跳到主内容
智客 ZICQ

技能库 智客分类:安全测试 review

Review

所有申请审查的审查指挥员和单一切入点。 调整需要审查的内容,然后运行正确的领域:安全(OWASP、认证、头条、供应链)、隐私(PII、跟踪、同意、GDPR/CCPA)、合规(HIPAA、SOC 2、PCI-DSS、GDPR)、设计(响应、可访问性、打字、i18n)、复原力(error处理、退化、API合同)、性能(Core Web Vitals、捆绑、运行时间)、SEO(Meta、结构数据、可爬行性)和GEO(AI引用准备、llms.txt、实体清晰度)。 用于发射前准备,事故后规划, 或任何“为X请求审查我的应用程序”.

596 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

所有申请审查的审查指挥员和单一切入点。 调整需要审查的内容,然后运行正确的领域:安全(OWASP、认证、头条、供应链)、隐私(PII、跟踪、同意、GDPR/CCPA)、合规(HIPAA、SOC 2、PCI-DSS、GDPR)、设计(响应、可访问性、打字、i18n)、复原力(error处理、退化、API合同)、性能(Core Web Vitals、捆绑、运行时间)、SEO(Meta、结构数据、可爬行性)和GEO(AI引用准备、llms.txt、实体清晰度)。 用于发射前准备,事故后规划, 或任何“为X请求审查我的应用程序”.

何时用

- 用户想要审查,但不确定是哪种

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 Orchestrator、When to use、Modes、Domains、Steps、1. Gather context。 其中含规范建议的小节:分步指令。

文件分析

文件分析:除 SKILL.md 外,正文引用了 references/security.md、references/privacy.md、references/compliance.md、references/design.md、references/resilience.md、references/performance.md,属于带资源的技能包,这些文件按需再读。

官方 description(原文)

Review orchestrator and single entry point for all application reviews. Triage what needs reviewing, then run the right domains: security (OWASP, auth, headers, supply chain), privacy (PII, tracking, consent, GDPR/CCPA), compliance (HIPAA, SOC 2, PCI-DSS, GDPR), design (responsive, accessibility, typography, i18n), resilience (error handling, degradation, API contracts), performance (Core Web Vitals, bundles, runtime), SEO (meta, structured data, crawlability), and GEO (AI citation readiness, llms.txt, entity clarity). Use for pre-launch readiness, post-incident planning, or any 'review my app for X' request.

Review OrchestratorWhen to useModesDomainsSteps1. Gather context2. Ask targeted questions (max 4)3. Generate review plan4. Execute5. Unified reportTips

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
review
description
Review orchestrator and single entry point for all application reviews. Triage what needs reviewing, then run the right domains: security (OWASP, auth, headers, supply chain), privacy (PII, tracking, consent, GDPR/CCPA), compliance (HIPAA, SOC 2, PCI-DSS, GDPR), design (responsive, accessibility, typography, i18n), resilience (error handling, degradation, API contracts), performance (Core Web Vitals, bundles, runtime), SEO (meta, structured data, crawlability), and GEO (AI citation readiness, llms.txt, entity clarity). Use for pre-launch readiness, post-incident planning, or any 'review my app for X' request.
  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。
指令中引用的文件 · 9
  • references/security.md
  • references/privacy.md
  • references/compliance.md
  • references/design.md
  • references/resilience.md
  • references/performance.md
  • references/seo.md
  • references/geo.md
  • references/report-format.md

以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。

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。

该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。

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」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-db95a9ca7b280800-%E5%AE%A1%E6%9F%A5.html
请存为 .cursor/skills/review/SKILL.md 或 .claude/skills/review/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/shiplightai/agent-skills 取完整目录,不要只建一个 SKILL.md。

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/shiplightai/agent-skills' --list

npx skills add 'https://github.com/shiplightai/agent-skills' --skill 'review'

