16,104 Open Skills

Free to get · One-click to use

✅ Keyword search & category filters
✅ Discussions & community interaction
✅ Version updates & multi-metric ranking
✅ Open SKILL.md standard

Import Skills

Composite Most Downloads Most Likes Most Comments Newest
myrealtrip myrealtrip
from GitHub Development & Coding
claude.md claude code

camp-day1

Day 1: CLAUDE.md와 Memory로 나에게 맞는 Claude Code 세팅하기 - 인터랙티브 강의 진행. Use when starting day 1 training, teaching Claude Code basics, CLAUDE.md setup, or onboarding new users.

⬇0 ❤8 12 hours ago · Uploaded Detail →
sstklen sstklen
from GitHub Data & AI
ai claude.md human-written

ai-md

AI.MD — Convert any human-written CLAUDE.md into AI-native structured format. Your CLAUDE.md is read by AI every single turn, not by you — so write it in AI's language.

⬇0 ❤9 4 days ago · Uploaded Detail →
AGoldian AGoldian
from GitHub Docs & Knowledge
documentation claude.md docs

doc-generator

Generates and updates project documentation including CLAUDE.md, rules, and hooks. Use when the user asks about documentation, project setup, CLAUDE.md, or when detecting that documentation is missing or outdated.

⬇0 ❤6 1 day ago · Uploaded Detail →
tobert tobert
from GitHub Tools & Productivity
docs claude.md agents

sync-docs

This skill should be used when the user asks to "sync docs", "update README", "update CLAUDE.md", "sync documentation with code", "check if docs are current", "refresh builtin table", "update help docs", "improve docs", "review documentation", or mentions documentation drift, stale docs, doc quality, or doc/code synchronization. Also trigger after adding or removing a builtin tool, changing language syntax, or modifying VFS mounts. --- # Sync & Improve Documentation Synchronize and continuously improve README.md, CLAUDE.md, help system docs, and language reference with the actual kaish codebase. The source of truth is always the code — docs follow. But don't just sync mechanically: apply kaizen. Every pass should leave docs clearer, more accurate, and more welcoming. ## Document Audiences Each document has a primary audience. Optimize for that audience: | Document | Primary Audience | Optimize For | |----------|-----------------|--------------| | **README.md** | **Humans** (developers discovering the project) | Clarity, invitation, first impressions. This is the front door. | | **CLAUDE.md** | **Claude / LLM agents** working in the codebase | Efficient orientation: architecture, conventions, build commands. What an agent needs to be productive immediately. | | **`docs/help/*.md`** | **LLM agents** consuming kaish via MCP | **Token density.** Every token costs money and context window. Pack maximum useful information per token. No filler, no preamble, no "this document describes...". | | **`docs/LANGUAGE.md`** | **Both** humans and agents | Complete language reference with working examples. | | **`help.rs`** | **Runtime** (agents calling `help builtins`) | Correct categorization of every registered tool. | > **Key distinction:** README.md sells kaish to humans. CLAUDE.md orients > agents to work *on* kaish. Don't mix these concerns. README doesn't need > crate internals; CLAUDE.md doesn't need marketing copy. ## Sources of Truth | What | Canonical Location | |------|

⬇0 ❤8 13 days ago · Uploaded Detail →
smith-horn smith-horn
from GitHub Testing & Security
claude.md progressive disclosure

claude-md-optimizer

Optimize oversized CLAUDE.md files using progressive disclosure. Analyzes content tiers, detects encryption constraints, creates sub-documents, and rewrites the main file with a Sub-Documentation Table. Triggers: optimize CLAUDE.md, reduce CLAUDE.md size, CLAUDE.md too long, apply progressive disclosure to CLAUDE.md

⬇0 ❤4 10 days ago · Uploaded Detail →
nobrainer-tech nobrainer-tech
from GitHub Tools & Productivity
claude.md automation workflow

continuous-improvement

Dopisuje zasady Workflow Orchestration, Task Management i Core Principles do CLAUDE.md bieżącego projektu. Triggeruj gdy użytkownik mówi "dodaj zasady do CLAUDE.md", "continuous improvement", "dopisz workflow rules", "upgrade CLAUDE.md", "setup CLAUDE.md".

⬇0 ❤2 6 days ago · Uploaded Detail →
atompilot atompilot
from GitHub Development & Coding
review ai claude.md

skill-evo

交互式锻造项目专属 Claude Code skills。每次执行都会扫描项目现状， 首次运行初始化完整 skill 体系，后续运行优化完善现有 skills。 所有生成的 skill 内置自我感知与进化协议。 触发词：初始化 skills、init skills、创建 skills、项目初始化、setup skills、 生成 CLAUDE.md、skill-evo、锻造 skill、优化 skill、完善 skill、进化 skill、 审查 skill、skill review、检查 skill、skill 质量、review skill。

⬇0 ❤2 9 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.

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