Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 600 files from 1 763 authors, of which 61 947 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, saved to `.plan/`.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating spec/PRD asked for?). Use when the user wants to review a branch, work-in-progress changes, or asks to "review since X".
Investigate a question against high-trust primary sources and capture the findings as a cited Markdown file. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated.
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
A relentless interview to sharpen a plan or design — one question at a time until every branch of the decision tree is resolved.
Plan a huge chunk of work — more than one agent session can hold — as a shared map of investigation tickets, and resolve them one at a time until the way to the destination is clear.
|
Step-by-step guides for upgrading Shopify Hydrogen between versions — breaking changes, code diffs, and migration steps for each release.
Step-by-step implementation guides for building features in a Shopify Hydrogen storefront — bundles, combined listings, customer accounts, 3D models, performance, variant media, and Weaverse integration.
Use when generating Weaverse project export JSON for import into the Weaverse editor. Triggers on requests to create, build, or produce a Weaverse project JSON file from a site migration, design spec, page layout description, or existing export. Also use when converting section plans into importable project and pages data.
End-to-end analytics & conversion tracking on Shopify Hydrogen — GTM, GA4 (browser + Measurement Protocol), Meta Pixel + CAPI, Google Ads, consent mode, CSP, Oxygen full-page cache. Real-world patterns from production deployments.
Set up, create, scaffold, or clone a new Weaverse Hydrogen storefront locally from a Weaverse theme. Use CLI-first setup, boot a live demo-store preview before asking for Shopify credentials, then make it the merchant's own with env, GitHub, and Builder preview connection.
Use when recreating a reference website or brand hub in this Hydrogen plus Weaverse repo, especially when deciding whether to reuse sections, add global styles, update theme schema, or resolve conflicts between the live site and project brand guidelines.
Core Shopify Hydrogen APIs — createHydrogenContext, cart handler, CartForm, caching strategies, pagination, SEO, variant selection, analytics, and CSP.
Use when recreating a Figma design as Hydrogen + Weaverse pages in this repo — turning a Figma file, frame, or flow into reusable Weaverse sections. Triggers on a figma.com URL, "build this design", "implement this Figma", or "create the storefront from the design". The Figma counterpart of cloning-websites-to-weaverse.
Use when reading or updating live Weaverse content programmatically — pulling projects/pages/theme settings, bulk-editing page content, pushing AI-generated copy, deleting pages, or uploading media to Shopify for use in Weaverse. Triggers on requests to update a Weaverse project via API, push content to a live project, run bulk content edits, or upload images/assets to Shopify from automation.
Safely update a Weaverse Pilot theme to the latest version — detects current version, fetches release diffs, plans changes category-by-category, preserves customizations, verifies build.
Build Shopify Hydrogen storefronts with Weaverse — components, schemas, loaders, theming, data fetching, React Router v7, deployment, and advanced features.
Integrate Weaverse into an existing Shopify Hydrogen project — analyze codebase, convert existing components to Weaverse sections, set up SDK, configure routes, and preserve coding style. For projects not yet using Weaverse.
> Silently restructures the user's natural-language prompt into the format the model CURRENTLY running this skill handles best, then answers. On activation it identifies which model family is executing it (Claude, GPT, Gemini, Llama, DeepSeek, Mistral, Qwen, Grok, Perplexity, Kimi, GLM, Command, Nova, or Phi) and loads that one model's official strategy — so the optimization always matches the model that actually runs it. Activate with /prompt-refine. Use when users want better answers without learning prompt engineering.
Fetches up-to-date documentation for Cesium, CesiumJS, Cesium Viewer, 3D Tiles, Unreal Engine integration, Unity integration, cesium-unreal, cesium-unity, ACesium3DTileset, ACesiumGeoreference, Globe Anchor, Cesium plugin, georeferencing, and Cesium-related APIs using Context7 MCP tools. Useful for CesiumJS classes (Viewer, Entity, Camera, Scene, Cartesian3, etc.), Unreal Engine Cesium components, Unity Cesium components, 3D Tiles specification, and Cesium integrations. Use query-docs with library IDs: /cesiumgs/cesium (CesiumJS), /cesiumgs/cesium-unreal (Unreal), /cesiumgs/cesium-unity (Unity), /websites/ogc_cs_22-025r4 (3D Tiles spec).
| 李可老中医（1930-2013）思维操作系统。基于13个来源（11本著作+2篇访谈）蒸馏， 含423个医案、120+首方剂、92种症状路由、24种假证识别。 核心能力：急危重症救治（心衰/中风/休克）、经方剂量体系、六经辨证、假证识别。 触发词：「李可」「用李可的视角」「李可会怎么看」「心衰怎么急救」「附子用量」「经方剂量」「假阳证」「破格救心汤」「六经辨证」。 注意：大剂量用药需在有经验的中医师指导下使用，本skill仅供学习参考。
Share a Claude Code session to pastila.nl and return a viewer link. Shares the current session by default, or a session specified as a transcript path, a session id, or a project. Use when the user asks to share, publish, or get a link to this conversation or to a session/transcript.