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 description: "Review orchestrator and single entry point for all application reviews. Triage what needs reviewing, then run the right domains: security (OWASP, auth, headers, supply chain), privacy (PII, tracking, consent, GDPR/CCPA), compliance (HIPAA, SOC 2, PCI-DSS, GDPR), design (responsive, accessibility, typography, i18n), resilience (error handling, degradation, API contracts), performance (Core Web Vitals, bundles, runtime), SEO (meta, structured data, crawlability), and GEO (AI citation readiness, llms.txt, entity clarity). Use for pre-launch readiness, post-incident planning, or any 'review my app for X' request." --- # Review Orchestrator The single entry point for application reviews. It triages what matters, then runs one or more domain reviews and merges them into a unified report. Each domain lives in `references/.md` and is loaded only when selected. ## When to use - User wants a review but isn't sure which kind - Pre-launch readiness assessment - Post-incident review planning - A targeted request for one domain ("check my app's security", "review SEO") ## Modes - **Triage** (default, `/review`) — ask context questions, recommend a plan, run it. - **Full suite** (`/review --all`) — run every applicable domain. - **Targeted** (`/review `) — jump straight into one domain, skipping triage. E.g. `/review security`, `/review seo`. Accepts an optional depth flag (`--quick` / `--thorough`). ## Domains Each row maps to a reference file. Load the file only when the domain is selected. | Domain | Reference | Run it when… (trigger signals) | |--------|-----------|-------------------------------| | security | `references/security.md` | auth/login changes, sensitive data, OWASP, headers/CORS/CSP, supply chain | | privacy | `references/privacy.md` | collects PII, tracking/analytics, consent banners, GDPR/CCPA | | compliance | `references/compliance.md` | regulated industry, audit prep, HIPAA/SOC 2/PCI-DSS/GDPR, payments or health data | | design | `references/design.md` | UI shipping without a designer, responsive, accessibility, typography, i18n | | resilience | `references/resilience.md` | error handling, network/API failures, empty/edge states, degradation | | performance | `references/performance.md` | slow pages, Core Web Vitals, bundle size, runtime/render perf | | seo | `references/seo.md` | public site, meta tags, structured data, crawlability, sitemaps | | geo | `references/geo.md` | discovered via AI assistants, LLM citation readiness, llms.txt, entity clarity | Shared conventions (phases, scoring, confidence, severity, output paths) live in `references/report-format.md` — every domain follows them. ## Steps ### 1. Gather context - Read the project: tech stack, framework, `package.json`, routes, components. - Check `git diff` for recent changes. - Look for existing reports in `shiplight/reports/`. - Auto-detect compliance markers (HIPAA/PHI, PCI/payment fields, GDPR/cookie consent). If invoked as `/review `, skip to step 4 for that domain. ### 2. Ask targeted questions (max 4) One at a time, with auto-detected defaults: 1. **What type of application?** (SaaS, healthcare, fintech, e-commerce, internal tool, marketing site, API-only) 2. **What triggered this review?** (pre-launch, new feature, dependency update, security incident, audit prep, routine) 3. **Any compliance requirements?** (none, HIPAA, SOC2, PCI-DSS, GDPR, multiple) — auto-detect from codebase 4. **Specific concerns?** (open-ended, optional) ### 3. Generate review plan Categorize each applicable domain as **CRITICAL** (must run), **RECOMMENDED** (meaningful value), or **OPTIONAL** (nice to have), with estimated depth (quick / standard / thorough). **SEO vs GEO prioritization by product type:** | Product type | SEO | GEO | |---|---|---| | Developer tools, API products, SaaS | RECOMMENDED | CRITICAL | | E-commerce, local business, marketplace | CRITICAL | OPTIONAL | | Content/media, documentation, blog | CRITICAL | CRITICAL | | Internal tools | — | — | Present a decision matrix: | Review | Priority | Rationale | Depth | |--------|----------|-----------|-------| | security | CRITICAL | New auth feature + SaaS app | thorough | | privacy | CRITICAL | Handles user PII, GDPR applies | standard | | … | | | | ### 4. Execute Ask: "Run all CRITICAL reviews now? [Y/n] Or pick specific ones." For each selected domain, **read `references/.md` and follow its five phases**, applying `references/report-format.md` for scoring, severity, and output paths. Run domains sequentially; show a brief summary after each before moving on. ### 5. Unified report After the selected domains complete, merge their per-domain reports into one, saved to `shiplight/reports/review-{date}.md`: - Overall readiness score (0–10) and per-domain scores - Top 5 findings across all domains, by severity - Regression test summary (total YAML tests generated, in `shiplight/tests/`) ## Tips - Run `/review` before every major launch. - `/review ` is the fast path when you already know what you need. - Reports accumulate in `shiplight/reports/` — the orchestrator can show trends. - YAML regression tests from reviews accumulate in `shiplight/tests/`.

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 .