- 📁 scripts/
- 📄 SKILL.md
vet
Run vet immediately after ANY logical unit of code changes. Do not batch your changes, do not wait to be asked to run vet, make sure you are proactive.
20 days ago · Uploaded
Detail →
Daily Featured Skills Count
04/16
04/17
04/18
04/19
04/20
04/21
04/22
♾️ Free & Open Source 🛡️ Secure & Worry-Free
Import Skills
- 📁 references/
- 📄 SKILL.md
tracey
Add proper Tracey spec annotations to code, find requirements, and check coverage. Use when working with projects that have Tracey configuration (.config/tracey/config.styx), when adding spec references to code, or when checking requirement coverage.
22 days ago · Uploaded
Detail →
- 📁 ci/
- 📁 core/
- 📁 migration/
- 📄 LICENSE
- 📄 README.md
- 📄 SKILL.md
playwright-skill
Battle-tested Playwright patterns for E2E, API, component, visual, accessibility, and security testing. Covers locators, fixtures, POM, network mocking, auth flows, debugging, CI/CD (GitHub Actions, GitLab, CircleCI, Azure, Jenkins), framework recipes (React, Next.js, Vue, Angular), and migration guides from Cypress/Selenium. TypeScript and JavaScript.
20 days ago · Uploaded
Detail →
- 📁 scripts/
- 📄 pyproject.toml
- 📄 SKILL.md
bilibili-hub
使用 Python + UV 读写哔哩哔哩（B 站）数据的技能，依赖 bilibili-api-python + aiohttp， 通过 browser_use get_cookies 自动获取 Cookie 完成认证，无需手动复制。 支持视频详情/字幕/AI总结/评论、用户主页、搜索、热门/排行榜、关注动态 Feed、 收藏夹、稍后再看、观看历史、互动操作（点赞/投币/三连）、动态发布与删除等。 当用户提到"B站"、"哔哩哔哩"、"bilibili"、"B站视频"、"B站热门"、"bilibili-hub"、 "获取B站数据"、"B站字幕"、"B站评论"、"B站收藏"、"B站动态"， 或任何需要以编程方式读写 B 站内容的场景，必须触发本技能。 --- # bilibili-hub > **改造来源**：[jackwener/bilibili-cli](https://github.com/jackwener/bilibili-cli)（Apache-2.0） > > 本技能在原仓库基础上做了以下简化与改造： > - 移除 `browser-cookie3` / `click` / `rich` / `PyYAML` / `qrcode` 依赖 > - Cookie 认证改为直接传入 `dict` 或从环境变量读取，不做浏览器自动提取 > - 移除 CLI 层（commands/）、QR 登录、formatter 等 > - 保留全部 API 方法，统一封装为同步接口（`asyncio.run`） > - 核心依赖 `bilibili-api-python`（逆向工程 B 站 API 的第三方 SDK） > - 在 Minis 环境中，Cookie 通过 `browser_use get_cookies` 自动获取 --- ## 文件结构 ``` /var/minis/skills/bilibili-hub/ ├── SKILL.md ├── pyproject.toml # bilibili-api-python + aiohttp └── scripts/ ├── __init__.py ├── exceptions.py # 6 种结构化异常 ├── payloads.py # 数据结构规范化（normalize_* 函数） └── client.py # BiliClient 核心类（全部 API 方法） ``` --- ## 认证方式 B 站 Web API 使用三个关键 Cookie： | Cookie | 说明 | |--------|------| | `SESSDATA` | 用户 Session（必填，读操作） | | `bili_jct` | CSRF Token（写操作必填：点赞/投币/发动态等） | | `DedeUserID` | 用户 ID（建议填写） | | `buvid3` | 设备 ID（建议填写，降低风控概率） | ### 方法一：browser_use 自动获取（Minis 环境首选） 1. `browser_use navigate` 打开 `https://www.bilibili.com`，确认已登录 2. `browser_use get_cookies` 获取 Cookie（原始值不出现在对话中） 3. 加载 offload env 文件： ```bash . /var/minis/offloads/env_cookies_www_bilibili_com_xxx.sh export BILI_SESSDATA="$COOKIE_SESSDATA" export BILI_JCT="$COOKIE_BILI_JCT" export BILI_USERID="$COOKIE_DEDEUSERID" export BILI_BUVID3="$COOKIE_BUVID3" ``` > **注意**：`get_cookies` 仅对当前页面域名生效，需先 navigate 到 `https://www.bilibili.com` 再调用。 ### 方法二：手动从浏览器 DevTools 获取 1. 登录 B 站，打开 DevTools → Application → Cookies → `https://www.bilibili.com` 2. 找到 `SESSDATA`、`bili_jct`、`DedeUserID` 的值 3. 存入 Minis 环境变量：`BILI_SESSDATA` / `BILI_JCT` / `BILI_USERID` ### Cookie 传入方式（三种） ```python # 方式一：
18 days ago · Uploaded
Detail →
- 📄 SKILL.md
elixir-expert
Expert in Elixir, Phoenix Framework, and OTP. Specializes in building concurrent, fault-tolerant, and real-time applications using the BEAM. Use when building Elixir applications, working with Phoenix, implementing GenServers, or designing distributed systems on the BEAM.
