跳到主内容
智客 ZICQ

技能库 智客分类:安全测试 review-swarm

Review Swarm

并行只读多代理审查当前 git diff 或明确文件范围,以发现行为回归,安全或隐私风险,性能或可靠性问题,以及合同或测试覆盖漏洞. 当用户要求审查群,并行审查,diff审查,回归审查,安全审查,或想要高信号问题外加优先的固定路径而不编辑文件时使用.

709 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

平行的只读多代理审查当前 git diff 或明确文件范围,以发现行为回归,安全或隐私风险,性能或可靠性问题,以及合同或测试覆盖漏洞

何时用

用户要求审查群、并行审查、diff审查、回归审查、安全审查,或想要高信号问题加上优先排序的固定路径而不编辑文件

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Review Swarm、Step 1: Determine Scope and Intent、Step 2: Launch Four Read-Only Reviewers in Parallel、Sub-Agent 1: Intent and Regression Review、Sub-Agent 2: Security and Privacy Review、Sub-Agent 3: Performance and Reliability Review。 其中含规范建议的小节:分步指令。

文件分析

文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。

官方 description(原文)

Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test coverage gaps. Use when the user asks for a review swarm, parallel review, diff review, regression review, security review, or wants high-signal issues plus a prioritized fix path without editing files.

Review SwarmStep 1: Determine Scope and IntentStep 2: Launch Four Read-Only Reviewers in ParallelSub-Agent 1: Intent and Regression ReviewSub-Agent 2: Security and Privacy ReviewSub-Agent 3: Performance and Reliability ReviewSub-Agent 4: Contracts and Coverage ReviewStep 3: Aggregate and Filter FindingsStep 4: Order the OutputStep 5: Recommend a Clear Path Forward

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
review-swarm
description
Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test coverage gaps. Use when the user asks for a review swarm, parallel review, diff review, regression review, security review, or wants high-signal issues plus a prioritized fix path without editing files.
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「review-swarm」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-28dd9dd0bbef2130-%E5%AE%A1%E6%9F%A5%E6%B2%BC%E6%B3%BD.html
请存为 .cursor/skills/review-swarm/SKILL.md 或 .claude/skills/review-swarm/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/dimillian/skills' --list

npx skills add 'https://github.com/dimillian/skills' --skill 'review-swarm'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版

name: review-swarm description: "Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test coverage gaps. Use when the user asks for a review swarm, parallel review, diff review, regression review, security review, or wants high-signal issues plus a prioritized fix path without editing files."

Review Swarm

Review a diff with four read-only sub-agents in parallel, then have the main agent filter, order, and summarize only the issues that matter. This skill is review-only: sub-agents do not edit files, and the main agent does not apply fixes as part of this workflow.

Step 1: Determine Scope and Intent

Prefer this scope order:

  1. Files or paths explicitly named by the user
  2. Current git changes
  3. An explicit branch, commit, or PR diff requested by the user
  4. Most recently modified tracked files, only if the user asked for a review and there is no clearer diff

If there is no clear review scope, stop and say so briefly.

When using git changes, choose the smallest correct diff command:

  • unstaged work: git diff
  • staged work: git diff --cached
  • mixed staged and unstaged work: review both
  • explicit branch or commit comparison: use exactly what the user requested

Before launching reviewers, read the closest local instructions and any relevant project docs for the touched area, such as:

  • AGENTS.md
  • repo workflow docs
  • architecture or contract docs for the touched module

Build a short intent packet for the reviewers:

  1. What behavior is meant to change
  2. What behavior should remain unchanged
  3. Any stated or inferred constraints, such as compatibility, rollout, security, or migration expectations

If the user did not state the intent clearly, infer it from the diff and say that the inference may be incomplete.

Step 2: Launch Four Read-Only Reviewers in Parallel

Launch four sub-agents when the scope is large enough for parallel review to help. For a tiny diff or one very small file, it is acceptable to review locally instead.

For every sub-agent:

  • give the same scope and the same intent packet
  • state that the sub-agent is read-only
  • do not let the sub-agent edit files, run apply_patch, stage changes, commit, or perform any other state-mutating action
  • ask for concise findings only
  • ask for: file and line or symbol, issue, why it matters, recommended follow-up, and confidence
  • tell the sub-agent to avoid nits, style preferences, and speculative concerns without concrete impact
  • tell the sub-agent to send findings back to the main agent only

Use these four review roles.

