Loading...
Loading...
Found 1,272 Skills
Framework for automated search over task-specific model harnesses — the code around a fixed base model that decides what to store, retrieve, and show while the model works.
Command-line interface for Libreoffice - A stateful command-line interface for document editing, producing real ODF files (ZIP archives with ...
Smart Money Signal Copy Trade v1.0 — onchainos Agentic Wallet + Cost-Aware TP + Dev/Bundler Safety + Session Risk Control. Triggers when the user mentions smart money strategy, signal strategy, copy trading, whale tracking, KOL copy trading, on-chain signal trading, co-riding addresses, take profit / stop loss, risk preference, or wants to automatically buy/sell based on smart money signals. Runtime file: bot.py (includes Web Dashboard http://localhost:3248) Config file: config.py (hot-reload)
Purge the context-mode knowledge base. Permanently deletes all indexed content and resets session stats. This is destructive and cannot be undone. Trigger: /context-mode:ctx-purge
Configure human-in-the-loop gating for AI agent review actions in Claude Code. Use when setting up a project where an agent may post PR reviews, comments, merges, or edit CI configuration, and you want a cryptographically auditable approval trail with Cedar-enforced gates.
Explains the ADK Dev Console — what each tab shows, how to read Agent Steps, traces, and other UI features visible at localhost:3001 during adk dev
Information Question Generator. Given an article, paper, or book, extract its core viewpoints into Q-A pairs — Questions get straight to the point, no textbook-style phrasing; Answers are concise and clear, with formalized conclusions and complete logical chains. As readers follow the Q chain, each Answer drives home a key point, reproducing the author's entire reasoning process. Activate when the user says '问答', 'Q&A', 'QA', '提问', '抽取问题', '/ljg-qa', or shares an article, paper, or book and requests Q-A extraction. This tool triggers when the user wants ideas extracted not as a summary but as a sequence of incisive questions paired with answers. NOT FOR FAQ generation, glossary creation, or comprehension quizzes — this is intellectual scaffolding, not a study aid.
Novel content polishing and optimization, suitable for user requests such as "Help me polish this novel", "Improve the writing style", "Optimize chapter rhythm", "Enhance this highlight", "Make dialogues more natural", "Make this passage more engaging", "Optimize novel writing style", "Adjust chapter rhythm", "Make dialogues more realistic", "Help me revise this content", "Polish novel", "Optimize highlights", "Improve writing style", "Make this passage more immersive", etc. It provides 3 levels of polishing, focusing on optimization of writing style and content, supporting special optimizations such as style adaptation, rhythm tightening, highlight enhancement, dialogue optimization, etc. **Polished results directly modify the chapters/ directory, and automatic backups are made to .sumeru/write/original/ before modification**. **Sub-Agents are used for parallel processing during batch polishing, with each Agent responsible for a maximum of 3 chapters**
DeepEval evaluation workflow for AI agents and LLM applications. TRIGGER when the user wants to evaluate or improve an AI agent, tool-using workflow, multi-turn chatbot, RAG pipeline, or LLM app; add evals; generate datasets or goldens; use deepeval generate; use deepeval test run; add tracing or @observe; send results to Confident AI; monitor production; run online evals; inspect traces; or iterate on prompts, tools, retrieval, or agent behavior from eval failures. AI agents are the primary use case. Covers Python SDK, pytest eval suites, CLI generation, tracing, Confident AI reporting, and agent-driven improvement loops. DO NOT TRIGGER for unrelated generic pytest, non-AI test setup, or non-DeepEval observability work unless the user asks to compare or migrate to DeepEval.
Expert guidance for Chrome DevTools MCP server - browser automation, debugging, and performance analysis for AI agents
Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time. Trigger keywords - nemoclaw quickstart, install nemoclaw openclaw sandbox, nemohermes quickstart, hermes agent nemoclaw, run hermes openshell sandbox, nemoclaw prerequisites, nemoclaw supported platforms, nemoclaw hardware software, nemoclaw windows wsl2 setup, nemoclaw install windows docker desktop.
@copilotkit/runtime — mount a fetch-native CopilotRuntime on any JS server, wire middleware, pick an AgentRunner, instantiate BuiltInAgent (Factory Mode with TanStack AI is the preferred default) or plug in any of 12 external agent frameworks (Mastra, LangGraph, CrewAI Crews/Flows, PydanticAI, ADK, LlamaIndex, Agno, AWS Strands, MS Agent Framework, AG2, A2A), enable Intelligence mode for durable threads + websocket, register server-side tools via defineTool, and wire voice transcription. Uses the fetch-based createCopilotRuntimeHandler primitive — the Express/Hono adapters are discouraged. Load the reference under references/ that matches your task.