Loading...
Loading...
Found 6,669 Skills
Converts an idea or an Inbox note into a structured Project Note
Preserve critical session state when compacting context. Use when context window is filling up and you need to summarize/reduce while keeping essential debugging information.
An intelligent search router based on the opencli command. This skill must be used when users want to search, query, look up or research information, especially when it involves specified websites, social media, technical materials, news, shopping, travel, job hunting, finance or Chinese content.
/cs:onboard — Founder interview that populates ~/.claude/company-context.md. The first command to run when starting with c-level-agents.
Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation
Transform documents into styled article series. Analyze input (md, txt, pdf, docx, pptx, xlsx, html, epub, images, url), extract core ideas, decompose into logical sections, write articles with user-selectable styles (professional, casual, custom), synthesize into organized output. Uses Docling for high-quality document conversion. Handles large documents with hierarchical summarization. Output to docs/generated/.
LangChain workflows for `create_agent`, LCEL chains, `bind_tools`, middleware, and structured output with production-safe orchestration. Use when implementing or refactoring LangChain application logic in Python or TypeScript.
Saves conversation history to session log files. Use when user says "保存对话", "保存对话信息", "记录会话", "save session", or "save conversation". Automatically creates timestamped session log in sessions/ directory.
Run adversarial review on a PM artifact via the pm-critic sub-agent. Dispatches natively on Claude Code with the pm-skills plugin (invokes @agent-pm-critic); on non-Claude clients (Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI) reads subagents/pm-critic.md and executes the system prompt inline. Returns findings graded P0/P1/P2/P3 with concrete fix suggestions per finding, plus a layered Status Summary section and machine-readable Status YAML block per master plan D26.
Tabular review — one row per document, one column per data point, every cell cited to source. Built for M&A diligence ("review these 200 target contracts for change-of-control, assignment, and MAC clauses") but works for any batch review that needs a spreadsheet out the other end. Use when user says "tabular review", "review grid", "build a grid", "extract these fields from these contracts", "review these documents for X, Y, Z", "give me a spreadsheet of", "batch review", or points at a folder of documents and asks to compare them.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Official GitHub Model Context Protocol Server for repository management.