Find the best CLAUDE.md, AGENTS.md and Claude skills

yaklangAGENTS.md

yakit

yaklang/yakit/AGENTS.md

本文件为所有 AI Agent（及新开发者）提供项目启动所需的背景知识。 阅读本文件后，你应能独立完成依赖安装与本地开发环境的启动。 Yakit 是一个基于 Electron + React 的跨平台桌面应用，主要技术栈包括 Electron、React、TypeScript 等。项目通过 Vite 构建渲染端，使用 Yarn 作为包管理器。 主进程在开发模式下会分别加载： - 主窗口：http://127.0.0.1:3000（app/main/index.js:247） - 引擎链接窗口：http://127.0.0.1:5173（app/main/index.js:143） 因此*两个渲染端都必须成功启动后，才能启动 Electron 主进程*，否则窗口会白屏。 项目共有三个需要安装依赖的子项目。一条命令即可按顺序全部安装（根目录 → Link 渲染端 → 主渲染端）：

No other project uses it yet

yaklangReads credentialsSkill

code-review

yaklang/yakit/.agents/skills/code-review/SKILL.md

对 Yakit 仓库的代码改动做规范化 code review：按代码逻辑、TS 定义、UI 引用与 Props、CSS 样式、依赖版本、配置项六个维度审查，检查测试用例缺失，强制执行 tsc 类型检查与 vitest 测试验证，输出「结果汇总 / 明细解释 / 合并结论」三块报告，经用户确认后写入文件。当用户要求 review、审查、评审代码改动，或在提交、合并、提 PR 前先检查代码时触发。审查对象可以是 PR 编号、分支 diff（含当前分支相对基线的改动）或工作区未提交改动。

Often used withclose-spec·add-new-model·compare-screenshots

yaklangSkill

commit-msg

yaklang/yakit/.agents/skills/commit-msg/SKILL.md

为 Yakit 仓库完成一次本地提交：确定提交范围（暂存区优先，空则弹框确认）、基于 diff 按改动类型归纳中文 message（每种类型一行）、commit 前弹窗确认、执行 git commit（不推送）。只要 message 时仅输出文本。用户说「提交」「commit 代码」或输入 /commit-msg，或被 create-pr 等 skill 调用时使用。

yaklangSkill

create-pr

yaklang/yakit/.agents/skills/create-pr/SKILL.md

为 Yakit 仓库一站式完成提 PR 流程：提交工作区改动、调用 code-review skill 评审、推送远端后在 yaklang/yakit 创建或更新 PR。当用户要求提 PR、提交 PR、创建 PR、发 PR、raise/submit/open PR、"create PR"、更新已有 PR，或使用 /create-pr 时触发。

Often used withupdate-pr

yaklangReads credentialsSkill

react-bits-pro

yaklang/yakit/.agents/skills/react-bits-pro/SKILL.md

Install and integrate React Bits Pro components, marketing blocks, App UI blocks, Agent Kit skills and landing-page templates into React/Next.js apps via the shadcn registry CLI with license-key auth. Use whenever the user wants animated components (WebGL/shader backgrounds, GSAP and Motion animation, 3D, cursor trails, text effects, cards, carousels, galleries), marketing sections (hero, features, pricing, navigation, footer, FAQ, CTA, auth, stats, blog, contact, social proof, about, waitlist, showcase, how-it-works, download, ecommerce, bento grids and Bento Builder), app interface blocks (app shells, sidebars, dashboards, data tables, analytics, command menus, settings, dialogs, kanban, billing, onboarding) or AI/agent surfaces (chat, prompt inputs, tool calls, agent plans, approvals, usage), landing-page templates, or Agent Kit design skills, page prompts and recipes. Also use when integrating these into an existing page or design system, or on "react bits", "reactbits", "@reactbits-starter", "@reactbits-pro", "app ui" or "agent kit".

yaklangCopilot instructions

yakit

yaklang/yakit/.github/copilot-instructions.md

All generated code must follow the rules defined in .editorconfig and .prettierrc.js. Key rules to apply when writing code:

No other project uses it yet

yaklangSkill

401-403-bypass-techniques

yaklang/hack-skills/skills/401-403-bypass-techniques/SKILL.md

401/403 bypass playbook. Use when encountering access-denied responses on admin panels, API endpoints, or restricted paths. Covers path manipulation, HTTP method tampering, header injection, protocol downgrade, and automated bypass tools.

