Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
A workflow that turns a supplied book or article into a short summary and a small action plan lasting a chosen number of days. It can work in English, Chinese, or both, but it only uses source text the user provides.
Browser engine for AI agents: fetch JS-rendered and Cloudflare-protected pages as clean markdown, run 5-engine aggregated web search (Baidu, Bing, Sogou, WeChat, Google), take screenshots as visual input, extract structured data from SPAs, and drive multi-step interactions (click, type, fill forms, login, paginate)…
Generate beautiful Mermaid diagrams — flowcharts, sequence, ER, class, state, pie, gantt, mindmap, timeline, gitgraph, C4, kanban, block, quadrant, sankey, XY charts. Renders to PNG locally and Markdown for GitHub. Use when the user asks for diagrams, visualizations, schemas, flowcharts, architecture overviews…
Implements interactive widget actions and bidirectional communication patterns for ChatKit. This skill should be used when building AI-driven interactive UIs with buttons, forms, entity tagging (@mentions), composer tools, and server-handled widget actions. Covers the full widget lifecycle from creation to replacement.
Grades agent skills by scoring agent conversations against efficiency and code-quality rubrics, then drafts concrete skill edits and a shareable report. Use when the user wants their agent setup graded from real conversation history, or asks which of their installed skills are actually working.
Appwrite Dart SDK skill. Use when building Flutter apps (mobile, web, desktop) or server-side Dart applications with Appwrite. Covers client-side auth (email, OAuth), database queries, file uploads with native file handling, real-time subscriptions, and server-side admin via API keys for user management, database…
Review the agents-remember cockpit dashboard like a user: discover the intended workflow scenarios, detect missing views and where users get stuck, and judge whether the UI is self-explanatory at a glance / leads the user / progressively discloses / has clear hierarchy / is a good observability surface. Conducts the…
Search and explore an Obsidian vault through the NoteBrain CLI (semantic search, tags, backlinks, connections, hidden links, boosted retrieval). Use it whenever the user mentions their notes, knowledge base, Obsidian vault, semantic search, finding connections or unlinked notes, or asks exploratory questions like…
Operate VibeKit inside projects created or configured by vibekit new and vibekit init. Use for VibeKit CLI and MCP tools, project setup, LocalNet, accounts, signing, network selection, deployment, transactions, and troubleshooting. Load before any on-chain action in a VibeKit-configured project. Excludes authoring…
Use when a feature or code change made by Claude is complete and the developer wants to confirm they actually understood it before shipping. Triggers on "handoff", "quiz me", "comprehension check", "did I understand this", "verify I read the code", "test my understanding", or after finishing a feature when the…
The prompt engineer for autonomous agent runs. Interviews the user about what they're building, then writes the perfect mission prompt — never-ask autonomy rules, multi-agent orchestration, end-to-end UI testing quality bar, and a provable definition of done baked in — plus a full overnight scaffold (feature list…
Use when the user explicitly invokes $fable-mode or asks for fable-mode style routing. Keep ordinary simple tasks outside this skill; it is for intent, output-form, grounding, capability, and depth control.
Converts a Webflow HTML export into a maintainable React app with TanStack Start (SSR, TanStack Router conventions) using an idiomatic React-first approach. Sets up Storybook early, builds UI primitive + page-section SOT components with variant stories before composing routes. Use when the user has a Webflow export…
A study assistant that turns PDF, Word, text, and Markdown learning materials into condensed key points and an interactive HTML review page. It supports scanned PDFs through OCR, which converts images of text into searchable text.
Eino LLM/AI application development framework assistant (Golang). Use when the user needs to: (1) Build AI agents, (2) Create LLM applications, (3) Implement tool calling, (4) Build multi-agent systems, (5) Create workflows with Graph/Compose, (6) Implement streaming, (7) Human-in-the-loop patterns, or any other Eino…
Connect to Weibo through the built-in local-mcp Weibo adapter and one fixed UXC link. Use when the user wants to read timelines, inspect posts, publish posts or comments, manage Weibo articles, or run Weibo search from an authenticated browser profile.
Execute a workflow script that orchestrates multiple subagents deterministically. Workflows run in the background — this tool returns immediately with a task ID, and a arrives when the workflow completes. Use /workflows to watch live progress.
Enforces the Airbnb iOS Swift Style Guide on Swift code. Use this skill any time the user wants to: review Swift code for style compliance, lint or audit an iOS codebase, apply Airbnb Swift conventions to new or existing code, understand why code violates Airbnb style rules, or get corrected rewrites of Swift…
Operate KOMPAS-3D MCP for 2D drawings, 3D parts, CAD-as-Code scripts, screenshots, exports, runtime memory, remote/local recovery, and Graph Brain diagnostics. Use when Codex needs to create, edit, inspect, validate, or debug geometry through mcpkompas3d, especially for sketch-feature chains, reusable scenarios…
A version-management skill that detects plugins changed since the last version commit and raises the version only for the affected plugin.
★not rated 27 yesterdayA83 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: