agentleFS
brayandiazcbrayandiazc/project-starter-template-en-ai/.claude/skills/open-pr/SKILL.md

open-pr

Skill2 starsChanged 2 months agoMITView on GitHub

Drafts a pull request for the current branch by filling out the repository's PR template based on the branch's changes. Use this when the user asks to open/create a PR, prepare a pull request, or write a PR description (e.g. "open a PR", "draft the pull request for this branch"). Does not merge.

  • Commits and pushes

67 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use implement-change, review-change and 8 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.
  • Codagent-AISkill

    implement-change

    Implements an approved change in one continuous session, with tiered test runs. Use when asked to implement a change from its approved definition, or to invoke codagent:implement-change.

    Also in 3 projects that use this

  • thlaureSkill

    review-change

    Use this skill when the user asks for a code review, a correctness pass, a check before PR, or asks whether a Signalist change follows project conventions.

    Also in 4 projects that use this

  • DataCoveySkill

    commit-push

    Commit and push the changes made on this chat session to the current branch. Use best practices from Conventional Commits.

    Also in 3 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

  • AnthropicSkill

    write-spec

    Write a feature spec or PRD from a problem statement or feature idea. Use when turning a vague idea or user request into a structured document, scoping a feature with goals and non-goals, defining success metrics and acceptance criteria, or breaking a big ask into a phased spec.

    Also in 3 projects that use this

  • owidSkill

    babysit-pr

    Spawn a background agent that babysits an open PR — triggers a Codex review, watches CI, judges and fixes valid findings, replies to and resolves review threads, and loops to a cap. Never merges. Trigger when the user asks to "babysit the PR", "ask for codex review(s) and watch CI", or after pushing a substantial chunk to a PR branch.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 66 edited versions we read keep these.

  • 1

    Distinctive

    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
  • could be automatic: a setting could enforce it
  1. Very specific:

    Run the doc-keeper subagent over the diff: it syncs docs/architecture/*,

    line 10
  2. Very specific:

    Run bash .githooks/pre-push: the CI checks, in about fifteen seconds and without spending Actions minutes.

    line 13
  3. Very specific:

    Read .github/PULL_REQUEST_TEMPLATE.md to learn the required sections and checklist.

    line 22
  4. Very specific:

    Create the PR with the gh CLI (e.g.

    line 31
  5. Distinctive:

    Do NOT merge, do NOT approve, and do NOT check off checklist items that are not actually done.

    line 34

“Common” is measured: kept by at least 6 in 10 of the 66 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

Prepare a pull request for the current branch.

  1. Before drafting anything, get the change ready. This is the only moment when someone looks at the whole set, and whatever is not updated here never gets updated:

    • Run the doc-keeper subagent over the diff: it syncs docs/architecture/*, the diagrams (entities, screens, auth, components), the ADR if a decision was made, the CHANGELOG.md entry, and the roadmap item the spec declared.
    • Run bash .githooks/pre-push: the CI checks, in about fifteen seconds and without spending Actions minutes.
    • Go through docs/conventions/definition-of-done.md, and especially the part no machine checks: a human review of the schema, authorization tested with another role, the four UI states.

    If anything is red, do not open the PR: say so and fix it first. A PR that is born red gets normalized and stops being looked at.

  2. Read .github/PULL_REQUEST_TEMPLATE.md to learn the required sections and checklist.
  3. Gather context on the branch's changes:
    • git log <base>..HEAD --oneline for the commit list (base is usually main).
    • git diff <base>...HEAD --stat and review notable diffs.
  4. Fill in every section of the template using that context:
    • Summary of what changed and why.
    • Linked issues / related ADRs or specs if referenced.
    • Testing notes (what you ran or what the reviewer should check).
    • Tick checklist items that genuinely apply; leave the rest for the author.
  5. Create the PR with the gh CLI (e.g. gh pr create --title ... --body ...) if the branch is pushed; otherwise output the filled template for the user to paste.
  6. Report the PR URL or the drafted body.

Do NOT merge, do NOT approve, and do NOT check off checklist items that are not actually done. Write a draft PR if the work is incomplete.

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.