agentleFS
Sign inStart free
malinskibeniaminmalinskibeniamin/skills/commit-push-pr/SKILL.md

commit-push-pr

Skill4 starsChanged 10 days agoMITView on GitHub

Commit, push, and open a reviewable PR, or execute an explicitly authorized merge. Use for delivery requests; --no-pr stops after push.

23 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use docs-ci, docs-interfaces 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.
  • jh941213Skill

    docs-ci

    문서 CI(링크·OpenAPI lint·breaking 게이트·mermaid 검증)나 문서 드리프트 감지(docs.yaml 신선도 검사)를 설치하거나 돌릴 때 사용. 문서 내용 작성은 docs-architecture·docs-interfaces·docs-manuals.

    Also in 3 projects that use this

  • jh941213Skill

    docs-interfaces

    API·이벤트 인터페이스 문서(OpenAPI·swagger·AsyncAPI 명세, 엔드포인트 레퍼런스, API 구성도·시퀀스, API CHANGELOG)를 만들거나 코드와 맞출 때 사용. 시스템 구성도는 docs-architecture, API 설계 원칙은 api-design-principles.

    Also in 3 projects that use this

  • RachaelQuiselSkill

    client-docs

    Client documentation. Use when a build needs documentation updates or missing project documents need to be identified.

    Also in 3 projects that use this

  • dbankscardSkill

    techdebt

    Find and report technical debt, duplicated code, and cleanup opportunities. Run at end of sessions.

    Also in 5 projects that use this

  • planailabsSkill

    docs-architecture

    Layout, build pipeline, and structural gotchas for this dual-Astro repo. Read before changing structure, routing, or adding content. Operational/dev-server questions → dev-build skill.

    Also in 3 projects that use this

  • diego-tobalinaSkill

    build-fix

    Fix build and compilation errors systematically. Run when build fails.

    Also in 3 projects that use this

  • +4 more from jh941213

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 17 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use REFERENCE.md and dependencies.

    line 9
  2. Very specific:

    Check status/diff/branch/log/PR.

    line 15
  3. Very specific:

    Keep feature branches; on default, create type/description.

    line 27
  4. Distinctive:

    Every PR: load PR, impact and body separately.

    line 38
  5. Very specific:

    Do not run /visual-recap or /make-pr-easy-to-review unless the user explicitly requests.

    line 48
  6. Very specific:

    Read CI: gh pr checks <number>.

    line 52
  7. Very specific:

    Follow CLAUDE.md: intent/impact/status and full PR URL on final status line, including updates.

    line 55

“Common” is measured: kept by at least 6 in 10 of the 17 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

Read Poteto.

Use REFERENCE.md and dependencies.

Explicit merge only: contract.

Preflight

  1. Check status/diff/branch/log/PR; push/PR auto-rebase behind owned PRs.
  2. Resolve endpoint: commit only, push (--no-pr), or PR. Commit-only skips remote and gh preflight.
  3. Push/PR: auto-setup safeguards; honor narrower endpoints.
  4. For PR, run gh stack view --json. Own one layer; never implicit gh stack submit.
  5. Review with owning skills; authorized council preserves coverage; do not block merely over skill invocation.
  6. Load dogfood for runnable PR work; require current PASS. BLOCKED needs user waiver.
  7. Stage by purpose; ask on unclear ownership.

Commit

With Changesets, load changesets after checks.

  1. Keep feature branches; on default, create type/description.
  2. Per coherent group, git add <explicit paths> then type(scope): description: lowercase, 5-72 chars, no period.
  3. Explicit commit-only intent stops here after clean-tree check.
  4. Push/PR, any CI fix or rebase: show origin/<branch>..HEAD, then push with tracking.
  5. User-owned feature rewrites use --force-with-lease without another permission prompt. Never plain-force; default/shared/foreign/concurrent rewrites need explicit permission.

Pull request

--no-pr never creates a PR. After push: existing PR upkeep, then check tree. Prepare evidence.

  1. Base: "${CLAUDE_PLUGIN_ROOT:-.}/scripts/resolve-pr-base.sh". Keep follow-up in current PR and metadata, including draft state. Draft PRs open without approval; stacks: /stacked-prs.
  2. Every PR: load PR, impact and body separately; keep drafts/value.
  3. Visible changes: inspect rendering; reuse checks. Captures only when helpful/required; no automatic video, annotations, snapshots or diagrams.
  4. Public repo (gh repo view --json visibility): scrub internal org, repo, product, person names and private links from commits, title, body, and evidence before push.
  5. Summarize checks/limits and dogfood inline; read back body/media access. Refresh invalidated evidence; no separate evidence file.

Upkeep: maintenance owner, select native transport before watching; no duplicate dispatcher.

Do not run /visual-recap or /make-pr-easy-to-review unless the user explicitly requests.

Completion

  1. Read CI: gh pr checks <number>; absent/pending/skipped is not green.
  2. Automatically fix applicable feedback/CI/conflicts; verify/push; continue one authorized transport.
  3. Report head/PR/checks/review gaps and continuation/blocker; honor narrower stops.
  4. Follow CLAUDE.md: intent/impact/status and full PR URL on final status line, including updates.

Preserve unrelated work; expose failures/recovery.

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