agentleFS
dream-horizon-orgdream-horizon-org/pulse/.agents/skills/pr-review/SKILL.md

pr-review

Skill44 starsChanged 5 months agoApache-2.0View on GitHub

Workflow for reviewing pull requests via GitHub MCP or GitHub CLI (gh) and team coding standards. Use when reviewing PRs, checking code quality, or providing structured review feedback.

  • Reads credentials

195 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use clack-cli-patterns, drag-to-reorder 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.
  • openchamberSkill

    clack-cli-patterns

    Use when creating or modifying OpenChamber CLI commands, prompts, terminal output, non-TTY behavior, `--quiet`, or `--json` behavior.

    Also in 3 projects that use this

  • openchamberSkill

    drag-to-reorder

    Use when implementing or modifying OpenChamber sortable or drag-to-reorder behavior, especially `@dnd-kit`, touch/mobile interactions, variable-width items, or wrapping layouts.

    Also in 3 projects that use this

  • jtenniswoodSkill

    expert-reset

    Reimagine this repository from first principles using the current product and user experience as the target. Use when the user says "/expert-reset", asks how the project should be rebuilt if starting again, wants bold architecture or component-structure recommendations, or wants a research-only reset plan unconstrained by current implementation details.

    Also in 3 projects that use this

  • CES-LtdSkill

    oss-pr

    Use when creating a pull request, after committing changes, or when user invokes /oss-pr. Covers branch management, quality checks, commit, push, and PR creation.

    Also in 3 projects that use this

  • CES-LtdSkill

    pr-automation

    PR Automation Orchestrator: poll open PRs, check CI, run review, fix, and merge eligible PRs. Use when: (1) Invoked by daemon via scripts/pr-automation.sh, (2) User says "/pr-automation".

    Also in 3 projects that use this

  • +7 more from openchamber

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 180 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Use one of the following. Prefer MCP when it is connected and healthy.

    line 19
  2. Very specific:

    Read the MCP tool schemas in the Cursor mcps folder, then call the documented tools.

    line 23
  3. Distinctive:

    Follow the prompts: GitHub.com vs Enterprise, HTTPS vs SSH, then either “Login with a web browser” or “Paste an authentication token.”

    line 39
  4. Very specific:

    If gh prints 401 or 403, complete gh auth login or refresh SSO (gh auth refresh -h github.com with -s scopes if needed).

    line 78
  5. Very specific:

    After fetching, proceed to Step 2 using the same review checklists whether data came from MCP or gh.

    line 80

“Common” is measured: kept by at least 6 in 10 of the 180 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

PR Review Workflow

Workflow

- [ ] Step 1: Fetch PR details (MCP or gh — see below)
- [ ] Step 2: Review diff by area
- [ ] Step 3: Check cross-cutting concerns
- [ ] Step 4: Provide structured feedback

Step 1: Fetch PR Details

Use one of the following. Prefer MCP when it is connected and healthy; otherwise use GitHub CLI in the project repo (or any cwd) with a logged-in user.

Option A: GitHub MCP (when available)

Read the MCP tool schemas in the Cursor mcps folder, then call the documented tools. Typical names:

  • get_pull_request — title, description, author, base/head branches
  • get_pull_request_files — list of changed files
  • get_pull_request_diff — full diff

Option B: GitHub CLI (gh)

Requires GitHub CLI installed and authenticated (gh auth status succeeds).

One-time login (interactive):

gh auth login

Follow the prompts: GitHub.com vs Enterprise, HTTPS vs SSH, then either “Login with a web browser” or “Paste an authentication token.”

Credentials you need:

MethodWhat you use
Web browserYour normal GitHub account sign-in (SSO/org access if the org requires it). No manual token copy if you use the browser flow.
Personal Access Token (HTTPS)A classic PAT with at least repo (private repos), or a fine-grained token with Repository access to the target repo and permissions: Contents Read, Metadata Read, Pull requests Read.

Verify:

gh auth status

Fetch PR metadata and changed files (replace OWNER, REPO, N):

gh pr view N --repo OWNER/REPO --json title,body,author,baseRefName,headRefName,state,commits,files

Full diff (patch):

gh pr diff N --repo OWNER/REPO

List file names only:

gh pr view N --repo OWNER/REPO --json files --jq '.files[].path'

Checkout the PR branch locally (optional, for git inspection):

gh pr checkout N --repo OWNER/REPO

If gh prints 401 or 403, complete gh auth login or refresh SSO (gh auth refresh -h github.com with -s scopes if needed).

After fetching, proceed to Step 2 using the same review checklists whether data came from MCP or gh.

Step 2: Review by Area

Backend Changes (backend/)

  • Service interface + impl pattern
  • ServiceError used for errors (not raw exceptions)
  • SQL in Queries class (not inline)
  • RxJava types (Single, Maybe, Completable)
  • MapStruct mapper (not manual mapping)
  • Lombok annotations on DTOs
  • Tests with >80% coverage on changed code
  • Checkstyle: 140 char lines, 2-space indent

Frontend Changes (pulse-ui/)

  • Screen folder convention followed
  • Mantine components (not raw HTML)
  • TanStack Query for server state
  • makeRequest for API calls
  • Types in .interface.ts files
  • CSS modules (not inline styles)

AI Agent Changes (pulse_ai/)

  • FunctionTool pattern with ToolContext
  • STATE_KEYS for state (not strings)
  • Registry entries (not hardcoded)
  • SQL safety enforced

Deploy Changes (deploy/)

  • Health check included
  • Dependencies with service_healthy condition
  • .env.example updated for new vars
  • No secrets in committed files

Step 3: Cross-Cutting

  • Alert metric changes → all 5 layers updated?
  • New env vars → added to .env.example?
  • New API endpoints → DTO + service + DAO + mapper + tests?
  • Security: no secrets, keys, or credentials in code?

Step 4: Feedback Format

## Review Summary

### Critical (must fix)
- ...

### Suggestions (should improve)
- ...

### Nice to Have (optional)
- ...

Include specific file:line references and code examples for fixes.

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.