Review

The top-level review verb — decide WHETHER, WHEN, WHICH, and HOW HARD to review a change before reaching for a review tool. Assesses the situation (a plan vs a diff, the risk surface, what changed since the last review, rounds already spent), picks the lightest review shape the risk justifies (in-session self-review → cross-model → multi-model panel), sets an initial round budget it will extend only on convergence, and dispatches. Exists to stop review spirals: reviewing before the plan is formed, reviewing after every trivial edit, or looping a reviewer past the point of convergence. Triggers

37 stars 7 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add iamneilroberts/claude-skills --skill review
Manual install
git clone --depth 1 https://github.com/iamneilroberts/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/review ~/.claude/skills/review

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

From the SKILL.md

# /review — the review orchestrator (whether / when / which / how hard)

`/review` does not blindly review — it **assesses the situation, picks the right review shape, sets
a round budget, and then runs it** (either an in-session self-review, or by dispatching to a
cross-model gate). Reviewing badly is worse than not reviewing: reviewing before the plan is formed
wastes a pass, reviewing after every trivial edit trains you to ignore findings, and looping a
reviewer past convergence *degrades* the change.

## The ladder (lightest → heaviest)

Escalate for **independence and thoroughness**, not out of habit. Start at the lightest tier the
risk justifies:

1. **light — in-session self-review (Phase 3B).** *I* review the diff. Fastest and cheapest (no
   external model, no process spawn). Its weakness is exactly its cost: it's the author grading its
   own work — **least independent** — so it's for **low-risk** diffs and as a first pass before
   escalating.
2. **cross-model — `/codex-review`** (if present). One independent external model (different
   vendor), mechanically gated. Reach here when the diff is non-trivial or self-review's
   independence isn't enough.
3. **panel — `/review-panel`** (if present). Multiple independent reviewers, pre-merge. For complex
   or elevated-risk (privacy/cost/data-loss/money) diffs where a mistake is asymmetric.

## Phase 1 — Assess (read, don't guess)
Read the full skill on GitHub

Details

Skill name
review
Path
skills/review/SKILL.md
Repo updated
21 August 2026

FAQ

What does the Review skill do?

The top-level review verb — decide WHETHER, WHEN, WHICH, and HOW HARD to review a change before reaching for a review tool. Assesses the situation (a plan vs a diff, the risk surface, what changed since the last review, rounds already spent), picks the lightest review shape the risk justifies (in-session self-review → cross-model → multi-model panel), sets an initial round budget it will extend only on convergence, and dispatches. Exists to stop review spirals: reviewing before the plan is formed, reviewing after every trivial edit, or looping a reviewer past the point of convergence. Triggers

How do I install the Review skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add iamneilroberts/claude-skills --skill review. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Review popular?

It lives in iamneilroberts/claude-skills, which has 37 GitHub stars and 7 forks.

Related skills

Brag

37

iamneilroberts/claude-skills

Memorialize something you just built by generating a self-contained "showcase" page for it — a persuasive, good-looking deep dive: what it is, why it's impressive, how it works — with a screenshot if one can be found or captured, and links to related showcase pages. This is the sales/hype-leaning counterpart to /write-post (which drafts a neutral, no-BS technical post); reach for /brag when you want it to sell. Fast by design, like /idea: ask only what's needed, build the page, don't turn it into a project. Triggers on `/brag <subject>`, "brag about this", "make a showcase page for X", "write

Writing & Content

Branch

37

iamneilroberts/claude-skills

Create an isolated git worktree for a task and log it to a shared work journal, so multiple Claude Code sessions run in parallel without racing on HEAD, uncommitted edits, or the index. Subcommands: `list`, `done <slug>`, `update` (heartbeat), `coord <message>` / `coord clear <slug>` (cross-session constraints). Triggers on `/branch`, "start in a worktree", "isolate this work", "parallel session", "heartbeat the journal".

Git & Code Review

Claude Code Best Practices

37

iamneilroberts/claude-skills

Use when asked about Claude Code workflow, prompt caching cost, session economics, CLAUDE.md hygiene, context-window management, plan mode, permission modes, hooks, skills, subagents, checkpointing/rewind, parallel sessions, worktrees, headless/CI usage, the Agent SDK, slash commands, MCP configuration, or "what's the right way to use Claude Code for X". Also use proactively BEFORE suggesting /model, /compact, fast-mode toggle, or editing CLAUDE.md mid-session, since those bust the system cache.

AI, LLMs & Agents

Review Panel

37

iamneilroberts/claude-skills

Run multiple independent code reviewers (Codex + Gemini + a fresh Claude) on the current diff or a plan, merge their structured verdicts, and apply a consensus-gated challenge round — returning a pass/fail exit code. Use for "panel review this", "get a multi-model review before I ship", "second-opinion review this diff", or /review-panel. Complements single-reviewer /codex-review.

AI, LLMs & Agents

LLM Tools

37

iamneilroberts/claude-skills

Use when a session is about to bulk-read 3+ files or any single file over ~400 lines, generate predictable boilerplate (tests, fixtures, config scaffolds, doc templates), or compress a long session transcript — and a cheap OpenAI-compatible worker model (Kimi, DeepSeek, OpenRouter, local Ollama) is available via the llm-ask/llm-write/llm-extract CLIs.

AI, LLMs & Agents

Condense

42

robbyt/claude-skills

Deduplicate and consolidate CLAUDE.md memory files. Trigger when user says "condense my CLAUDE.md files", "deduplicate CLAUDE.md", "clean up my memory files", or "consolidate my instructions". Removes redundancy within files and across the file hierarchy.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.