review-loop
Use only when the user explicitly asks to review and fix in a loop until clean.
Skill by lwlee2608
Chalk Labs
Need help deploying review-loop?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/lwlee2608-review-loop
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/review-loop
What's inside
- Skill name
review-loop- Description
- Use only when the user explicitly asks to review and fix in a loop until clean. Not for plain reviews (use review-code); never invoke proactively.
- License
- MIT
- Instructions
- 21 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Review Loop Review, fix, re-review until a round finds nothing worth fixing. Fixes are new code — they need their own review. ## Rules 1. **Review in a fresh subagent every round.** Invoke `review-code` with `<target> --sub` (default target `diff`). If `review-code` is missing, spawn a subagent to review for correctness, security, resource, and performance defects, rating each finding Yes / Judgment call / No for worth fixing. Never review your own fixes inline. 2. **Pass `--second-opinion` to round 1 only.** Round 1 reviews the full change; later rounds review small fix diffs, where another agent adds cost but little coverage. Its Final Call reads code before any fixes exist, so it does not break rule 1. 3. **Use `diff` from round 2 for every target, including paths.** GitHub does not see unpushed fixes, re-reviewing the whole codebase wastes context, and path-scoped reviews can miss fixes in related files. For `pr <number>`, check out the PR first. 4. **Fix every Yes; fix a Judgment call only if Trivial or Small.** Skip No. When a round has a Final Call, act on it instead: Fix → fix, Optional → fix only if Trivial or Small, Skip → skip. Do not re-fix or re-argue a skipped item when a later round raises it again. 5. **Run the repo's checks after each round's fixes** (`make build` / `make test` / `make lint`, else native commands). Fix breakage before the next review. 6. **Stop when a round has nothing new to fix.** Cap at 5 rounds; round 5 is review-only, even if it finds actionable issues. Do not edit after that review — hand the open findings to the user. If a fixed finding comes back in any round, stop fixing and report the open findings. 7. **Commit each fix unless told otherwise.** `--commit each` (default) — one commit per fixed finding. `--commit end` — one commit after the loop stops. Never push, except under `--merge` (rule 8). On the default branch, branch before the first commit — otherwise `diff` anchors at HEAD and committed fixes drop out of the next review. 8. **With `--merge`, merge only a clean loop.** Merge only if no findings are open and checks pass; otherwise skip it and say why. Push the branch, then merge its PR by reading and following `merge-pr`'s SKILL.md. The Skill tool refuses it because it is user-only; the flag is the user's go-ahead. If the branch has no PR or `merge-pr` is missing, say so and stop. 9. **Report at the end:** rounds run and why it stopped, fixes (`path:line` — what changed), skipped findings with a reason each, open findings, check results, and the merge result under `--merge`.
From lwlee2608/agent-skills, MIT.
More from lwlee2608/agent-skills
- 0.587score
plan-feature
lwlee2608
Use when planning a feature too big to hold in one session.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
gh-create-pr
lwlee2608
Use when creating/raising/opening/submitting a GitHub PR.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
build-feature
lwlee2608
Use when implementing a phased feature plan file.
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
create-skill
lwlee2608
Use when creating a new agent skill.
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
review-code
lwlee2608
Use when asked to review a local diff, a GitHub PR, or a whole codebase.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
merge-pr
lwlee2608
Merge a GitHub PR, close linked issues, and delete the branch.
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
second-opinion
lwlee2608
Use when the user asks for a second-opinion review from another agent (e.g., "get a second opinion", "review with pi", "review using gpt-6-astra"…
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
whoami
lwlee2608
Use when the user asks for the current session's ID (e.g., "/whoami", "what's your session id", "who are you") so another agent session can find or message…
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
retro
lwlee2608
Use when the user asks for a retrospective on an agent session ("/retro", "how did this session go", "what could this session do better"), for the current…
SkillAFreshness: A★ 1Claude Code +9 - 0.547score
generate-media
lwlee2608
Use when generating or editing an image or video with an AI model — ads, mockups, style variations, image-to-video.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
explain-outcome
lwlee2608
Use when reporting a failed command, test, build, or deploy, an investigation into an error or incident, or the result of a multi-step task.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
linear-issues
lwlee2608
Use when reading, searching, creating, updating, or commenting on Linear issues.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 1, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/lwlee2608/agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from lwlee2608
- 0.587score
build-feature
lwlee2608
Use when implementing a phased feature plan file.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
plan-feature
lwlee2608
Use when planning a feature too big to hold in one session.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
gh-create-pr
lwlee2608
Use when creating/raising/opening/submitting a GitHub PR.
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
review-code
lwlee2608
Use when asked to review a local diff, a GitHub PR, or a whole codebase.
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
create-skill
lwlee2608
Use when creating a new agent skill.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
merge-pr
lwlee2608
Merge a GitHub PR, close linked issues, and delete the branch.
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get review-loop running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
review-loop skill. Agent Mart. https://agentmart.dev/skills/lwlee2608-review-loop (last updated 2026-10-24)