Loading...
Loading...
Found 1,873 Skills
Web search via Brave search engine.
C3 architecture toolkit. Manages architecture docs in .c3/ directory. Operations: onboard, query, audit, change, ref, sweep. Triggers: /c3, architecture questions when .c3/ exists, C3 docs management. Classifies intent from request, loads operation-specific reference, executes. <example> user: "adopt C3 for this project" assistant: "Using c3 to onboard this project." </example> <example> user: "where is auth in the C3 docs?" assistant: "Using c3 to query the architecture." </example> <example> user: "add a new API component" assistant: "Using c3 to orchestrate the change." </example>
Use when the user wants to manage Valet agents, channels, connectors, organizations, or secrets via the valet CLI. Handles creation, deployment, linking, teardown, and all multi-step workflows. Also use when asked to "create an agent", "deploy an agent", "design an agent", "build me an agent that...", "create a connector", "set up a webhook", or anything involving the Valet platform or any request to create and deploy AI agents. Also use when asked to "learn from this session", "capture this workflow", "save this as an agent", "make this repeatable", or when writing SOUL.md files.
Extract subtitles from YouTube video links and convert them into Chinese transcripts. Supports both auto-generated and manual subtitles. Usage scenarios: (1) Users provide a YouTube link and request subtitle/transcript extraction, (2) Users request to convert YouTube video content into text, (3) Users say "Help me convert this YouTube video to text" or similar requests. Trigger words: YouTube subtitles, video to text, extract subtitles, YouTube transcript, video text draft.
When creating vector artwork, illustrations, or SVG graphics for creative expression - provides iterative drawing workflow with visual feedback using render-svg tool
Batch-process web pages via headless Playwright browser, extract HTML, convert to markdown using Turndown, and save to timestamped scratchpad file. Use when user asks to "capture these pages as markdown", "save web content", "fetch and convert webpages", or needs clean markdown from HTML. All URLs from one prompt → single file at docs/web-captures/<timestamp>.md.
Read content from Feishu cloud documents or knowledge bases and analyze document structure. It is used when users request to "view", "read", "analyze", "fetch", "open" Feishu documents or knowledge bases. It supports reading via document ID, knowledge base Token or URL. Markdown is used as the intermediate format and stored in the /tmp directory.
Cal.com event types, schedules, and availability configuration. TRIGGERS - event type, booking page, schedule, availability, create calendar, configure calcom, booking link.
Access AI-generated documentation and insights for GitHub repositories via DeepWiki. This skill should be used when exploring unfamiliar codebases, understanding repository architecture, finding implementation patterns, or asking questions about how a GitHub project works. Supports any public GitHub repository.
Master orchestrator: brand-init → brand-compile → brand-assets. One command to go from zero to full brand system.
Fetch and read web pages as Markdown via Jina Reader (https://r.jina.ai/). Use when you need the readable content of a URL (articles, docs, blog posts) without a browser/JS, or when you want a quick plain-text/markdown snapshot for summarization, quoting, or extraction.
Use the Docyrus CLI (`docyrus`) to interact with the Docyrus platform from the terminal. Use when the user asks to authenticate, list apps, query/manage data records (`ds`), manage dev app data source schema objects (`studio`), send API requests, switch environments/tenants/accounts, or discover OpenAPI specs via the `docyrus` command-line tool. Triggers on tasks involving docyrus CLI commands, terminal-based Docyrus operations, `docyrus ds list`, `docyrus studio`, `docyrus discover`, `docyrus auth`, `docyrus env`, or shell-based Docyrus workflows.