Total 31,136 skills, AI & Machine Learning has 5040 skills
Showing 12 of 5040 skills
Agente de contexto para continuidade entre sessoes. Salva resumos, decisoes, tarefas pendentes e carrega briefing automatico na sessao seguinte.
improve a CLAUDE.md file using <important if> blocks to improve instruction adherence
Vector-based semantic memory using embeddings for intelligent recall. Store and search memories by meaning rather than keywords. Use when you need semantic search, similar document retrieval, or context-aware memory.
Generate and critically evaluate grounded improvement ideas for the current project. Use when asking what to improve, requesting idea generation, exploring surprising improvements, or wanting the AI to proactively suggest strong project directions before brainstorming one in depth. Triggers on phrases like 'what should I improve', 'give me ideas', 'ideate on this project', 'surprise me with improvements', 'what would you change', or any request for AI-generated project improvement suggestions rather than refining the user's own idea.
Load top-performing Shinka programs into agent context using `shinka.utils.load_programs_to_df`, and emit a compact Markdown bundle for iteration planning.
A comprehensive traditional Chinese metaphysics agent ("Yi Jing" expert) that combines Mei Hua Yi Shu (Timing) with Gemini AI for modern interpretation.
Orchestrate Chinese LLMs (DeepSeek, Qwen, Yi, Moonshot) through OpenRouter API with LangChain. Use when: openrouter, chinese llm, deepseek, qwen, moonshot, yi model, model routing, auto router, llm orchestration.
Implementation guidance for creating individual agents in the Arcanea system with proper structure, capabilities, and integration.
Comprehensive skill for project planning and prompt engineering. Covers hierarchical plans (briefs, roadmaps, phases), Claude-to-Claude meta-prompts, and multi-stage workflows. Use when: planning, prompt creation, agentic pipeline work, project roadmap, meta-prompts, research to implement workflow.
Guide first-time users to build a USER.md for their agents, integrating both "human-centric narrative" and "structured preference" styles to produce a unified configuration file. Use this skill when users want to create a USER.md, write a personal profile for AI, or ask "how to make agents understand me better".
Extract learnings about skill creation/improvement from a session and propagate them to the central skill learnings file, then sync to appropriate skills. Use when a session revealed patterns, anti-patterns, or insights about structuring skills. Invoke via /update-skill-learnings or after skill creation/improvement sessions.
Skill global de TrackOps para explicar que hace TrackOps, exigir la instalacion explicita del runtime con npm y guiar la activacion local de proyectos y OPERA en cada repositorio.