artifact_atlas

Token-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, validating phases.

Route an idea or request through the Agentic Operator — classify route × tier and dispatch to rf, arc, skillmeat, meatywiki, intenttree, or multi-hop workflows. Use when the user brings an idea to route, requests escalation to a new tier, approves/rejects a pending gate, or asks for run status/history. Triggers: "op new", "route this", "which subsystem", "escalate", "approve", "reject", "what's the status", "spin up". Do NOT use for: direct subsystem command invocation (use rf, intenttree, council-review, meatywiki, skillmeat-cli skills instead).

Manage SkillMeat and Claude Code environments through natural language. Use this skill for artifact discovery/deployment/management, bundles, MCP and context entity operations, and Memory & Context workflows. This skill uses progressive disclosure: load only the specific workflow or reference docs needed for the current user request.

Expert reference for Claude Code itself — features, setup, troubleshooting, and enterprise use. Use this skill when answering questions about Claude Code installation, authentication, slash commands, agent skills, MCP server configuration, hooks, plugins, subagents/agent teams, sessions, IDE integration (VS Code, JetBrains, desktop, Chrome, Slack), CI/CD integration, enterprise deployment (SSO, sandboxing, monitoring), extended thinking, prompt caching, checkpointing, cost tracking, or debugging Claude Code behaviour. Distinct from the Agent SDK: this skill is about operating and understanding Claude Code as a tool, not about building applications on the Claude Agent SDK.

Google Gemini CLI orchestration for AI-assisted development. Capabilities: second opinion/cross-validation, real-time web search (Google Search), codebase architecture analysis, parallel code generation, code review from different perspective, image generation, SVG/animation generation, multimodal screenshot-to-code. Actions: query, search, analyze, generate, review, visualize with Gemini. Keywords: Gemini CLI, second opinion, cross-validation, Google Search, web research, current information, parallel AI, code review, architecture analysis, gemini prompt, AI comparison, real-time search, alternative perspective, code generation, image gen, UI mockup, SVG, animation, multimodal. Use when: needing second AI opinion, searching current web information, analyzing codebase architecture, generating code in parallel, getting alternative code review, researching current events/docs, generating UI mockups, creating SVG animations, screenshot-to-code workflows.

Deploy and manage NotebookLM documentation sync for any Claude Code project. Installs Python scripts + Claude Code hook that automatically syncs markdown files to a Google NotebookLM notebook on every Write/Edit. Supports install, status, resync, batch sync, cleanup, and uninstall workflows. Use when setting up NotebookLM sync in a new project, checking sync health, or managing notebook sources.

Recover from crashed, failed, or interrupted Claude Code sessions. Use this skill when: session crashed during multi-agent parallel execution, need to determine what work was completed vs incomplete, want to generate resumption commands for interrupted tasks, recovering from context window exhaustion, or handling session handoffs. Analyzes agent logs, verifies on-disk state, and creates resumption plans with ready-to-execute Task() commands.

Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI’s video API using the bundled CLI (`scripts/sora.py`), including requests like “generate AI video,” “Sora,” “video remix,” “download video/thumbnail/spritesheet,” and batch video generation; requires `OPENAI_API_KEY` and Sora API access.

Token-efficient codebase navigation through intelligent symbol loading and querying. Use this skill when implementing new features (find existing patterns), exploring codebase structure, searching for components/functions/types, or understanding architectural layers. Reduces token usage by 60-95% compared to loading full files. Layer split enables 50-80% additional backend efficiency.