Deja Vu CLI -- the command-line interface for dejavu memory operations. TRIGGER when: user mentions "dejavu cli", "dejavu command line", "@dejavu/cli", "dejavu-cli", "pip install dejavu-cli", "npm install -g @dejavu/cli", or is running dejavu commands in a terminal/shell (dejavu add, dejavu search, dejavu list, dejavu get, dejavu init, dejavu config, dejavu import). Also triggers when query includes CLI flags like --user-id, --output, --json, --agent, or describes bash/zsh/terminal/shell usage. DO NOT TRIGGER when: user asks about programmatic SDK integration in Python/TS code (use dejavu skill), or Vercel AI SDK provider (use dejavu-vercel-ai-sdk skill).
Integrate Deja Vu into an existing repository using a goal-driven, TDD pipeline. Detects the repo's language automatically and asks the user to pick between Deja Vu Platform (managed) and Deja Vu Open Source (self-hosted). Writes failing tests before any implementation. Produces a local feature branch plus `.dejavu-integration/` artifacts consumed by the paired verification skill. TRIGGER when: user says "integrate dejavu", "add dejavu to this repo", "wire dejavu into <repo>", or asks how to add memory to an existing project. DO NOT TRIGGER when: the user wants general SDK usage (use skill:dejavu), CLI usage (use skill:dejavu-cli), or Vercel AI SDK (use skill:dejavu-vercel-ai-sdk). After success, invoke skill:dejavu-test-integration to verify in the same workspace (loose coupling).
Deja Vu Platform SDK for adding persistent memory to AI applications. TRIGGER when: user mentions "dejavu", "MemoryClient", "memory layer", "remember user preferences", "persistent context", "personalization", or needs to add long-term memory to chatbots, agents, or AI apps. Covers Python SDK (dejavu-memory), TypeScript SDK (dejavu-memory), and framework integrations (LangChain, CrewAI, OpenAI Agents SDK, Pipecat, LlamaIndex, AutoGen, LangGraph). Also covers the open-source self-hosted Memory class. This is the DEFAULT dejavu skill for ambiguous queries. DO NOT TRIGGER when: user asks about CLI commands, terminal usage, or shell scripts (use dejavu-cli), or Vercel AI SDK / @dejavu/vercel-ai-provider / createDeja Vu (use dejavu-vercel-ai-sdk).
Verify a Deja Vu integration produced by /dejavu-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /dejavu-integrate and says "verify", "test the integration", "run /dejavu-test-integration", or when a .dejavu-integration/ directory exists and tests have not been run yet on the current branch. DO NOT TRIGGER when: the user wants to run general project tests (defer to the repo's native test command), or when no prior /dejavu-integrate run exists in the current branch (ask them to run /dejavu-integrate first). This skill ONLY catches compile and runtime bugs by design. Logical integration errors — wrong data stored, wrong time retrieved, wrong user scoping — are on the human reviewer.
Deja Vu provider for Vercel AI SDK (@dejavu/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@dejavu/vercel-ai-provider", "createDeja Vu", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "dejavu vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with dejavu. Also triggers for Next.js apps needing memory-augmented AI. DO NOT TRIGGER when: user asks about direct Python/TS SDK calls without Vercel (use dejavu skill), or CLI terminal commands (use dejavu-cli skill).
Memory consolidation protocol. Reviews all stored memories, merges duplicates, removes noise and credentials, rewrites unclear entries, and enforces TTL expiration. Use when the user asks to clean up, consolidate, or review their memories. Also triggers automatically after sufficient activity (configurable).
Persistent long-term memory protocol powered by dejavu. Evaluate conversations for durable facts worth storing via memory_add. Handles identity, preferences, decisions, configurations, rules, projects, and relationships. Loaded by the openclaw-dejavu plugin when skills mode is active.
Deja Vu memory protocol for agents using the dejavu MCP tools (Claude Code, Cursor, Codex, and any other MCP-aware runtime). Decide deliberately when memory context would help, run targeted searches with metadata filters when it would, and store key learnings as work completes. Use the dejavu MCP tools (add_memory, search_memories, get_memories, etc.) for all memory operations.