attack-path-analysis
Use when Codex is already in the attack-path-analysis phase of a security scan or the user explicitly asks to trace a security…
@cowork-osInstall SkillProductivity
Skill
/code-reviewer
Perform professional code review for local changes or GitHub pull requests.
Claude Code
$ npx -y skills add CoWork-OS/CoWork-OS --skill code-reviewer --agent claude-code
Codex
$ npx skills add CoWork-OS/CoWork-OS --skill code-reviewer -a codex -y
Cursor
$ npx skills add CoWork-OS/CoWork-OS --skill code-reviewer -a cursor -y
Gemini CLI
$ npx skills add CoWork-OS/CoWork-OS --skill code-reviewer -a gemini-cli -y
GitHub Copilot
$ npx skills add CoWork-OS/CoWork-OS --skill code-reviewer -a github-copilot -y
OpenCode
$ npx skills add CoWork-OS/CoWork-OS --skill code-reviewer -a opencode -y
Windsurf
$ npx skills add CoWork-OS/CoWork-OS --skill code-reviewer -a windsurf -y
SKILL.md
code-reviewer.SKILL.mdname: code-reviewer description: "Perform professional code review for local changes or GitHub pull requests." version: "1.0.0" metadata: author: CoWork OS Contributors <info@coworkosapp.com> source-author: "google-gemini"
code-reviewer
Purpose
Perform professional code review for local changes or GitHub pull requests.
Routing
- Use when: Use for formal, structured review workflows on local diffs or GitHub PRs.
- Do not use when: Don't use for one-off formatting checks without code-quality feedback.
- Outputs: Findings grouped by severity with rationale and approval/revise recommendation.
- Success criteria: Covers correctness, maintainability, performance, security, and testability.
Trigger Examples
Positive
- Use the code-reviewer skill for this request.
- Help me with code-reviewer.
- Use for formal, structured review workflows on local diffs or GitHub PRs.
- code-reviewer: provide an actionable result.
Negative
- Don't use for one-off formatting checks without code-quality feedback.
- Do not use code-reviewer for unrelated requests.
- This request is outside code-reviewer scope.
- This is conceptual discussion only; no tool workflow is needed.
Runtime Prompt
- Current runtime prompt length: 3052 characters.
- Runtime prompt is defined directly in `../code-reviewer.json`.
Stats
542
Stars
100
Forks
Active
Maintenance
TypeScript
Language
MIT
License
Last commit
Created
544157 skills
Stars on GitHub
Momentum
- stars in total
- 544
Other skills on cowork-os.
@cowork-osInstall Skilldeep-security-scan
Use when the user asks for a deep, exhaustive, multi-pass, or variance-reducing repository-wide Codex Security scan. Run repeated…
@cowork-osInstall Skillfinding-discovery
Use when Codex is already in the finding-discovery phase of a security scan or the user explicitly asks to discover candidate…
@cowork-osInstall Skillfix-finding
Use when the user explicitly asks to fix and verify a validated or plausible security finding. Do not use as the primary trigger…
@cowork-osInstall Skillsecurity-diff-scan
Use when the user asks for a security review of a pull request, commit, branch diff, working-tree patch, or other Git-backed…
@cowork-osInstall Skillsecurity-scan
Use when the user asks for a repository-wide or scoped-path security scan.
@cowork-osInstall SkillMore skills from other plugins.
i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress…
@ayghriInstall Skill
distilly
Set up the owner profile so a personal agent knows who it works for (first-run setup, \"get to know me\"), or distill colleague,…
@titanwingsInstall SkillQuestions about code-reviewer.
- Which coding agents can use code-reviewer?
- code-reviewer installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.