MCPInstall

review

Unified review skill — auto-detects plan or code, assembles the right panel, runs a bounded review-fix loop with severity gating. Use when a plan or implementation needs review.

Installs
393
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/camacho/ai-skills --skill review
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads review automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

/review

Detects whether to review a plan or code, assembles the right panel, runs the review-fix loop.

1. Detect Mode

From args or context:

  1. Explicit: /review plan or /review code — use that.
  2. Plan file exists in ai-workspace/plans/ (non-.done.md) and no commits beyond main — plan mode.
  3. git diff main...HEAD produces output — code mode.
  4. Ambiguous — ask: "Reviewing the plan or the code?"

Optional overrides after mode:

  • Round cap: default 3. "thorough" (5) or "quick" (1).
  • Severity gate: defaults differ by mode — plan mode = P2, code mode = P3 (local-merge flow assumes nits are cheaper to fix now than to file as issues). "strict" forces P1, "p2" forces P2, "lenient" forces P3.

2. Assemble Panel

Plan mode (Step 4)

Lead: technical-editor (always). Target: the plan file.

Code mode (Step 6)

Lead: code-reviewer (always). Target: changed files (git diff main...HEAD).

Conditional reviewers (both modes)

Scan the target for signals. Add matching reviewers:

SignalPlan modeCode mode
Architecture, new modules, DI patternsarchitect-reviewerarchitect-reviewer
AGENTS.md, config.toml, sync.sh, skillscodex-specialistcodex-specialist
Auth, credentials, tokens, secretssecurity-auditorsecurity-auditor
UI, CSS, components, accessibilityui-designerdesign-reviewer

No signal match — run with lead only.

Invoke /assemble-panel if available for RETAIN, EXPAND, CONVERGE, and ESCALATE_RECURRING governance. Do not duplicate its policy algebra.

Codex/Cursor: read .agents/skills/assemble-panel/SKILL.md and apply inline.

3. Dispatch

  • Plan mode: invoke /plan-review via Skill tool. Pass panel and round cap. Its internal P0 loop counts as R1.
  • Code mode: dispatch panel via Agent tool. Request severity-tagged findings (P0-P3).

Untagged findings: treat as P1.

4. Loop: Fix, Record, Re-review

For each round (R1..R{cap}):

a. Triage by severity gate:

  • Fix (P0 through P{gate}): fix immediately. Commit: fix: address R{N} review findings with Co-Authored-By trailer.
  • Record (P{gate+1}+): record, do not fix.

b. Record below-gate findings:

  • Plans: append ### Deferred Findings (R{N}) to the plan file.
  • Code: gh issue create --label review-finding --title "R{N}: <summary>". Cap 10/round, 20 total. If gh unavailable, append to .branch-context.md.

c–f. Panel governance — invoke /assemble-panel for RETAIN, EXPAND, CONVERGE, ESCALATE_RECURRING.

Terminal P3 Sweep (code mode, gate = P3)

P3 nits multiply: fixing 15 P3s produces a diff that re-enters the panel and surfaces 15 new P3s. To bound this, the last fix round in code mode is a terminal sweep:

  1. Apply P3 fixes from the round.
  2. Commit: fix: address R{N} review findings (P3 sweep).
  3. Run validation (typecheck + tests). If any fail, treat the failure as a new round at gate=P2 — the sweep is voided and the loop continues normally.
  4. Do NOT re-dispatch the panel for another round.
  5. Print the summary and exit with verdict APPROVE.

A round is the terminal sweep when all of: gate is P3, no P0/P1/P2 findings remain unfixed, and the round surfaced only P3 findings. P0–P2 findings always re-enter the loop normally (terminal sweep applies only to nit-only rounds).

5. Summary

Review Summary
───────────────────────────────────────
Mode:      plan | code
Target:    <file or diff summary>
Rounds:    <N of cap>
Gate:      P<N>

│ Round │ P0 │ P1 │ P2 │ P3+ │ Fixed │ Recorded │
│───────│────│────│────│─────│───────│──────────│

Verdict: APPROVE | ESCALATE
  • APPROVE — all above-gate findings resolved. Next step:
    • Plan mode → Build (Step 5)
    • Code mode → Archive (Step 7)
  • ESCALATE — unresolved above-gate findings after cap. Present to human.

Guardrails

  • Never modify protected files (see AGENTS.md).
  • Hard max: 5 rounds even if requested higher.
  • Never auto-merge or auto-approve. Produces a verdict, not an action.
  • Plain text output only — cross-surface safe.

Fallbacks

  • /plan-review unavailable → dispatch technical-editor + architect-reviewer directly.
  • /assemble-panel unavailable → fall back to [technical-editor, code-reviewer], gate=P2, cap=3.
  • gh not authenticated → degrade to .branch-context.md.
  • Reviewer returns DROP → exit immediately, print summary.

FAQ

What does the review skill do?

Unified review skill — auto-detects plan or code, assembles the right panel, runs a bounded review-fix loop with severity gating. Use when a plan or implementation needs review.

How do I install review?

Run npx skills add https://github.com/camacho/ai-skills --skill review in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/review/ (personal) or .claude/skills/review/ (project).

Which AI agents can use review?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is review safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains review?

It is published by camacho in camacho/ai-skills. It has 393 recorded installs.

More from camacho/ai-skills

View all →

archive

camacho/ai-skills

Fills Outcomes & Learnings in a plan file and renames it to .done.md.

bail

camacho/ai-skills

Reflects, updates GitHub Issue, closes PR if open, cleans up worktree/branch.

capture

camacho/ai-skills

Creates a draft GitHub Issue with triage label from natural language description.

669 installs

plan-review

camacho/ai-skills

Auto-assembles review panel using deterministic rules, dispatches agents against plan file, collects verdicts.

orient

camacho/ai-skills

Fetches issue context, auto-detects task type, maps to branch prefix, presents brief.

reflect

camacho/ai-skills

Use after merging a branch or completing a task to consolidate learnings into memory layers, close out issues, and verify the phase gate.

Popular code quality & workflow skills

View category →

grill-me

mattpocock/skills

A relentless interview to sharpen a plan or design.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

handoff

mattpocock/skills

Compact the current conversation into a handoff document for another agent to pick up.

domain-modeling

mattpocock/skills

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

codebase-design

mattpocock/skills

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

diagnosing-bugs

mattpocock/skills

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.