omc-review — Claude Code skill: review code before release
omc-review is a Claude Code skill that checks finished code for defects, risks, and bloat before release. It ranks issues by severity without making fixes.
MIT 309 installs ★ 40,997 updated 2026-11-03
npx skills add Yeachan-Heo/oh-my-claudecode --skill omc-review -a claude-codeWhat omc-review does
The skill runs two parallel passes: the standards axis reads the diff against the repo's documented rules (CLAUDE.md, CONTRIBUTING.md, docs/standards/ directories), the intent axis validates the code against task or ticket acceptance criteria. Results stay separate: a change can pass one and fail the other. Within each axis the skill checks correctness (edge cases, error paths, concurrency), risk (security boundaries, destructive operations, data integrity), reuse (existing utilities the change should have used) and test coverage.
When quality gates are configured for the omc-review stage, the skill calls omc quality-gates list --stage omc-review --json and spawns a separate Task for each gate, which loads the named skill and returns VERDICT: PASS or VERDICT: BLOCK. A blocking gate with a BLOCK verdict halts the release; advisory gates inform without blocking. The skill does not impose gates where none exist: without entries in qualityGates["omc-review"] the Quality Gates section is omitted.
Output is a list of findings from critical to minor with file, line and failure scenario; what was checked and clean; what could not be assessed. The reviewer runs in a separate lane from the author.
What it helps with
- spot logic bugs and uncovered edge cases before merging
- rank problems by severity: defects, risks, simplification
- validate diff against both repo standards and task requirements in two passes
- run quality gates to block release on critical findings
- surface untested behavior and destructive operations
Example prompts for the agent
- Review the last commit for correctness and risks before merging
- Run review on changes in
src/auth/— need to find security issues and logic bugs - Launch
omc-reviewfor diff of current branch againstmain, show findings by severity
How to install omc-review
1Skills CLI (Vercel)
npx skills add Yeachan-Heo/oh-my-claudecode --skill omc-review -a claude-code2Manually: put the files in place
~/.claude/skills/review/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/review/
1Skills CLI (Vercel)
npx skills add Yeachan-Heo/oh-my-claudecode --skill omc-review -a codex2Manually: put the files in place
.agents/skills/review/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Yeachan-Heo/oh-my-claudecode --skill omc-review -a cursor2Manually: put the files in place
.cursor/skills/review/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Yeachan-Heo/oh-my-claudecode skills/review2Manually: put the files in place
.github/skills/review/SKILL.md1Skills CLI (Vercel)
npx skills add Yeachan-Heo/oh-my-claudecode --skill omc-review -a gemini-cli2Platform CLI
gemini skills install https://github.com/Yeachan-Heo/oh-my-claudecode --path skills/reviewManually: put the files in place
.devin/skills/review/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add Yeachan-Heo/oh-my-claudecode --skill omc-review -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about omc-review
How to install omc-review in Claude Code?
Run npx skills add Yeachan-Heo/oh-my-claudecode --skill omc-review -a claude-code, then npx skills add Yeachan-Heo/oh-my-claudecode --skill review -a claude-code. The skill will land in ~/.claude/skills/review/SKILL.md.
What does omc-review do?
It evaluates finished code for logic defects, security risks and bloat. Runs two passes: one validates the diff against repo standards, the other against task requirements. Ranks findings by severity, does not author fixes.
What are quality gates in omc-review?
When quality gates are configured for the omc-review stage, the skill spawns separate tasks for each gate, which return PASS or BLOCK. A blocking gate with BLOCK verdict halts the release; advisory gates inform without blocking.
Source text
SKILL.md · MIT
---
name: omc-review
description: Evaluate finished work for defects, risk, and simplification before it ships
---
# Review
Use this skill to evaluate work that already exists. Review never authors the
change it is judging.
This is the canonical review workflow. `ai-slop-cleaner` is an opt-in lane
within it.
## Goal
Find what is actually wrong, ranked by severity, with enough detail to act on.
## Workflow
1. Establish what changed and what it was meant to do.
2. Read the change against that intent.
3. Check correctness first, then risk, then simplification.
4. Verify each candidate finding before reporting it.
5. Report findings most-severe first.
## What to check
- **Correctness** — logic defects, edge cases, error paths, concurrency
- **Risk** — security boundaries, destructive operations, data integrity
- **Reuse** — existing utilities or patterns the change should have used
- **Simplification** — code that could be deleted or collapsed
- **Coverage** — behavior that ships untested
## Two axes, run apart
A substantial diff is reviewed as two parallel sub-agent passes, reported separately — never merged or cross-ranked, because a change can pass one axis and fail the other (standards-conforming but wrong behavior; faithful but convention-breaking):
- **Standards axis** — the diff against the repo's documented standards plus a judgement-call-only smell baseline; anything tooling already enforces is skipped. The standards set is discovered, not assumed: search the repo for standards documents (CLAUDE.md/AGENTS.md, `docs/standards/` volumes, `CONTRIBUTING.md`, `CODING_STANDARDS.md` or equivalents) and review against whatever exists — a standards file you didn't look for is a standard you didn't apply.
- **Intent axis** — the diff against what the work was meant to do — the task, spec, or ticket acceptance criteria: requirements missing or partial, behavior nobody asked for, each finding quoting its source line.
Keep each sub-agent brief under ~400 words and pointed at one axis. Aggregate without picking a single winner across axes — that reranking is what the separation exists to prevent; state each axis's verdict on its own. A small diff stays one pass.
## Rules
- Separate lanes: the reviewer must not be the author's same active context.
- Verify before reporting. A plausible-sounding finding that does not reproduce is noise.
- State severity honestly; do not pad the list to look thorough.
- "No findings" is a valid result when the work is sound.
- Advisory by default — review informs, it does not gate. Hard gates (release,
security, destructive operations) stay separate and fail closed.
## Output
- Findings, most-severe first, each with file, line, and concrete failure scenario
- What was checked and found clean
- Anything that could not be assessed
## Quality Gates
Before finalizing the review, check the existing merged OMC `qualityGates["omc-review"]` entries (project stage entries replace the user list; see `docs/quality-gates-configuration.md`). If there are no entries, do not call `omc quality-gates list`, spawn gate tasks, or add a Quality Gates section or gate records to the review output. If there is at least one entry, call `omc quality-gates list --stage omc-review --json` and show every validation error. For each available gate, spawn one independent Claude Code `Task` that loads the named skill from `resolvedPath`, reviews the same changes, and returns `VERDICT: PASS` or `VERDICT: BLOCK` plus findings. Use the configured model override when present; do not pass another reviewer's output to the gate. Reuse the same gate lane if the change is revised and reviewed again.
When gates are configured, record `{ gate, mode, verdict }` for each gate in a Quality Gates section of the review output. Unresolved skills are `gate_unavailable` with a visible warning, never PASS; they do not fail the review stage. A blocking `BLOCK` makes the overall result `REQUEST CHANGES`; advisory results are informational and never block.
© Yeachan-Heo · MIT · Yeachan-Heo/oh-my-claudecode