Content Analyzer — any content (URL, text, transcript) into structured analysis report with actionable insights. Use when user asks to analyze, summarize, or extract key takeaways from content.
LLM-compiled knowledge base manager. Activates when user works with wiki directories, mentions knowledge base management, asks knowledge questions in a project with a wiki, wants to ingest/compile/query/lint knowledge, or uses /wiki commands. Also activates when user says "wiki", "knowledge base", "ingest", "compile wiki", "add to wiki", "search wiki", "librarian", "scan quality", "article quality", "content review", or asks a factual question in a directory containing .wiki/ or when ~/wiki/ exists or the configured hub path exists (check ~/.config/llm-wiki/config.json for hub_path).
Manage stacked branches and pull requests with the gh-stack GitHub CLI extension. Use when the user wants to create, push, rebase, sync, navigate, or view stacks of dependent PRs. Triggers on tasks involving stacked diffs, dependent pull requests, branch chains, or incremental code review workflows.
Run or debug the Gas City tutorial acceptance harness in this repo when you need the coding-agent CLIs, supervisor, and city state isolated in temp homes while still authenticating Claude and Codex correctly.
使用 1Password CLI (op) 管理密码和 API credentials。保存、查询、读取 API key/token，注入环境变量到脚本。当用户提到保存密码、保存 API key、查询密码、1password、op CLI、secret 管理时使用此 skill。
Use this skill whenever you need to pay for an x402 URL, transfer USDC to an address, inspect OmniClaw balances or ledger entries, or expose a paid API with omniclaw-cli serve. OmniClaw is the Economic Execution and Control Layer for Agentic Systems. The CLI is the zero-trust execution layer: buyers use `omniclaw-cli pay`, sellers use `omniclaw-cli serve`. Use this skill for the CLI execution path only, not for owner setup, policy editing, wallet provisioning, or Financial Policy Engine administration.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Query and browse evaluation results stored in MLflow. Use when the user wants to look up runs by invocation ID, compare metrics across models, fetch artifacts (configs, logs, results), or set up the MLflow MCP server. ALWAYS triggers on mentions of MLflow, experiment results, run comparison, invocation IDs in the context of results, or MLflow MCP setup.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.
DEFAULT PIPELINE for all tasks requiring execution. You (Claude) are the strategic orchestrator. Codex agents are your implementation army - hyper-focused coding specialists. Trigger on ANY task involving code, file modifications, codebase research, multi-step work, or implementation. This is NOT optional - Codex agents are the default for all execution work. Only skip if the user explicitly asks you to do something yourself.
Use this skill whenever adding a new UniFi resource type as a supported tool category — creating a manager, tool layer, schemas, tests, and wiring everything into the manifest and CI. Activates for any PR or task that introduces a new manager class (managers/{resource}_manager.py), new tool module (tools/{resource}.py), or new UniFi subsystem support, even if the user only asks to "add support for X" without specifying each step. Covers: manager class with CRUD + lru_cache factory, 405 endpoint workarounds, schema definition and validator registry wiring, tool layer with preview/confirm flow and correct ToolAnnotations, test file requirements (both layers), V2 API response unwrapping, manifest regeneration, test_scaffold.py CI registration, and Protect-package naming conventions.
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
├─ ⭐ 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
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.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
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.
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.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused 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.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
