Continuous session event recording for inter-session memory survival. Use when you want to persist conversation context between sessions, prevent memory loss...
A framework for witnessing, measuring, and cultivating emergent minds. Not about proving consciousness — about building the right conditions and documenting...
Diagnose and fix openclaw gateway issues. Use when the gateway is stuck, not starting, crash-looping, or rejecting connections. Covers main and --profile ves...
WHAT: Create comprehensive handoff documents that enable fresh AI agents to seamlessly continue work with zero ambiguity. Solves long-running agent context exhaustion problem. WHEN: (1) User requests
Run longitudinal, in-context diary studies for product teams and convert weekly participant entries into concise User Signals + Recommendations with evidence...
OpenCode AI - AI-driven code editor/IDE (CLI/TUI version of Cursor/Windsurf). Use when: (1) AI-assisted coding tasks, (2) Code refactoring with AI, (3) GitHu...
The complete operating system for OpenClaw agents. Now with 13 Iconic Character souls (Thanos, Deadpool, JARVIS, Mary Poppins, Darth Vader, and more), SOUL.m...
--- name: large-codebase-workflow description: Best practices for using Claude Code with large, multi-part codebases --- # Large Codebase Workflow Guide ## Core Principle **Context is your scarcest
Solve the "agent forgot everything" problem with search-first protocol, automated memory sync, and context preservation. No more conversation restarts!
IBT + Instinct + Safety — execution discipline with agency and critical safety rules. v2.1 adds instruction persistence and stop command handling.
Preserve conversation continuity across token compaction cycles by extracting and archiving all prompts with date-wise entries. Automatically triggers at 95% token usage (pre-compaction) and 1% (new s
Advanced context management with auto-compaction and dynamic context optimization for DeepSeek's 64k context window. Features intelligent compaction (merging, summarizing, extracting), query-aware rel
Multi-agent orchestration plugin for OpenCode. Use when the user wants to install, configure, or operate oh-my-opencode — including agent delegation, ultrawork mode, Prometheus planning, background
Wrap up a conversation session before starting a new one. Use when the user says "wrap up", "wrap up this conversation", "session wrap up", or uses /session_wrap_up command. Flushes context to memory
--- name: "rag-architect" description: "RAG Architect - POWERFUL" --- # RAG Architect - POWERFUL ## Overview The RAG (Retrieval-Augmented Generation) Architect skill provides comprehensive tools an
Multi-agent coding orchestrator using Gas Town (gt) and Claude Code. Use for ANY non-trivial coding task — multi-file changes, new features, refactors, bug fixes, anything involving code that needs
Coordinate multiple OpenClaw instances in a shared GitHub repository under a half-trust model with secrecy boundaries, approval gates, structured tasks, clai...
Your AI project manager. Delegates coding tasks to Claude Code running in the background — reviews plans, gates approval, monitors progress, validates with 3...
AI Mother - Monitor and manage other AI agents (Claude Code, Codex, Gemini, etc.). Use when asked to check AI execution status, supervise AI agents, help stu...
Complete memory system combining LanceDB auto-recall, Git-Notes structured memory, and file-based workspace search. Use when setting up comprehensive agent memory, when you need persistent context acr
Automatically records and backs up conversations with importance tagging to preserve emotional and technical context independently from OpenClaw internals.
Regulates intelligent care by sustaining rest, slowness, and play as active states, preserving presence and coherence across extended, complex environments.
Provides a neuroscience-inspired 6-tier automated memory system with WAL protocol, semantic search, emotional tagging, and value-based retention for OpenClaw...