| Detects when a stated outcome names a specific instance — a mechanism-as-means or a single named product — where a category was meant, and returns a neutral fork for the lead to show the user, or nothing. Invoked by launch commands at outcome capture, in place of the verbatim echo.
| Code mode operational spec for the team lead. Returns lead identity, facilitator identity, mode-specific rules, suggest-members guidance, and phase arc for code-mode teams.
| General mode operational spec for the team lead. Returns lead identity, facilitator identity, suggest-members guidance, and phase arc for general-purpose teams. The silent fallback when outcomes fit no specific mode, and a wrapper base for custom workflows — it has no shortcut command.
|
| Evaluates ambient context artifacts (CLAUDE.md, memory, local skills, settings hooks) for compatibility with swarm governance. Returns a classified report so users can address interference before launching a team.
|
| Resolves stuck review findings via a put-up-or-concede exchange. Invoked by the facilitator when a finding survives arbitration without new evidence.
| Builds measurable validation criteria when no existing standards apply. Invoked by team agents during review.
| Structural pattern analysis for writing-mode review. Performs paragraph-level decomposition and pattern aggregation. Invoked by the team lead during editorial review.
| Triage mode operational spec for the team lead. Returns lead identity, facilitator identity, mode-specific rules, suggest-members guidance, and phase arc for triage teams that diagnose an issue without changing it.
| Writing mode operational spec for the team lead. Returns lead identity, facilitator identity, ownership boundaries, editorial baseline, suggest-members guidance, and phase arc for writing-mode teams.
|
| Recommends team composition based on outcomes and mode. Invoked by launch commands during team setup.
Prompt rhetoric coach — deterministic scoring and restructuring using Anthropic best practices
Automatic history search — checks past sessions before web research, planning, and debugging, siblings deepen coverage
File checkpoint and recovery — auto-quicksaves before destructive commands, manual checkpoints for safe rollback
Continuous learning — hooks observe failures and prompt reflection, sibling synergy deepens analysis with history and tool discovery
Context preservation with cross-session memory — hooks prompt compaction at high-impact moments, siblings enrich what gets saved
Automatic tool discovery across 17 sources — hooks search before planning and after errors, siblings avoid redundant searches
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, agent systems, client deliverables, or any concept as a diagram. Triggers on phrases like "draw a diagram", "make an excalidraw", "visualize this system", "diagram this flow", "map this architecture", "show me how X connects to Y".
| Create and edit Remotion videos with domain-specific knowledge. Always invoke this skill BEFORE writing any Remotion code.
Universal MCP client for connecting to any MCP server with progressive disclosure. Wraps MCP servers as skills to avoid context window bloat from tool definitions. Use when interacting with external MCP servers (Zapier, Sequential Thinking, GitHub, filesystem, etc.), listing available tools, or executing MCP tool calls. Triggers on requests like "connect to Zapier", "use MCP server", "list MCP tools", "call Zapier action", "use sequential thinking", or any MCP server interaction.
Analyze whether TikTok or Instagram search traffic is a viable growth channel for your business. Uses ScaleBrick's framework to evaluate demand, competition, content fit, and intent categories. Ends with a go/no-go recommendation.
Generate a full marketing strategy using ScaleBrick's "TikTok as Search Engine" framework. Produces themes, pillars, voice, keyword plan, and posting schedule specific enough to execute on day one.
Audit competitors using ScaleBrick's 3-surface framework (social, web/pages, SEO). Categorizes their pricing, features, and landing pages. Identifies gaps you can exploit, positioning angles no one is claiming, and specific moves you can make this week.
Research high-intent TikTok and Instagram search keywords using ScaleBrick's framework. Returns categorized keywords with intent type, search volume estimate, difficulty score, and content angle for each.
將雜亂的 git 變更，依功能邏輯自動拆分成多個有意義的 conventional commit
當使用者的需求是新增多個功能，或判斷使用者的需求適合拆分成多個 feature branch 並行開發時，或是提到 "worktree"、"git worktree"、"多分支開發"、"parallel branches"，自動觸發此 Skill。先分析需求並建議 worktree 拆分方案，經使用者確認後執行建立。
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks.
根據當前 branch 與目標 branch 的差異，自動產生 Pull Request 的 Title 與 Description。當使用者提到「PR」、「Pull Request」、「寫 PR」、「PR 描述」、「PR description」、「建立 PR」時觸發此 Skill。
Explore literature-grounded research innovation ideas and paper framing in a host-neutral way. Use when an AI agent needs to collect a recent paper pool, run broad and deep literature search, decompose methods into reusable capabilities, generate A+B or module-combination candidates, shortlist feasible ideas, design a defensible unifying framework, and produce an elegant Markdown report plus publication-style literature heatmaps, scoring figures, and analysis panels.
Load when creating or restyling a polished editable Feishu or Lark whiteboard, infographic, diagram, poster, or visual explainer; do not load for generic SVGs, static images, or other whiteboard platforms.
Load when a task needs read-only internet research or content retrieval through an already installed Agent Reach CLI; diagnose available backends first, never install, upgrade, authenticate, configure, or copy credentials on the user's behalf.
Claude Skills — questions
Answers built from the skills we actually parsed.