The `AtomicAgent` is the core class for LLM interactions in the Atomic Agents framework. It handles structured input/output, conversation history, and system prompt management.
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →The `AtomicAgent` is the core class for LLM interactions in the Atomic Agents framework. It handles structured input/output, conversation history, and system prompt management.
Proper project organization is essential for maintainable Atomic Agents applications. Structure scales from simple scripts to complex multi-agent systems.
Play a short audible alert and a spoken prompt indicating which project needs attention. Use this as the final step after completing work on every response, and also right before asking the user for i
Configure AI personality using the AURA protocol (HEXACO-based). Use when user wants to customize agent personality, reduce sycophancy, adjust communication style, or mentions AURA/personality configuration.
Automatic learning from session command patterns
System intelligently routes user messages to optimal models via task classification, cost-based diversity, and high-stakes safety overrides.
Microsoft AutoGen multi-agent configuration for conversational AI systems
Send /new to a provider's pane to start a new session without context injection.
Use when first installing Axiom, unsure which skill to use, want an overview of available skills, or need help finding the right skill for your situation — interactive onboarding that recommends skills based on your project and current focus
Use when implementing ANY Apple Intelligence or on-device AI feature. Covers Foundation Models, @Generable, LanguageModelSession, structured output, Tool protocol, iOS 26 AI integration.
Use when implementing ANY computer vision feature - image analysis, object detection, pose detection, person segmentation, subject lifting, hand/body pose tracking.
>
Interact with Polymarket prediction markets.
>
Use to standardize competitive positioning, objection handling, and talk
Context packages and learning patterns. Use when managing context packages, error patterns, or strategies.
Activate a beta feature using an activation code
View your activated beta features and their status
blender-toolkit
Create a new technical blog post with deep educational value and professional quality
Create new posts using the hydrate command.
Use after modifying existing systems to update blueprint documentation. Read blueprints with read_blueprint before changes, update with write_blueprint after. Prevents documentation drift.
Teaches how to discover, validate, and add llms.txt documentation sources to the blz CLI. Use when adding documentation to blz, finding llms.txt or llms-full.txt files, validating sources, refreshing content, or managing the documentation index. Covers source discovery, dry-run validation, and index file handling.
Check GitHub Project board status for the monorepo. Use when user asks about board status, what's in progress, sprint status, or issue tracking.
> **Claude는 정원사, 사용자는 나무**
Bug hunting with Codex CLI Use when: (1) /bugs is invoked, (2) task relates to bugs functionality.
Business model design using Osterwalder's Business Model Canvas and Lean Canvas. Creates 9-block canvases with structured analysis for business model innovation and startup validation.
Lean Canvas를 사용하여 포괄적인 비즈니스 모델을 설계합니다. 수익 흐름과 비즈니스 전략을 계획할 때 사용하세요.
calendar
Calendar management and scheduling. Create events, manage meetings, and sync across calendar providers.
Develops Canvas code execution features with Pyodide/iframe sandboxing. Use when working on Python/JS execution, package management, or sandbox security.
Capture user ideas verbatim in .wrangler/ideas/ directory using the MCP issues_create tool with type='idea'. Preserves exact user wording without interpretation or enhancement.
Эксперт categorical encoding. Используй для ML feature engineering, one-hot, target encoding и embeddings.
CatSharp Scale Galois Connections between agent-o-rama and Plurigrid ACT via Mazzola's categorical music theory
Facts about how Claude Code organizes and stores data.
Use when working with Claude Code plugin marketplaces - adding, updating, creating, or understanding how marketplace versioning and caching work.
GitHub repository skill for mcfearsome/cc-mcp-executor-skill
Automatically discover distributed systems skills when working with consensus, CRDTs, replication, partitioning, and distributed algorithms
Development skill from everything-claude-code
Development skill from everything-claude-code
Update CFN system expert agent with relevant git commits and project changes
Autonomously draft and polish chapters through multi-skill editorial passes. Use when you have a complete outline and want to produce a polished first draft with iterative refinement.
Track and analyze character development arcs throughout the manuscript
Creates a **production-ready ChatGPT-style chatbot widget** with advanced features:
Check bash script syntax without executing. Use before committing bash scripts or when verifying syntax correctness.
Manage project checklist (view, add, check, edit)
checkpointing
This skill should be used when developing or modifying dotfiles using chezmoi. Covers using .chezmoidata for configuration data and modify_ scripts (or run_onchange_after_ scripts for symlinked directories) for non-destructive file merging. Particularly useful when needing to configure application settings without overwriting user preferences.
>
Comprehensive session management for Claude Code - search, analyze, and resume conversations from any directory.