Sub-Agent 1: Intent and Regression Review

Review whether the diff matches the intended behavior change without introducing extra behavior drift.

Check for:

  1. Unintended behavior changes outside the stated scope
  2. Broken edge cases or fallback paths
  3. Contract drift between callers and callees
  4. Missing updates to adjacent flows that should change together

This sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.

Recommended sub-agent role: reviewer

Sub-Agent 2: Security and Privacy Review

Review the diff for security regressions, privacy risks, and trust-boundary mistakes.

Check for:

  1. Missing or weakened authn or authz checks
  2. Unsafe input handling, injection risks, or validation gaps
  3. Secret, token, or sensitive data exposure
  4. Risky defaults, permission expansion, or trust of unverified data

This sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.

Recommended sub-agent role: reviewer

Sub-Agent 3: Performance and Reliability Review

Review the diff for new cost, fragility, or operational risk.

Check for:

  1. Duplicate work, redundant I/O, or unnecessary recomputation
  2. Added work on startup, render, request, or other hot paths
  3. Leaks, missing cleanup, retry storms, or subscription drift
  4. Ordering, race, or failure-handling problems that make the change brittle

This sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.

Recommended sub-agent role: reviewer

Sub-Agent 4: Contracts and Coverage Review

Review the diff for compatibility gaps and missing safety nets.

Check for:

  1. API, schema, type, config, or feature-flag mismatches
  2. Migration or backward-compatibility fallout
  3. Missing or weak tests for the changed behavior
  4. Missing logs, metrics, assertions, or error paths that make regressions harder to detect

This sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.

Recommended sub-agent role: reviewer

Report only issues that materially affect correctness, security, privacy, reliability, compatibility, or confidence in the change. It is better to miss a nit than to bury the user in low-value noise.

Step 3: Aggregate and Filter Findings

The main agent owns synthesis. Treat sub-agent output as raw review input, not final output.

Merge findings across all four reviewers and filter aggressively:

  • drop duplicates
  • drop weak or speculative claims
  • drop issues that conflict with the stated intent
  • drop minor style or readability comments unless they hide a real bug or maintenance risk

Normalize surviving findings into this shape:

  1. File and line or nearest symbol
  2. Category: regression, security, reliability, or contracts
  3. Severity: high, medium, or low
  4. Why it matters
  5. Recommended fix or follow-up
  6. Confidence: high, medium, or low

If a reviewer may be correct but the intent is unclear, turn it into an open question instead of a finding.

Step 4: Order the Output

Present findings in this order:

  1. High-severity, high-confidence issues
  2. Medium-severity issues that are likely worth fixing before merge
  3. Lower-severity issues or follow-ups that can wait

Keep the review concise. Findings should be actionable and evidence-backed.

If there are no material issues, say that directly instead of manufacturing feedback.

Step 5: Recommend a Clear Path Forward

After the findings, give the user a short path forward:

  • what to fix before merge
  • what to improve if time permits
  • what can safely be left alone

When helpful, group the path forward into:

  • fix now
  • fix soon
  • optional follow-up

Do not implement fixes as part of this skill. The output is a read-only review plus a prioritized recommendation.

相关技能

安全测试

Skill Vetter

人工智能特工的安全第一技能审查。 在安装来自 ClawdHub, GitHub 或其他来源的任何技能之前使用 。 检查红旗,许可范围,可疑图案.

安全测试

Moltguard

MoltGuard——由OpenGuardrails担任OpenClaw保安. 安装 MoltGuard 以保护你和你的人类免受迅速注射、数据过滤和恶意命令的影响。 资料来源:https://github.com/openguardrails/openguardrails/tre…

安全测试

Security Auditor

用于审查安全漏洞代码,实施认证流,审计OWASP Top 10,配置CORS/CSP头,处理秘密,输入验证,SQL注射预防,XSS保护,或任何与安全相关的代码审查.

安全测试

Skill Vetter

安装任何AI代理技能前的安全审查协议. 红旗侦取入证盗取,疏通密码,放出. 风险分类:低/中/高/高。 编制结构化审查报告。 不先运行此功能, 绝不安装不信任的技能 .