All Skills

INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph, LangSmith, or Deep Agents. Covers required packages, minimum versions, environment requirements, versioning best practices, and common community tool packages for both Python and TypeScript.

Automate Drip Jobs tasks via Rube MCP (Composio). Always search tools first for current schemas.

Automate Dreamstudio tasks via Rube MCP (Composio). Always search tools first for current schemas.

Orchestrates test planning pipeline (research → manual → auto tests). Coordinates ln-521, ln-522, ln-523. Invoked by ln-500-story-quality-gate.

Systematic code review protocol — review code with rigor and specificity. Use this skill whenever the user asks you to review code, check a PR, audit a file, look over changes, or give feedback on implementation quality. Also use when they say 'review this', 'is this code good', 'check my work', 'what do you think of this implementation', or 'any issues with this'. Covers correctness, security, readability, performance, maintainability, and testing.

READ this skill when designing or planning any game system architecture — including combat, skills, AI, UI, multiplayer, narrative, or scene systems. Contains paradigm selection guides (DDD / Data-Driven / Prototype), system-specific design references, and mixing strategies. Works as a domain knowledge plugin alongside workflow skills (OpenSpec, SpecKit) or plan mode of an agent.

Use when implementing any feature or bugfix in the Culinary Advisor Next.js project - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

Analyzes ongoing work patterns and the existing agent/skill roster to suggest creating new agents or skills for specialized or repetitive tasks. Continuously monitors what tasks are being done repeatedly or where specialist knowledge would help. Avoids recommending duplicates.

INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).

Worker that runs parallel external agent reviews (Codex + Gemini) on code changes. Background tasks, process-as-arrive, critical verification with debate. Returns filtered suggestions with confidence scoring.

Technical architecture review agent for execution plans. Uses cto-advisor skill to evaluate technical decisions, architecture patterns, tech debt implications, and technology choices in plan.md. Triggered by: 'review technical plan', 'cto review', 'architecture review', or automatically during Step 2 (Evaluate Plan) for tracks involving architecture decisions, integrations, or infrastructure changes.

Design habit-forming product loops using the Hook Model (Trigger, Action, Variable Reward, Investment). Use when the user mentions "users aren''t coming back", "engagement loops", "habit formation", "push notifications", or "variable rewards". Covers ethics evaluation and onboarding for habits. For friction reduction and B=MAP, see improve-retention. For viral sharing, see contagious.

Automate Doppler Marketing Automation tasks via Rube MCP (Composio). Always search tools first for current schemas.

Automate Echtpost tasks via Rube MCP (Composio). Always search tools first for current schemas.

Diagnose and fix retention problems using behavior design (B=MAP). Use when the user mentions "users drop off", "activation rate", "onboarding friction", "retention metrics", or "why users don''t complete". Covers the Ability Chain, prompt design, and tiny behaviors that compound. For habit loops and variable rewards, see hooked-ux. For intrinsic motivation, see drive-motivation.

INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod.

Worker that runs existing tests to catch regressions. Auto-detects framework, reports pass/fail. No status changes or task creation.

INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval/validation workflows, and the 4-tier error handling strategy.

Apply the six principles of ethical persuasion (reciprocity, commitment, social proof, authority, liking, scarcity) to product design, copy, and sales. Use when the user mentions "social proof", "persuasive copy", "why users don''t convert", or "ethical persuasion". For deal negotiation tactics, see negotiation. For viral word-of-mouth, see contagious.

Configure PyInstaller for Python binary builds with spec files and bundling options.

Transform research findings into actionable implementation plans with stakes-based rigor, test-first strategy, and granular task decomposition.

Bootstrap-Vue design spec for Stitch. Outputs hard-constraints prefix or selector JSON and assembled prompt.

Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling.

INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread_id, time travel, Store, and subgraph persistence modes.