claude

security

安全审计:对代码库、API、服务、CLI、库和守护进程做漏洞审查与安全评估,按信任边界给出证据、复现方式、优先级和最小修复(Cloudflare security-audit skill)。

1 on GitHubby hidontknowupdated 3 days ago
/

Plugin security from marketplace agent-kit in hidontknow/agent-kit. Commands read from the repo's manifest — 2 days ago.

What it installs

Skills (1)

  • security-audit
View source on GitHub

More from hidontknow/agent-kit

All 28 plugins →

ecc

claudecodex

ECC(Everything Claude Code,"Agent 运行环境的操作系统"):超大型 Agent 增强套件,71 个子 Agent、300+ skill、98 个命令、规则、可复用的 hooks 和 MCP 约定,覆盖 TDD、代码审查、安全、性能、多语言最佳实践和运维工作流;支持 Claude Code、Codex、Cursor、OpenCode、Kimi 等。

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

1

Scientific Agent Skills(原 Claude Scientific Skills):K-Dense 出的 177 个科研 skill,覆盖生物信息与基因组、化学信息学与药物发现、蛋白质组与质谱、临床研究、医学影像与数字病理、神经科学、材料、物理天文、工程仿真、地理遥感、实验室自动化、数据分析与可视化、科研写作与文献综述等,每个 skill 对应一个科学库、数据库(100 多个)或研究流程。

177 skills

1

Matt Pocock 的工程 skill(27 个):用提问打磨需求(grill-me / grilling)、需求转规格与工单(to-spec、to-tickets)、实现、TDD、诊断 bug、代码审查、PR、领域建模、代码库架构改进、调研、复盘、交接、教学等,小而可组合,适合真实工程而非 vibe coding。

39 skills

1

Addy Osmani 的 Agent Skills:25 个覆盖完整开发流程的工程 skill(想法打磨 → 写规格 → 拆任务 → 增量实现 → 测试调试 → 代码审查 → 上线),包括 spec 驱动开发、TDD、API 设计、前端工程、安全加固、性能优化、可观测性、CI/CD、文档与 ADR、弃用迁移、上下文工程、git 工作流等;另有 9 个斜杠命令(/spec、/plan、/build、/test、/constraints、/review、/webperf、/code-simplify、/ship)和 4 个审查子 Agent。

25 skills · 4 agents

1

caveman

claude

Caveman:让 AI 编码 Agent 少说、少读、少花钱。回答压缩成「原始人」短句(代码、命令、报错原样保留);日志、JSON、CSV、测试输出在模型读到前先压缩;Auto 按问题难度选模型和推理强度;Blocks 复用 Agent 写过的脚本;另有网页压缩、记忆文件压缩、token 用量分析。一条命令接入 Claude Code、Codex、Gemini CLI、OpenCode 等 30 多个 Agent。

22 skills · 1 command · 3 agents

1

Emil Kowalski 的设计工程 skill(18 个):动画从零构建、手势交互、编排、性能、审查与精简,Apple 设计原则,移动端原生体验,破坏性测试 UI,多版本原型,UI 库选择,Sonner,现代 Swift。

18 skills

1

Similar plugins

ecc

claudecodex

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

affaan-m/ECC 302,088

Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.

hooks

anthropics/claude-code 155,476

Design fluency for frontend development. 1 skill with 24 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.

1 skill · 4 agents · hooks

pbakaus/impeccable 109,099

Cross-installation agent federation with zero-trust security, PII-gated data flow, and compliance-grade audit trails

3 skills · 1 command · 1 agent

ruvnet/ruflo 81,589

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

Maintain security?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins28 plugins