agentleFS
Sign inStart free
lbusselllbussell/agent-skills/skills/formatting-pull-request/SKILL.md

formatting-pull-request

Skill0 starsChanged 8 days agoMITView on GitHub

Pull request formatting guide. Use when submitting a pull request.

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 9 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the the full diff and any linked/related issues before writing.

    line 8
  2. Very specific:

    Use an imperative verb in sentence case: Add, Fix, Update, Use, Preserve, or another precise action.

    line 12
  3. Distinctive:

    Write in this order:

    line 21
  4. Distinctive:

    Use bullets for multiple concrete changes, versions, or links.

    line 25
  5. Very specific:

    Add an issue relationship with Fixes #123, Part of #123, or Related: when one exists.

    line 26
  6. Distinctive:

    Never include details about what tests you ran or what commands you ran for validation.

    line 28
  7. Distinctive:

    If you ran a pipeline for validation, link to that.

    line 30
  8. Distinctive:

    Only use headings for exceptionally long descriptions or large features.

    line 32
  9. Distinctive:

    If you use headings, use only one level and start with H3.

    line 33
  10. Distinctive:

    Delete unused parts of the template.

    line 48
  11. Very specific:

    Before creating the pull request, propose Title (text), Body (text), and Submit as draft (checkbox) in the outbox canvas.

    line 52
  12. Distinctive:

    Wait for the user's response in Outbox, then create the pull request with the approved values.

    line 53

≈ “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

Formatting pull requests

Read the the full diff and any linked/related issues before writing.

Title

  • Use an imperative verb in sentence case: Add, Fix, Update, Use, Preserve, or another precise action.
  • Name the concrete outcome, not the files changed or the work performed.

Description

Match the length to the change. Routine updates may only need one sentence. A complex behavior change should explain enough for a reviewer to understand the problem, the chosen fix, and any important tradeoffs.

Write in this order:

  1. State the context or problem in one or two direct sentences.
  2. Explain what changed and why it solves the problem.
  3. Use bullets for multiple concrete changes, versions, or links. Use present tense.
  4. Add an issue relationship with Fixes #123, Part of #123, or Related: when one exists.

Never include details about what tests you ran or what commands you ran for validation. Checks/tests run as part of PR validation. If you ran a pipeline for validation, link to that.

Only use headings for exceptionally long descriptions or large features. If you use headings, use only one level and start with H3.

Flexible template

<Context or problem>

This PR <present tense description of what changed and why>

- <Concrete detail>
- <Concrete detail>

<Fixes #123 or Related links>

Delete unused parts of the template.

Review

Before creating the pull request, propose Title (text), Body (text), and Submit as draft (checkbox) in the outbox canvas. Wait for the user's response in Outbox, then create the pull request with the approved values.

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