원클릭으로
subagent-review
Keep reviews light by running quick spec and quality checks after each task before claiming completion.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Keep reviews light by running quick spec and quality checks after each task before claiming completion.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Load BEFORE writing or changing code on Jess hot paths (core tree/eval/render, grammar/parser, extend/selector algorithms). Packages the 9 V8-architecture invariants as pre-write checks and points at the canonical checklist.
Use when working with fixture-based or expected-output tests (especially Less test-data). Helps isolate one fixture, reproduce deterministically, update expectations safely, and avoid cross-package build pitfalls.
Use when changing exports, entrypoints, or shared types across packages. Ensures public API stability, correct ESM/CJS surface, and cross-package build/test validation.
Use when changing perf-sensitive codepaths (parsing, selector/extend algorithms). Provides a lightweight sanity protocol and avoids ungrounded perf claims.
Use a strict observe-hypothesize-trace-verify-fix loop when debugging; avoid random changes and context loss. Use when the user is debugging, investigating a failure, or fixing a bug.
Run and read the verification command every time before claiming success. Use when you are about to report a fix, tests/builds passing, or task completion.
| name | subagent-review |
| description | Keep reviews light by running quick spec and quality checks after each task before claiming completion. |
Use this skill when you’re wrapping up a discrete task (bug fix, feature, doc cleanup). It does not spawn subagents, but it reminds you to run the minimal spec and quality verifications that an independent reviewer would otherwise do.
superpowers/subagent-driven-development without spinning up parallel agents.git status, lint, or formatting checks relevant to the touched files. Scan the diff for clarity, remove boilerplate comments, and double-check there are no stray console.log calls or .only.pnpm test -- --run ... (0 failures), git status -sb (clean)). Mention both the spec check and quality scan before claiming completion.git status / diff review because “I remember it was clean.”systematic-debugging (if applicable) and verification-before-completion.git status -sb + lint (per .cursor/rules/30-tests.mdc).