PR Review Pipeline

Example multi-phase skill — reviews a pull request by spawning a security specialist and a performance specialist in parallel, each primed with a numbered checklist, then merges their findings into a deterministic workspace. Structural reference for building phased skills with sub-agents; not wired to anything, do not invoke it.

5 starsGit & Code Review Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add tomada1114/tomada-claude-plugins

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add tomada1114/tomada-claude-plugins --skill pr-review-pipeline
Manual install
git clone --depth 1 https://github.com/tomada1114/tomada-claude-plugins.git /tmp/tomada-claude-plugins
mkdir -p ~/.claude/skills
cp -r /tmp/tomada-claude-plugins/tomada-kit/skills/creating-agent-skills/examples/pr-review-pipeline ~/.claude/skills/pr-review-pipeline

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# PR Review Pipeline (structural example)

Shows one shape: parallelism inside a phase, phases in strict sequence, sub-agents that never talk to each other, and a workspace path derived from the arguments rather than invented per run.

## Contract

**Input:** a PR number in `$ARGUMENTS`.

**Workspace:** `~/code-reviews/{pr-number}-{slug}/`, slug = PR title lowercased, kebab-cased, ASCII, max 5 words.

**Outputs:** `diff.patch` (snapshot) · `findings-security.md` · `findings-performance.md` · `review.md` (merged, severity-ranked).

Deriving the path from the input rather than a timestamp is what makes a re-run after a force-push land on top of the previous review instead of beside it.

## Phase 0: Workspace

1. Take the PR number from `$ARGUMENTS`; ask if missing.
2. `gh pr view <num> --json title -q .title` → slug → workspace path. Create it. If it already exists, ask whether to overwrite or read the existing findings.
3. `gh pr diff <num> > <workspace>/diff.patch`.
4. Read `diff.patch` once here and extract the changed-file list grouped by directory, with hunk line ranges.

Step 4 is what makes the Phase 1 prompts concrete. Fetching once and writing to disk also means two fresh contexts can both read the diff without two round trips.

## Phase 1: Parallel specialists
Read the full skill on GitHub

Details

Skill name
pr-review-pipeline
Path
tomada-kit/skills/creating-agent-skills/examples/pr-review-pipeline/SKILL.md
Repo updated
12 November 2026

FAQ

What does the PR Review Pipeline skill do?

Example multi-phase skill — reviews a pull request by spawning a security specialist and a performance specialist in parallel, each primed with a numbered checklist, then merges their findings into a deterministic workspace. Structural reference for building phased skills with sub-agents; not wired to anything, do not invoke it.

How do I install the PR Review Pipeline skill?

Claude Code plugin: /plugin marketplace add tomada1114/tomada-claude-plugins. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is PR Review Pipeline popular?

It lives in tomada1114/tomada-claude-plugins, which has 5 GitHub stars and 0 forks.

Related skills

Auditing Prompt Docs

5

tomada1114/tomada-claude-plugins

Audit and fix prompt-bearing documents — SKILL.md, CLAUDE.md, AGENTS.md, agent and command definitions, reference files, whole repositories — against Anthropic's published prompting guidance for current Claude models, proposing edits for approval before writing anything. Also answers how to prompt a specific model: holds the per- model guidance for Claude Fable 5.2, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 alongside the cross-model practices. Use when reviewing or slimming an instruction file, when instructions are ignored or fire too often, when migrating a prompt to a newer m

AI, LLMs & Agents

Auditing Repositories

5

tomada1114/tomada-claude-plugins

Audit the repository you are in, often a template or an app cut from one, for technical debt and room to improve in four areas: architecture and design patterns; tests; file structure and code quality; and tooling, CI, dependencies and the agent harness. Design a safe, test-first fix for every evidenced finding, and file the findings as GitHub issues that follow the repository's own issue conventions (triaging-issues, issue forms, past issues). A finding inherited from the template is also filed in the template repository. Cheap read-only sub-agents collect the evidence and high-effort analyst

Testing & QA

Authoring Goal Prompts

5

tomada1114/tomada-claude-plugins

Author a self-contained prompt for Claude Code's /goal command, run unattended in a separate session — a lead-to-staff handoff where this session researches, designs, and decides with full context, and a fresh executor session (Opus 5.5 or Fable 5.2, with none of that context) implements. Drafts a goal with measurable done-criteria, transcript-verifiable checks, scope + anti-cheat constraints, and stop rules; packages design intent, code examples, research findings, checklists, and pre-answered decisions as support files in a per-goal state directory whenever the executor would otherwise re-de

AI, LLMs & Agents

Review PR Codex

5

Magnus-Gille/claude-skills

Run a requested, read-only cross-model review of a pull request or branch diff using the installed Codex CLI. Use only when the user asks for review-pr-codex or a Codex PR review.

Git & Code Review

Commit

5

Magnus-Gille/claude-skills

Create or amend a Git commit with author verification, diff review, and a conventional message. Use only when the user explicitly asks to commit or amend changes.

Git & Code Review

Ticket Fleet

5

Magnus-Gille/claude-skills

Compatibility route for legacy ticket-fleet requests. Use ship-it's PR endpoint for each scoped ticket (a Plane ticket key such as GRIM-87) and its batch reference for coordination; this entrypoint does not dispatch workers or authorize merge/deploy.

Git & Code Review

Browse the most popular Claude skills, all git & code review skills, or write your own with the skills generator.