yaklangSkill

active-directory-acl-abuse

yaklang/hack-skills/skills/active-directory-acl-abuse/SKILL.md

Active Directory ACL abuse playbook. Use when exploiting misconfigured AD permissions including GenericAll, WriteDACL, DCSync rights, shadow credentials, LAPS reading, GPO abuse, and BloodHound-guided attack paths.

yaklangSkill

active-directory-certificate-services

yaklang/hack-skills/skills/active-directory-certificate-services/SKILL.md

AD Certificate Services attack playbook. Use when targeting misconfigured AD CS for privilege escalation via ESC1-ESC13 template abuse, NTLM relay to enrollment, CA officer abuse, and certificate-based persistence.

yaklangSkill

active-directory-kerberos-attacks

yaklang/hack-skills/skills/active-directory-kerberos-attacks/SKILL.md

Kerberos attack playbook for Active Directory. Use when targeting AD authentication via AS-REP roasting, Kerberoasting, golden/silver/diamond tickets, delegation abuse, or pass-the-ticket attacks.

yaklangPipes a download into a shellSkill

ai-ml-security

yaklang/hack-skills/skills/ai-ml-security/SKILL.md

AI/ML security playbook. Use when assessing model supply chain attacks (pickle RCE, poisoned weights), adversarial examples, model poisoning, model stealing, data privacy attacks (membership inference, model inversion), and autonomous agent security risks.

yaklangSkill

android-pentesting-tricks

yaklang/hack-skills/skills/android-pentesting-tricks/SKILL.md

Android pentesting playbook. Use when testing Android applications for SSL pinning bypass, exported component abuse, WebView vulnerabilities, intent redirection, root detection bypass, tapjacking, and backup extraction during authorized mobile security assessments.

yaklangSkill

anti-debugging-techniques

yaklang/hack-skills/skills/anti-debugging-techniques/SKILL.md

Anti-debugging detection and bypass playbook. Use when reversing protected binaries that detect debuggers via ptrace, PEB flags, timing checks, or signal/exception handlers on Linux and Windows.

yaklangSkill

api-auth-and-jwt-abuse

yaklang/hack-skills/skills/api-auth-and-jwt-abuse/SKILL.md

API authentication and JWT abuse playbook. Use when testing bearer tokens, API keys, claim trust, header spoofing, rate limits, and API auth boundary weaknesses.

yaklangSkill

api-authorization-and-bola

yaklang/hack-skills/skills/api-authorization-and-bola/SKILL.md

API authorization and BOLA testing playbook. Use when APIs expose object identifiers, nested resources, hidden writable fields, or weak function-level authorization.

yaklangSkill

api-recon-and-docs

yaklang/hack-skills/skills/api-recon-and-docs/SKILL.md

API reconnaissance and documentation review playbook. Use when discovering endpoints, schemas, versions, OpenAPI specs, hidden docs, and surface area for API testing.

yaklangSkill

api-sec

yaklang/hack-skills/skills/api-sec/SKILL.md

Entry P1 category router for API security. Use when choosing between API recon, authorization, token abuse, and hidden-parameter workflows before any deeper API topic skill.

yaklangSkill

arbitrary-write-to-rce

yaklang/hack-skills/skills/arbitrary-write-to-rce/SKILL.md

Arbitrary write to RCE playbook. Use when you have an arbitrary write primitive (from heap exploitation, format string, or OOB write) and need to convert it into code execution by targeting GOT, hooks, _IO_FILE vtable, exit_funcs, TLS_dtor_list, modprobe_path, .fini_array, or C++ vtables.

yaklangSkill

attack-surface-mapping

yaklang/hack-skills/skills/attack-surface-mapping/SKILL.md

Draw a testable attack surface from one authorized target URL or one application. Use when the user says 攻击面, 供给面, 画攻击面, map the surface, application recon, find the business host, JS inventory, or when the only visible page is login. Derive hosts, APIs, keys, and the object graph from what the app already exposes. Do not open with directory brute or payload spray. Use when the user runs /attack-surface-mapping.

yaklangSkill

authbypass-authentication-flaws

yaklang/hack-skills/skills/authbypass-authentication-flaws/SKILL.md

Authentication bypass testing playbook. Use when assessing login flows, password reset logic, account recovery, MFA bypass, token predictability, brute-force resistance, and session boundary flaws.