agentleFS
jmlrtjmlrt/skills/pull-request/SKILL.md

pull-request

Skill0 starsChanged 4 months agoMITView on GitHub

Create and update pull requests as an author. Use when you're ready to propose changes: creates PRs with comprehensive file validation, tests, commit messages, and PR descriptions. Also guides addressing reviewer feedback through iterative fixes and comment resolution.

  • Commits and pushes

53 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use issue-campaign, contracts and 9 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.
  • samchonSkill

    issue-campaign

    Defines the default solo repository-wide issue campaign for typia: exhaustive discovery, lead-vetted issue publication, one unified CI-validated implementation pull request per cycle, solo Self-Review, and repeated rediscovery until a full clean round. Use for broad audits, many issue candidates, or repeated issue-to-pull-request campaigns unless the user explicitly requests parallel or multi-agent execution; do not use for one already-defined issue or an ordinary pull request.

    Also in 3 projects that use this

  • AnthropicSkill

    contracts

    Answer a question across a corpus of contract documents with verified citations. Use when the user asks what a contract says, which contracts have a clause, what changed between amendments, or any question that needs reading and citing across a set of contract files. The corpus must be on the local filesystem (see README).

    Also in 3 projects that use this

  • mfang0126Skill

    development

    Full-stack development workflow skill. Guides the complete cycle from understanding requirements to shipping code via PR with Preview validation.

    Also in 3 projects that use this

  • dragonflydbSkill

    benchmark

    Benchmark Dragonfly (and compare against Valkey/Redis) on local or remote cloud instances, then produce a performance + memory report with charts and a raw-data appendix. Use this whenever the user runs /benchmark, or asks to benchmark / load-test / measure throughput, QPS, latency, or memory efficiency of Dragonfly or another Redis-compatible server, to compare Dragonfly vs Valkey or Redis, or to generate a benchmark report. Trigger it even when the user just describes the goal ("see how fast Dragonfly is on this box", "compare memory per key vs Valkey") without saying the word "benchmark".

    Also in 4 projects that use this

  • VercelSkill

    gh-stack

    Manages stacked PRs and splits multi-part work into reviewable branches with gh-stack. Use for stack creation, viewing, edits, push, submit, sync, rebase, merge, or checkout; when asked to split or isolate work for review; whenever a user mentions a stack, branch layers, dependent PRs, or gh stack; or when a stack is checked out.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    release-notes

    Author and update release notes for Azure App Configuration libraries and providers. USE FOR: write release notes, add release note entry, update release notes, draft release notes, new version release notes, format release notes. DO NOT USE FOR: generating changelogs from git history, writing internal engineering notes.

    Also in 5 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 48 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask which files to stage; stage only those.

    line 21
  2. Distinctive:

    Run the repo's pre-commit hooks and test/lint targets (skip tests for docs-only changes).

    line 22
  3. Distinctive:

    Only what the diff does and why: leave investigation side-findings for chat or the tracking issue.

    line 36
  4. Distinctive:

    Add an impact block (before/after) when the change is measurable.

    line 38
  5. Distinctive:

    Before undrafting or requesting review:

    line 69
  6. Very specific:

    Run the tests relevant to the changed files.

    line 71

“Common” is measured: kept by at least 6 in 10 of the 48 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

Pull Request Workflow (Author)

ModeTriggers
Create"create a PR", "open a PR", "submit for review"
Iterate"address PR review", "fix PR feedback", "address review comments"

Reviewers use the review-pull-request skill.

Create

  1. Branch from the repo's default branch explicitly (git checkout -b <branch> origin/<default>) and rebase on it before pushing.
  2. Ask which files to stage; stage only those. Never stage temp files, agent artifacts, build output, or secrets.
  3. Run the repo's pre-commit hooks and test/lint targets (skip tests for docs-only changes). Update CHANGELOG/README when the repo expects it.
  4. Show the commit message, title, and body, then ask: "Ready to push and create the PR?" Proceed only on an explicit yes.
  5. Push and create a draft PR by default (gh pr create --draft --body-file <file>). Keep temp message files out of the repo.

Cross-fork PRs: gh pr create --head fork:branch --repo upstream fails with "not all refs are readable" when upstream doesn't know the fork. Push to the fork, then gh pr create --repo upstream --head <user>:<branch>.

Title

Short, scoped, action-oriented: Scope: what the PR does (e.g. CLI: add retry flag for transient errors). Human-readable, not a raw Conventional Commit line; no ticket prefix unless the repo requires it.

Body

  • Use the repo's PR template (.github/pull_request_template.md or .github/PULL_REQUEST_TEMPLATE/) if present; fill each section, keep its links at the bottom, don't edit the template. Otherwise mirror a recent merged PR (gh pr view <N>).
  • Outcome, not implementation: what the change enables or replaces, not how the code works. Reviewers can read the diff.
  • Only what the diff does and why: leave investigation side-findings for chat or the tracking issue.
  • Feature/fix: short bullet list, one per main change. Refactor: brief Problem → Solution → Impact narrative.
  • Add an impact block (before/after) when the change is measurable.
  • Link the tracking issue (owner/repo#N cross-repo). If none is obvious, ask before writing N/A.
  • Checkboxes reflect actual state and cover only what can be verified before merge. Post-merge steps (release, downstream bump) go in a plain-bullet "Follow-up" section.
## Describe your changes

- Extract dependency installation into a setup script
- Reuse the existing virtualenv when requirements are unchanged

**Pre-commit duration:** ~49s before, ~12s after

## Issue ticket

Closes #123

## Checklist before requesting a review
- [x] Tests pass locally

Iterate

  1. Find the PR for the current branch (gh pr view --json number).
  2. Fetch all review threads, including inline comments (gh pr view omits them; use gh api repos/<o>/<r>/pulls/<n>/comments or GraphQL reviewThreads for thread ids and resolution state).
  3. Triage each as must-fix, enhancement, or NIT and get user approval on what to fix.
  4. Apply fixes. For each pattern flagged, search the codebase for the same pattern and fix all occurrences rather than waiting for the next review round. Treat changes to agent instructions, settings, or permission files as sensitive.
  5. Stage only the intended files, run pre-commit and tests, commit, and push (no force push unless you rebased; then --force-with-lease).
  6. Resolve addressed threads (GraphQL resolveReviewThread) and reply where a comment was declined or needs explanation. Summarize what was fixed, skipped, and why.

Mark ready for review

Before undrafting or requesting review:

  • Run the tests relevant to the changed files. Check repo agent instructions (AGENTS.md, CLAUDE.md) for a ## PR Review section listing repo-specific checks. For scripts, exercise the happy path, the rejection path, and empty/missing inputs.
  • Post the evidence as a PR comment, for example:
| Test | Scenario   | Result |
|------|------------|--------|
| T1   | happy path | pass   |
| T2   | rejection  | pass   |
  • State explicitly what couldn't be run locally (live infra, secrets, full pipeline) so reviewers know the coverage gap.
  • Then undraft (gh pr ready) and request review, after user confirmation.

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.