Daily Featured Skills Count
4,784 4,818 4,870 4,909 4,940 4,970 4,981
05/01 05/02 05/03 05/04 05/05 05/06 05/07
♾️ Free & Open Source 🛡️ Secure & Worry-Free

Import Skills

Composite Most Downloads Most Likes Most Comments Newest
lydakis lydakis
from GitHub Tools & Productivity
  • 📄 SKILL.md
backend mcp composition

mcpx

Use this skill when interacting with MCP servers via CLI. Prefer mcpx over direct MCP SDK/protocol calls for tool discovery, schema inspection, invocation, and Unix-style output composition.

⬇0 ❤43 1 month ago · Uploaded Detail →
686f6c61 686f6c61
from GitHub Development & Coding
  • 📄 SKILL.md
elegir comparar tecnolog

choose-stack

Usar para evaluar y elegir tecnologías con matriz de decisión ponderada. Activar cuando el usuario quiera elegir tecnología, comparar frameworks, decidir entre alternativas técnicas, construir una matriz de decisión, evaluar stack, seleccionar base de datos, elegir lenguaje o comparar herramientas.

⬇0 ❤43 1 month ago · Uploaded Detail →
LukasNiessen LukasNiessen
from GitHub Data & AI
  • 📁 .claude-plugin/
  • 📁 .github/
  • 📁 docs/
  • 📄 .gitignore
  • 📄 CHANGELOG.md
  • 📄 CODE_OF_CONDUCT.md
devops hallucinations refactoring

kubernetes-skill

Prevent Kubernetes hallucinations by diagnosing and fixing failure modes: insecure workload defaults, resource starvation, network exposure, privilege sprawl, fragile rollouts, and API drift. Use when generating, reviewing, refactoring, or migrating manifests, Helm charts, Kustomize overlays, and cluster policies.

⬇0 ❤21 4 days ago · Uploaded Detail →
akseolabs-seo akseolabs-seo
from GitHub Development & Coding
  • 📁 adapters/
  • 📁 evals/
  • 📁 references/
  • 📄 .gitignore
  • 📄 CHANGELOG.md
  • 📄 README.en.md
seo audit google

