Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Requesting Code Review

ASecurity

Harness 代码审查:WU 轻量审查与 GROUP 尾盘集体审查。完成实现、批次收尾、合并前使用。触发:review、审查、code-review、集体审查。

3 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentscode-reviewgit

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add wrysmil/Code-Harness-Kit --skill requesting-code-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Requesting Code Review?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Requesting Code Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/wrysmil-requesting-code-review/badge)](https://www.skillsdirectory.com/skills/wrysmil-requesting-code-review)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: requesting-code-review
description: Harness 代码审查:WU 轻量审查与 GROUP 尾盘集体审查。完成实现、批次收尾、合并前使用。触发:review、审查、code-review、集体审查。
---

# Requesting Code Review(Harness)

**Core principle:** Review early, review often — **Harness 下必须用独立 `reviewer` 实例,禁止裸 `generalPurpose`。**

## 两层审查(必辨)

| 层 | 谁发起 | 机制 | 落盘 |
| --- | --- | --- | --- |
| **WU 轻量审查** | Coder(WU 内) | 独立 `reviewer` 实例 | **不落盘**;返回 `code_review: PASS\|BLOCK` |
| **GROUP 集体审查** | Leader(尾盘 B) | 独立 `reviewer`;须先 collective-test PASS | Leader Write `reviews/*-code-review.md` |

**顺序(尾盘):** collective-test → 本 skill → code-review 产物。细则:batch-closeout spec §4。

## 委派协议

1. 声明 `Skills: requesting-code-review@<path> loaded`
2. Load 本 skill
3. 委派 **独立 `reviewer` 实例**(与所有 Coder/Implementer **不同实例**;readonly)
4. Prompt 正文:`.agents/agents/reviewer.md`;占位符见 `code-reviewer.md`
5. **Leader** 将集体审查返回 Write `artifact-templates/code-review.md` 路径;Reviewer **不** Write 文件

**平台绑定:** 见 `platform/*/bindings.md`(SpawnWorker(reviewer))。

**范围证据:** 优先 **文件列表 + diff 摘要**;worktree 批次可用 `{BASE_SHA}`/`{HEAD_SHA}`,非必须。

## 何时必须

- GROUP 尾盘(Tier 2+ 批次交付)
- WU 内 Coder 闭环(`coder.md` § 轻量审查)
- 合并 main 前(Leader 组织)

## 禁止

- 实现与审查同一 subagent 实例
- 无 `reviewer` 约束的 Task
- 跳过 collective-test 直接集体审查
- Reviewer 会话内 Write `.ai-runtime-artifacts/`
- 仅以 Coder `code_review: PASS` 替代尾盘集体审查

## 反馈处理

- Critical → 立即修;Important → 继续前修;Minor → 记录
- 有依据时可 push back

## Superpowers 原版(非 Harness 项目)

无 Harness Kit 时,可用 Task `general-purpose` + git SHA + `code-reviewer.md` 模板(见 skill 副本 `_vendor` 说明)。**本项目忽略该路径。**

Attribution

wrysmilwrysmil
View sourceMore from wrysmil →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →