agentleFS
Sign inStart free
bazel-contribbazel-contrib/rules_python/.agents/skills/create-pr/SKILL.md

create-pr

Skill692 starsChanged 6 days agoApache-2.0View on GitHub

Propose, draft, or create a pull request by delegating to a

  • Commits and pushes

196 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use update-pr, act-on-feedback 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.
  • MicrosoftSkill

    update-pr

    Update the pull request for the current session. Use when the user wants to push new changes to an existing PR.

    Also in 9 projects that use this

  • MicrosoftSkill

    act-on-feedback

    Act on user feedback attached to the current session. Use when the user submits feedback on the session's changes via the Submit Feedback button.

    Also in 3 projects that use this

  • ModelEngine-GroupSkill

    create-release-note

    从 PR/commit 中自动生成结构化的 Release Notes，并可选创建 GitHub Draft Release。支持 x.y.0 版本合并前一 minor 系列的 release notes。当用户要求生成发布说明、创建 release notes 时触发。参数为版本号和可选的上一版本号。

    Also in 3 projects that use this

  • frostneySkill

    native-nostalgia-stack

    Applies the user's FreePascal toolchain and its build, formatting, hook, and test contracts while leaving project-specific mechanics local. Use when scaffolding or working in a FreePascal project that follows this toolchain.

    Also in 3 projects that use this

  • frostneySkill

    software-engineering-excellence

    Applies the user's engineering standards during substantial technical work: preserve scope, use current evidence, delegate independent parts, and complete authorized outcomes. Use during substantial implementation, debugging, refactoring, or multi-part delivery work.

    Also in 3 projects that use this

  • parkchuSkill

    start-mission

    넥스트스텝(NextStep) 미션을 처음 시작할 때, 미션 저장소를 fork·clone하고 최초 작업 브랜치(step1 등)까지 만들어 준다. gh CLI로 fork하고 clone까지 이어서 처리하며, gh가 없거나 인증이 안 돼 있으면 브라우저 Fork 안내로 폴백한다. 이미 fork/clone돼 있으면 재사용하고 이어서 진행한다(재실행 안전). 사용자가 "미션 시작하려는데 저장소 세팅해줘", "새 미션 시작할래", "fork부터 해줘", "/nextstep:start-mission" 등으로 요청할 때 사용한다.

    Also in 3 projects that use this

  • +1 more from microsoft

The file

We split this skill into the rules it gives an agent

12 rules. 0 are common, 3 are distinctive, and 9 are very specific to this project.

  • 0

    Common

    Most of the 179 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 9

    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. Distinctive:

    When proposing, drafting, or creating a Pull Request, you MUST ALWAYS delegate to a subagent.

    line 7
  2. Very specific:

    Code Review Subagent: Before launching the PR subagent, launch a subagent (invoke_subagent, TypeName: "self") to run the review-code skill …

    line 12
  3. Very specific:

    Launch PR Subagent: Use invoke_subagent (TypeName: "self").

    line 16
  4. Very specific:

    Follow CONTRIBUTING.md and @/.agents/rules/pr.md.

    line 18
  5. Very specific:

    Only use *This is an agent-generated comment reviewed and approved by the user.* if the user previously reviewed pr_info.md and approved …

    line 28
  6. Very specific:

    Artifact Requirements: Create pr_info.md in the subagent's own artifact directory (do not attempt to write to the parent's artifact …

    line 31
  7. Distinctive:

    Create a regular PR

    line 38
  8. Distinctive:

    Create a draft PR

    line 39
  9. Very specific:

    Propose vs. Create: If proposing or drafting a PR, do NOT run gh pr create or gh pr comment—only create the pr_info.md artifact.

    line 42
  10. Very specific:

    Targeting Upstream Repo: When creating, target upstream using --repo bazel-contrib/rules_python and --head <fork_owner>:<branch>.

    line 46
  11. Very specific:

    Open Questions Label: If the PR description contains open questions, apply the "do not merge" label (--label "do not merge").

    line 48
  12. Very specific:

    Interactive Actions: When presenting choices via ask_question, always include the clickable markdown link to pr_info.md in the question …

    line 60

“Common” is measured: kept by at least 6 in 10 of the 179 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

When proposing, drafting, or creating a Pull Request, you MUST ALWAYS delegate to a subagent. NEVER create or draft PRs directly in the main conversation.

Instructions

  1. Code Review Subagent: Before launching the PR subagent, launch a subagent (invoke_subagent, TypeName: "self") to run the review-code skill (.agents/skills/review-code/SKILL.md). Wait for it to finish and fix any issues before proceeding.
  2. Launch PR Subagent: Use invoke_subagent (TypeName: "self").
  3. Subagent Prompt Instructions:
    • Follow CONTRIBUTING.md and @/.agents/rules/pr.md.
    • PR Title: Conventional commits format (agents: prefix for agent rules/skills).
    • PR Body: Explain why and conceptual how. Wrap strictly at 72 columns max. Use concise, active phrasing (Strunk & White).
    • AI Disclosure Comment: Draft (and post via gh pr comment if creating the PR) the AI disclosure comment explaining how PR comments will be handled. When posted automatically during create pr without prior user review of the comment text, end it with: *This is an automatically generated agent comment.* Only use *This is an agent-generated comment reviewed and approved by the user.* if the user previously reviewed pr_info.md and approved the draft text.
    • Artifact Requirements: Create pr_info.md in the subagent's own artifact directory (do not attempt to write to the parent's artifact directory) with:
      • PR title, 72-column wrapped body, AI disclosure comment text (and comment URL if posted), and PR number/URL (if created).
      • User decision choices (include only when proposing/drafting before PR creation):
        1. Create a regular PR
        2. Create a draft PR
        3. Provide feedback on the draft text
        4. Discard the draft text
    • Propose vs. Create: If proposing or drafting a PR, do NOT run gh pr create or gh pr comment—only create the pr_info.md artifact. Execute gh pr create and gh pr comment immediately when explicitly requested to create the PR (e.g., create pr).
    • Targeting Upstream Repo: When creating, target upstream using --repo bazel-contrib/rules_python and --head <fork_owner>:<branch>.
    • Open Questions Label: If the PR description contains open questions, apply the "do not merge" label (--label "do not merge").
  4. Return Status: Direct subagent to report the PR number/draft status, AI disclosure comment URL (if posted), and the absolute file path to its pr_info.md artifact back to the caller.
  5. Publish and Link Artifact in Main Agent: Upon subagent completion, read the subagent's pr_info.md via view_file, publish it to the main agent's own artifact directory via write_to_file (UserFacing: true, and RequestFeedback: true when proposing), and output a clickable markdown link to the main agent's pr_info.md. When the PR was created immediately, summarize the created PR and posted AI disclosure comment in chat; when proposing, prompt for confirmation.
  6. Interactive Actions: When presenting choices via ask_question, always include the clickable markdown link to pr_info.md in the question prompt.

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