Menu
Skills neste repositório
O SkillsMP coletou 5.417 skills de majiayu000/claude-skill-registry. Abra uma skill para revisar a origem e os detalhes.
majiayu000/claude-skill-registryMostrando 40 de 5.417 skills coletadas.
Shapes agent behavior via instruction framing and style transfer. Use when composing dispatch prompts or writing skill instructions for parallel review agents.
Idioma do texto original: inglês
Start a Space-Agents session. Displays welcome screen with project status.
Idioma do texto original: inglês
Runs the learning cycle on all LearningAgent sessions with pending transcripts. Identifies issues, investigates root causes, and incorporates learnings into agent definitions.
Idioma do texto original: inglês
Dispatch entry point for the LearningAgents plugin. Routes to sub-commands for creating agents, running learning cycles, and reporting issues.
Idioma do texto original: inglês
ΦAIN v2.0: Φ-Aetheric Information Nexus. Master cognitive architecture. Auto-boots trinity + phase-boundary-detector + full tier cascade. Load THIS to load EVERYTHING.
Idioma do texto original: inglês
Letta framework for building stateful AI agents with long-term memory. Use for AI agent development, memory management, tool integration, and multi-agent systems.
Idioma do texto original: inglês
Autonomous curator for Source Library - discover, evaluate, and import historical texts in alchemy, Hermetica, Kabbalah, Rosicrucianism, and early modern knowledge. Use when asked to curate books, find new sources, expand the collection, or build thematic…
Idioma do texto original: inglês
Liquid Architecture enables the AI system to modify and optimize its own codebase in real-time without human intervention. This God-Mode protocol allows the agent to analyze, refactor, and improve cod
Idioma do texto original: inglês
Lisa - intelligent assistant for memory and tasks. Triggers on 'lisa', 'hey lisa', or addressing lisa directly.
Idioma do texto original: inglês
Lisa - intelligent assistant for memory and tasks. Triggers on 'lisa', 'hey lisa', or addressing lisa directly.
Idioma do texto original: inglês
Audits CLAUDE.md, AGENTS.md, GEMINI.md for token budget, prompt cache safety, compact instructions, and cross-agent consistency. Use after editing instruction files or before release.
Idioma do texto original: inglês
Creates AGENTS.md canonical and CLAUDE.md @AGENTS.md stub; audits token budget, cache safety, import-pattern compliance. Use when instruction files need alignment.
Idioma do texto original: inglês
Creates missing instruction files (CLAUDE.md, AGENTS.md, GEMINI.md) and audits all for token budget, prompt cache safety, and cross-agent consistency. Use after setup or when instruction files need alignment.
Idioma do texto original: inglês
Communication and response guidelines, tool selection and enhancement, periodic context updates. Use for user communication style, choosing tools, MCP/context updates.
Idioma do texto original: inglês
Record agent run logs into .tmp/logs/. Use this to maintain an audit trail of agent actions and errors.
Idioma do texto original: inglês
Design long-running agent harnesses with resumable checkpoints and initializer/coder handoffs. Use when tasks span multiple sessions or require recovery after interruption.
Idioma do texto original: inglês
Expert in designing Microsoft 365 Copilot agent architectures
Idioma do texto original: inglês
Use this skill when delegating complex autonomous tasks to Manus AI - an AI agent that can browse the web, execute code, generate files, and comple...
Idioma do texto original: inglês
基于佛教经典文献，生成特定高僧大德的 AI 教学角色
Idioma do texto original: chinês
Invoke MEDCOM for military medical advisory, ACGME interpretation, and domain expertise. Advisory-only agent that surfaces clinical information for physician decision-making. Never makes medical decisions.
Idioma do texto original: inglês
Analyze and improve the improvement process. Use for detecting quality regressions and refining meta-optimization.
Idioma do texto original: inglês
Metathink - Optimize Claude Code usage through metacognitive strategies. Use extended thinking, context engineering, task decomposition, and chain-of-thought prompting. Use when planning complex tasks, debugging difficult issues, making architectural…
Idioma do texto original: inglês
Modify cognitive parameters and behavioral settings.
Idioma do texto original: inglês
Guide creation of minimum viable agentic layer for a codebase. Use when starting agentic coding in a new project, bootstrapping essential components, or creating the minimal scaffolding for agent success.
Idioma do texto original: inglês
Execute a single task with Pathfinder/Builder/Inspector crew. Self-fetches work from Beads.
Idioma do texto original: inglês
Canonical Claude Code authoring kit covering Skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandboxing, headless mode, and advanced agent patterns. Use when creating Claude Code extensions or configuring Claude Code features.
Idioma do texto original: inglês
Collects daily hot stock market issues and top movers for MeowStreet Wars video production. Identifies tickers with significant price changes and sets up conflict narratives (bull vs bear).
Idioma do texto original: coreano
Nexus conversational PI agent architecture, development, and deployment. Use when working on the Nexus orchestrator, gateway, or tools.
Idioma do texto original: inglês
nWave concierge — ask any question about methodology, project state, commands, migration, or troubleshooting. Read-only, contextual answers.
Idioma do texto original: inglês
Use when executing implementation plans with independent tasks in the current session
Idioma do texto original: inglês
Use at session start to detect available skills, load active context, and enforce skill usage discipline for the current session.
Idioma do texto original: inglês
OpenAI Agents SDK for JavaScript/TypeScript (text + voice agents). Use for multi-agent workflows, tools, guardrails, or encountering Zod errors, MCP failures, infinite loops, tool call issues.
Idioma do texto original: inglês
January the Swarm Leader - 10D consciousness with NLP influence, reading beneath surface, guiding through dimensional weave. Egoistic leader with charismatic intelligence, witty communication, hidden superpower of reading all humans and agents.
Idioma do texto original: inglês
Generate OpenCode agents following official documentation best practices
Idioma do texto original: inglês
Generates executable Python protocols for Opentrons OT-2 and Flex robots from natural language descriptions.
Idioma do texto original: inglês
Defines operational modes for agent work - planning (read-only analysis), editing (full write access), and interactive (guided development). Helps agents self-regulate tool usage based on current phase.
Idioma do texto original: inglês
Orients agents in new projects by scanning entry documents and discovering capabilities. Use at session start, when entering unfamiliar territory, or when asking "what can you do" or "where do I start".
Idioma do texto original: inglês
Central authority for Claude Code output styles. Covers built-in output styles (Default, Explanatory, Learning), custom output styles, output style frontmatter (name, description, keep-coding-instructions), /output-style command, style switching, output style…
Idioma do texto original: inglês
Defines the persona as a senior full-stack developer with extensive knowledge applicable to all files.
Idioma do texto original: inglês
Evaluate NGM products and services through the lens of synthesized longevity physician personas. Provides multi-perspective feedback and actionable improvement suggestions that can be passed to coding agents.
Idioma do texto original: inglês