suggestions or were not run for the description. Add a short factual note for relevant checks actually performed or specific verification gaps. Never claim a check ran or passed without evidence; automated checks do not establish that the UI was tested.

Keep drafts in chat unless the user authorizes creating or updating the PR. This skill does not itself authorize publishing or changing other PR metadata.

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.

Check your setup, free