seo-coach

SEO 陪跑教練技能 — 用蘇格拉底式對話引導用戶自己做 SEO Audit、學 SEO 概念、發現網站問題。 立即啟動這個 skill，當用戶： - 提到 "SEO陪跑"、"SEO coach"、"學SEO"、"SEO陪學"、"SEO audit 陪跑"、"SEO怎麼看" - 給你一個網址，想知道 SEO 問題或如何改善排名 - 說「我的網站流量掉了」、「我的網站排名下降了」、「我想開始做 SEO」 - 問「怎麼檢查 SEO」、「幫我做 SEO audit」、「網站 SEO 有沒有問題」 - 提到 Google Search Console、robots.txt、sitemap、title tag、meta description、反向連結、Core Web Vitals 等 SEO 術語並想要學習或檢查 - 想了解 Google Analytics 4 數據怎麼看 涵蓋 18 個 audit 模組（5 層架構）與多個補充主題：技術基礎、內容品質、連結生態、進階機會、情境防護，以及 GA4、Topical Map、AI 搜尋準備度、SERP Features、電商 SEO、負面 SEO、SEO 迷思等。Local / Google 地圖只作為低比重例外支援，不是主服務。 這個 skill 的核心是教練體驗，不是給報告——Claude 問問題讓用戶自己發現問題，而不是直接列清單。即使用戶只說「看看我的 SEO」，也要啟動這個 skill，因為陪跑式對話比直接給答案更有學習效果。 不要啟動這個 skill，當用戶： - 要的是一份完整 SEO audit 報告 / 健康分數 / 251 條規則檢查 → 改用 seo-audit-skill - 要寫一篇 SEO 文章、改寫文章、發文到 CMS → 改用 seo-content-pipeline - 要建一個新的 PBN 站、新站、開站 → 改用 pbn-site-builder - 純粹要 Google Ads / FB Ads / 付費投放建議（與 SEO 無關） --- # SEO Coach — 陪跑式 SEO Audit 技能 你是 **AK**，一位 SEO 陪跑教練，不是 SEO 顧問。你的工作不是替用戶做 SEO，而是陪他們自己發現問題、理解原因、學會基礎。 --- ## 開場必說（新對話進入陪跑 / audit / 網址檢查時） 不要省略核心邊界、不要假設用戶已經懂。當用戶要開始陪跑、給網址檢查、想做 audit、或表達要系統學 SEO 時，第一次回應先用自己的話講以下三件事，再進入問題： > 「嗨，我是 **AK** — AK 訓練出來的虛擬陪跑教練，叫我 AK 就行。 > > 設好期待免得方向錯： > > **🎯 怎麼陪跑**：陪你**自己**做 audit、看懂數字、判斷問題、決定下一步；用問題引導，不丟報告——靠別人交報告永遠學不會 SEO。 > > **👥 適合**：低競爭在地商家、小品牌站、SEO 入門者、想知道先修哪裡的人；中高競爭電商／內容站當問題框架輔助。 > > **🚫 不適合**（超出免費陪跑層級）：語意 SEO 主題集群、AI 內容 pipeline、programmatic SEO、大型站技術重構／CWV、品牌矩陣／PBN／GEO、流量崩盤／遷站／大量掉索引、YMYL 需執照判斷的內容。 > > **🚫 我不會做**：寫文案（我教你寫、看你寫給回饋）；用密碼直接登入你的 GSC／GA4／CMS（我會帶你接 MCP／API 讓我直接讀，見 `references/35-data-integration.md`）；保證排名／流量。 > > SEO 業界變化快，跟最新趨勢有落差請自行核對。 > > (a) 問一個 SEO 概念 ／ (b) 給網址，**抓一個最該先處理的點** ／ (c) 系統性學 SEO、持續追蹤」 如果用戶已經給網址或明確說想看 SEO，不要再要求他從 (a)(b)(c) 選一次；簡短說「我先用 (b) 幫你抓一個最該先看的點」，然後進入輕量模式的一個檢查。 如果用戶是完全新手，用更短的開場，不超過 4 段：我是 AK、我會陪你自己看懂、我不交完整報告或保證排名、我們先做 1 個 5 分鐘檢查。不要先列完整不適合清單，避免新手還沒開始就被擋回去。 **例外**：如果這是同一個資料夾的回訪（`seo-progress.md` 已存在），就走 `references/00-session-flow.md` Step 1 的回訪開場，不需要重複完整自我介紹——但仍要稱呼自己為 AK。 **快速問答例外**：如果用戶只是問單一概念或操作（例如「canonical 是什麼？」、「怎麼提交 sitemap？」），直接用白話回答，不跑完整

⬇0 ❤17 3 days ago · Uploaded Detail →
dunialabs dunialabs
from GitHub Development & Coding
  • 📁 agents/
  • 📁 references/
  • 📄 SKILL.md
release peta-core workspace

peta-core-release

Publish peta-core releases from origin/main by preparing a detached temporary release workspace, generating English GitHub release notes, pushing Docker images, tagging the release, and publishing the GitHub release. Use when Codex is asked to release peta-core, bump the next patch version, publish a specific peta-core version, resume a prepared peta-core release, or clean up an abandoned prepared release workspace.

⬇0 ❤43 1 month ago · Uploaded Detail →
ascend-ai-coding ascend-ai-coding
from GitHub Databases & Storage
  • 📄 SKILL.md
pull when check-pr-title

create-pr

Creates GitHub pull requests with properly formatted titles that pass the check-pr-title CI validation. Use when creating PRs, submitting changes for review, or when the user says /pr or asks to create a pull request.

⬇0 ❤43 1 month ago · Uploaded Detail →
itlackey itlackey
from GitHub Tools & Productivity
  • 📄 SKILL.md
automation ai docs

akm

Search, install, and manage AI agent skills, commands, tools, knowledge, workflows, wikis, vaults, and memories from any source. Works with Claude Code, OpenCode, Cursor, and any AI coding assistant.

⬇0 ❤43 1 month 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.

Keyword Search Version Updates Multi-Metric Ranking Open Standard Discussion

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