一键在 Manus 中运行任何 Skill

开始使用

subagent-review

星标28

分支1

更新时间2026年7月12日 00:16

Keep reviews light by running quick spec and quality checks after each task before claiming completion.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

jesscss

jesscss/jess

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

Subagent Review Checklist

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.

When to apply

You’ve just finished coding/testing a change and are about to say “this task is done” or “tests/build pass.”
You want to mimic the two-stage review (spec + quality) described by superpowers/subagent-driven-development without spinning up parallel agents.

Mini two-stage review

Spec sanity check – Re-read the requirements/plan for this task. Ask: “Does the behavior still match the plan?” Run or re-run the focused test, reproduce the edge case, or verify the command that proves the spec.
Quality check – Run 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.
Document review outcome – Record the commands run and their pass/fail status (e.g., pnpm test -- --run ... (0 failures), git status -sb (clean)). Mention both the spec check and quality scan before claiming completion.

Anti-patterns

Skipping git status / diff review because “I remember it was clean.”
Claiming success without explicitly noting both a spec-focused check and a quick quality check.
Relying on mental review alone—write down the commands you ran so you can cite them later.

Project context

Use the skill in tandem with systematic-debugging (if applicable) and verification-before-completion.
The “spec check” command is often the focused Vitest suite for extend/core tasks; quality check is usually git status -sb + lint (per .cursor/rules/30-tests.mdc).

同仓库更多 Skills

同仓库

perf-architecture

jesscss/jess

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.

2026-07-2328

fixture-driven-dev

jesscss/jess

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.

2026-07-2228

api-surface-safety

jesscss/jess

Use when changing exports, entrypoints, or shared types across packages. Ensures public API stability, correct ESM/CJS surface, and cross-package build/test validation.

2026-07-1228

perf-sanity

jesscss/jess

Use when changing perf-sensitive codepaths (parsing, selector/extend algorithms). Provides a lightweight sanity protocol and avoids ungrounded perf claims.

2026-07-1228

systematic-debugging

jesscss/jess

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.

2026-07-1228

verification-before-completion

jesscss/jess

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.

2026-07-1228

name	subagent-review
description	Keep reviews light by running quick spec and quality checks after each task before claiming completion.

Subagent Review Checklist

When to apply

You’ve just finished coding/testing a change and are about to say “this task is done” or “tests/build pass.”
You want to mimic the two-stage review (spec + quality) described by superpowers/subagent-driven-development without spinning up parallel agents.

Mini two-stage review

Spec sanity check – Re-read the requirements/plan for this task. Ask: “Does the behavior still match the plan?” Run or re-run the focused test, reproduce the edge case, or verify the command that proves the spec.
Quality check – Run 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.
Document review outcome – Record the commands run and their pass/fail status (e.g., pnpm test -- --run ... (0 failures), git status -sb (clean)). Mention both the spec check and quality scan before claiming completion.

Anti-patterns

Skipping git status / diff review because “I remember it was clean.”
Claiming success without explicitly noting both a spec-focused check and a quick quality check.
Relying on mental review alone—write down the commands you ran so you can cite them later.

Project context

Use the skill in tandem with systematic-debugging (if applicable) and verification-before-completion.
The “spec check” command is often the focused Vitest suite for extend/core tasks; quality check is usually git status -sb + lint (per .cursor/rules/30-tests.mdc).