17 days ago · Uploaded
Detail →
- 📁 cases/
- 📁 examples/
- 📁 references/
- 📄 .gitignore
- 📄 CHANGELOG_v2.9.0.md
- 📄 README.md
hello_js_reverse_skill
Node.js / Python 接口自动化与签名还原工程技能：对自有平台或已授权平台的 Web API 进行签名分析与接口对接， 通过 Camoufox 反检测浏览器动态调试与静态源码分析，定位并还原前端加密/签名逻辑， 使用 Node.js 或 Python 实现算法复现与自动化接口调用。 深度集成 camoufox-reverse MCP v0.8.0（C++ 引擎级指纹伪装，78 个逆向分析工具，域级 Session 档案 + 断言系统）。 擅长 JSVMP 虚拟机保护的双路径攻克：路径 A 算法追踪（Hook / 插桩 / 日志分析 / 源码级插桩四板斧， 通用对RS 5/6、Akamai sensor_data、webmssdk、obfuscator.io）、 路径 B 环境伪装（jsdom/vm 沙箱 + 浏览器环境采集对比 + 全量补丁）。 v2.6.0 新增反爬类型三分法（签名型/行为型/纯混淆）作为顶层决策框架，明确 pre_inject_hooks 与 hook_jsvmp_interpreter(mode="proxy") 对签名型反爬不可用， 引入 mode="transparent" 签名安全备选与 MCP 侧 AST 源码插桩（消除 CDN 依赖）。 v2.9.0 新增域级 Session 档案（跨任务复用反爬判定/指纹基准/Cookie 归因）与断言驱动交付体系， Phase 5 升级为断言驱动结构化交付，新增降级梯度原则防止 AI 过早放弃。
20 days ago · Uploaded
Detail →
- 📁 references/
- 📄 SKILL.md
design-deck
Present visual options for architecture, UI, and code decisions with high-fidelity side-by-side previews. For comparing approaches visually — code diffs, diagrams, UI mockups, images — not for gathering structured input (use interview for that). Supports previewBlocks (code, mermaid, image, html), previewHtml, generate-more loops, and plan/PRD-driven flows.
17 days ago · Uploaded
Detail →
- 📄 SKILL.md
buddy
Show, pet, or manage your coding companion. Use when the user types /buddy or mentions their companion by name.
9 days ago · Uploaded
Detail →
- 📄 SKILL.md
session-query
Query previous pi sessions to retrieve context, decisions, code changes, or other information. Use when you need to look up what happened in a parent session or any other session file.
22 days ago · Uploaded
Detail →
- 📁 api/
- 📁 config/
- 📄 SKILL.md
backend-api
直接调用后端 API，直接控制项目配置、文件管理、知识库、MCP 等核心功能
18 days ago · Uploaded
Detail →
- 📄 SKILL.md
ai-slop-remover
Identifies and removes AI-generated code smells without changing behavior. Targets obvious comments, over-defensive code, spaghetti nesting, and generic naming.
3 days ago · Uploaded
Detail →
- 📄 SKILL.md
prove-feature
Create a temporary real project and prove a prove_it feature works (or doesn't) end-to-end. Builds a disposable git repo, writes a focused config, runs real dispatches through the installed or local prove_it, and produces a human-readable session transcript. Use when you need to prove a feature, reproduce a bug, or validate a fix against a real project — not just unit tests. --- # Prove a feature works (or doesn't) Build a throwaway project and exercise a prove_it feature through the real dispatcher pipeline. The output is a human-readable transcript the user can read to confirm the system works end-to-end. ## What "prove" means — read this first **Proving a feature means watching the feature do its actual job, not just watching the dispatcher accept a config and return a decision.** If the feature is a reviewer that detects dead code, you must: 1. Create a project that **contains dead code** → run the reviewer → see it **catch** the dead code 2. Create a project that **has no dead code** → run the reviewer → see it **pass clean** If the feature is a task that validates API design, you must: 1. Write an API file with **real design violations** → see the task **reject** it 2. Write a clean API file → see the task **approve** it If the feature is a when-condition gate, you must: 1. Run with the condition **unmet** → see the task **get skipped** 2. Run with the condition **met** → see the task **actually execute and produce its real output**
22 days ago · Uploaded
Detail →
Skill File Structure Sample (Reference)
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
SKILL.md Requirements
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Why SkillWink?
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
FAQ
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
1. What are Agent Skills?
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
2. How do Skills work?
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
3. How can I quickly find the right skill?
Use these three together:
- Semantic search: describe your goal in natural language.
- Multi-filtering: category/tag/author/language/license.
- Sort by downloads/likes/comments/updated to find higher-quality skills.
4. Which import methods are supported?
- Upload archive: .zip / .skill (recommended)
- Upload skills folder
- Import from GitHub repository
Note: file size for all methods should be within 10MB.
5. How to use in Claude / Codex?
Typical paths (may vary by local setup):
- Claude Code：~/.claude/skills/
- Codex CLI：~/.codex/skills/
One SKILL.md can usually be reused across tools.
6. Can one skill be shared across tools?
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
7. Are these skills safe to use?
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
8. Why does it not work after import?
Most common reasons:
- Wrong folder path or nested one level too deep
- Invalid/incomplete SKILL.md fields or format
- Dependencies missing (Python/Node/CLI)
- Tool has not reloaded skills yet
9. Does SkillWink include duplicates/low-quality skills?
We try to avoid that. Use ranking + comments to surface better skills:
- Duplicate skills: compare differences (speed/stability/focus)
- Low quality skills: regularly cleaned up