skill-generator
Generates Claude Code skills from user descriptions. Use when creating new skills, converting documentation to skills, or scaffolding skill structure.
Generates Claude Code skills from user descriptions. Use when creating new skills, converting documentation to skills, or scaffolding skill structure.
Condenses Claude Code session transcripts into readable summaries by filtering metadata, system notifications, and command artifacts. Use when the user wants to review, analyze, or understand what happened in a Claude Code session, view tool usage patterns, or export session data. Triggers when user mentions "analyze session", "review transcript", "condense logs", "what tools did I use", or similar workflow analysis requests.
Use when working with the AGI Memory System - creating memories, querying, testing, database operations, or understanding the memory architecture.
game-designer for engaging, immersive learning experiences.
Real-time voice AI knowledge including STT and TTS providers, LiveKit Agents plugins, and voice pipeline patterns. Use when working with speech-to-text, text-to-speech, voice agents, LiveKit, or any voice-related infrastructure.
Generates comprehensive documentation explaining how a codebase works, including architecture, key components, data flow, and development guidelines. Use when user wants to understand unfamiliar code, create onboarding docs, document architecture, or explain how the system works.
Open questions register. Use for: QID generation, OQ-SIG-001 format IDs, append questions, open_questions.md. Generate sequential QIDs, append questions with context. Use in clarifier when registering open questions instead of guessing. Invoke via bash .claude/scripts/demoswarm.sh openq next-id|append.
Create personalized, adaptive learning pathways with branching logic, prerequisite tracking, competency-based progression, and mastery-based advancement. Use when designing adaptive curricula or personalized learning experiences. Activates on "learning path", "adaptive curriculum", "personalization", or "custom pathway".
Complete game asset design, creation, implementation, and optimization team. Use when creating visual assets, art direction, sprites, UI elements, icons, textures, animations specs, audio design, or any game visuals. Covers AI image generation (Gemini), asset pipelines, optimization for web/mobile, style guides, and performance tuning. Triggers on requests for game art, icons, backgrounds, character designs, UI assets, promotional materials, or asset troubleshooting.
Externalize detailed memory to Memory Bank before conversation summarization to prevent context loss. Triggers: CP, checkpoint, save, 存檔, 記一下, 保存, sync memory, dump, 先記著, 備份, backup, snapshot, 快照, 記錄, 等等, 先停, pause, 離開前, before leaving, 收工.
Brainstorm and advise on technical decisions using structured process and MCP helpers. EXCLUSIVE to brainstormer agent. Does NOT implement — only advises.
Fast ideation and problem exploration. Triggers on Ukrainian/English phrases like "подумай", "поміркуй", "брейнштормінг", "brainstorm", "think through", "накидай ідеї", "generate ideas". Rapid divergent thinking to uncover insights, problems, and solutions through interactive dialogue.
Test Claude Code skills in real-world scenarios to validate functionality, usability, and effectiveness. Task-based testing operations for scenario testing, example validation, integration testing, and usability assessment. Use when testing skill functionality, validating examples work correctly, ensuring real-world effectiveness, or conducting scenario-based quality assurance.
Spawns a focused subagent to query language/framework documentation. Use for complex questions requiring exploration across multiple symbols, external library APIs, or understanding how to combine types from different packages. Currently supports Go; more doc sets may be added later.
Expert game development and design skill for building complete, polished games. Use when creating games, game prototypes, or interactive entertainment experiences across platforms (React Native, web, Unity concepts, Godot). Covers game mechanics, physics, AI opponents, level design, progression systems, visual effects, sound integration, and player experience. Triggers on requests to build games, create game mechanics, design levels, implement game AI, add game audio, or develop interactive entertainment.
This skill should be used when the user asks to "brainstorm", "help me think through this", "explore ideas", "organize my thoughts", "work through this problem", or mentions needing help with complex thinking, decision-making, problem exploration, or wants a thinking partner for exploring challenges through Socratic questioning.
Teaches document writing patterns and templates that agents apply when generating documentation, reports, contracts, guides, and technical writing. Use when creating API docs, user guides, reports, changelogs, ADRs, or technical documentation.
Meta-skill for creating, refining, and managing Agent Skills. Use when needing to create new skills, improve existing skills, analyze skill performance, or teach the agent new capabilities. Enables self-improvement and knowledge capture.
Protocols for efficiently identifying, retrieving, and combining relevant skills from the index to solve complex problems without context overload.
Generates quiz questions, scenarios, and assessments aligned to learning objectives. Use when creating quizzes, test questions, knowledge checks, scenarios, question banks, or when user mentions "quiz," "assessment," "test questions," "knowledge check," or "question bank."
Meta-skill that enables skills to evolve and improve themselves through performance monitoring, variant generation, and data-driven optimization. Use this skill when you need to create new self-evolving skills, analyze skill performance, generate improved variants, deploy changes safely, or rollback to previous versions. This skill manages the complete evolution lifecycle: monitor → analyze → generate → test → deploy → verify.
Consult official Claude Code documentation from docs.claude.com using selective fetching. Use this skill when working on Claude Code hooks, skills, subagents, MCP servers, or any Claude Code feature that requires referencing official documentation for accurate implementation. Fetches only the specific documentation needed rather than loading all docs upfront.