Loading...
Loading...
Found 34 Skills
A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks.
Operate and evolve agent-memory-workbench with replay-first memory, minimal JSON edits, and a strict two-branch policy (normal + human-verification).
INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.
Resume the most recent agent session for the current working directory. Use when the user says "where were we", "resume", "handoff", "pick up where I left off", or starts a session with no fresh context.
Create and configure AI agents, upload files for RAG, manage MCP servers, and handle agent memories using the Cargo CLI. Use when the user wants to create or update agents, upload knowledge base files, connect MCP tool servers, or manage agent memories. For sending messages to agents, use the cargo-orchestration skill instead.
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool use, function calling.
Enables continuous self-improvement through learning from failures, user corrections, and capability gaps. Integrates with QAVR for learned memory ranking.
End-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (CLAUDE.md, README.md, docs/) and agent memory against the code so nothing rots. OCD-level review and synchronization of project documents and agent memory after a session. MUST trigger when the user says: "sync up", "tidy up docs", "update memory", "clean up docs", "/sync", "/neat", "sync up", "tidy up docs", "tidy up", "update memory", "organize", "wrap up", "this phase is done", "newcomers can start directly", or any phrase suggesting a development milestone where knowledge needs reconciliation. Also trigger when the user reports stale docs, conflicting memories, or wants a clean handoff to teammates or other agents. A standalone "tidy" with prior development context counts — do not under-trigger. Cross-platform: works on Claude Code, OpenAI Codex, OpenCode, and OpenClaw.
The agentmemory plugin hooks that capture observations automatically across the agent session lifecycle. Use when explaining how memory gets captured without manual saves, when debugging missing observations, or when tuning what gets recorded.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Observe user interaction patterns, extract per-session facets, update a dual-matrix soul state, and periodically synthesize a personalized Soul profile for better collaboration.
Full-stack hybrid memory system with vector + keyword search. Stores embeddings in SQLite with FTS5 for BM25 keyword search and cosine similarity. Enables semantic memory recall for agents.