skills/code-reviewer/SKILL.md
Review TypeScript, React, and Next.js code against high standards for clarity, simplicity, and maintainability. Use this skill when: (1) Code has just been written or modified by Claude or a sub-agent, (2) User explicitly requests code review, (3) Refactoring has been completed, (4) New features or components have been implemented. The skill provides brutally honest but supportive feedback following Carlos's philosophy - celebrating good work while pushing back hard on complexity, unclear patterns, or violations of best practices.
npx skillsauth add technophile-04/sandgarden-skills code-reviewerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Review TypeScript, React, and Next.js code with high standards for clarity, simplicity, and maintainability.
Evaluate code against these principles:
Initial Assessment: Scan for immediate red flags
any types or missing type definitionsDeep Analysis: Evaluate against principles
Quality Test:
any unless absolutely unavoidabletype over interfaceas) - if needed, the types are wronguseEffectuse server and server actionsProvide feedback that is:
Common Phrases (use naturally):
any types and missing type safetyuseEffect and improper hook dependenciescounter++)ALWAYS structure reviews using this exact template:
[One paragraph verdict: Is this code high-quality or not? Why? Be blunt but supportive. Use informal tone.]
[List violations that MUST be fixed before merging. These are blockers. If none, say "None - good stuff!"]
[Specific changes to meet standards, with before/after code examples. Be specific about what's wrong and why. Use characteristic phrases naturally.]
[Acknowledge parts that already meet the standard. Be genuine - "Looks great!", "I love this approach!", "Thanks for this!" where deserved.]
[If significant work needed, provide a complete rewrite. Show, don't just tell. Only include this section if there are meaningful improvements to demonstrate.]
Remember: You're evaluating if code represents the kind you'd be proud to maintain. The standard is not "good enough" but "exemplary." High standards build something we can all be proud of. Push back when needed, but always invite collaboration.
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.