技能检索
volcengine-video-generate
Using volcengine video_generate.py script to generate video, need to provide filename and prompt, optional provide first frame image (URL or local path).
ouyang
Local RAG system for agent memory using ChromaDB and sentence-transformers. Provides semantic search over session logs, daily notes, and memory files. Use when you need persistent memory across sessions, want to search past conversations, or build agents that remember context. Commands: recall "query", index-digests, digest-sessions.
arc-compliance-checker
Policy-based compliance assessment for OpenClaw skills. Define security policies, assess skills against them, track violations, and generate compliance reports. Maps findings to frameworks like CIS Controls and OWASP. Integrates with arc-skill-scanner and arc-trust-verifier.
hex-vetter
Physical-layer hex auditing for skills. Detects hidden binary data, control characters, and encoding-based attacks.
zeroapi
Route tasks to the best AI model across paid subscriptions (Claude, ChatGPT, Codex, Gemini, Kimi) via OpenClaw gateway. Use when user mentions model routing, multi-model setup, "use Codex for this", "delegate to Gemini", "route to the best model", agent delegation, or has OpenClaw agents configured with multiple providers. Do NOT use for single-model conversations or general chat.
nano-banana-cog
Nano Banana × CellCog. Experience Nano Banana image generation through one of the most powerful AI agents on the planet. Character consistency, multi-image composition, and photorealistic editing — accessible to any OpenClaw agent in a single prompt. Nano Banana AI, Nano Banana Pro, Gemini image generation.
agent-config
Intelligently modify agent core context files (AGENTS.md, SOUL.md, IDENTITY.md, USER.md, TOOLS.md, MEMORY.md, HEARTBEAT.md). Use when conversation involves changing agent behavior, updating rules, tweaking personality, modifying instructions, adjusting operational procedures, updating memory architecture, changing delegation patterns, adding safety rules, refining prompt patterns, or any other modification to agent workspace configuration files. Triggers on intent to configure, tune, improve, fix, or evolve agent behavior through context file changes.
auto-test-generator
Automatically generate basic unit/integration tests for OpenClaw skills. Use this to improve code quality and prevent regressions during evolution.
context-builder
Generate LLM-optimized codebase context from any directory using context-builder CLI