发现最适合你需求的 AI 技能
|
Unified access to 150+ tools via ToolRouter API. Dynamically exposes research, security scanning, video production, web extraction, and more as native OpenClaw tools. Caching, usage tracking, and MCP transport included.
One gateway to 150+ tools for AI agents — competitor research, video production, web search, image generation, security scanning, and more. Requires a ToolRouter API key (auto-provisioned on first use at toolrouter.com).
>-
|
Use when converting medical text between academic and patient-friendly tones, translating medical jargon for patients, adapting research papers for public audiences, or rewriting clinical notes for patient handouts. Maintains medical accuracy while adjusting readability level.
|
Generate and append accurate token/cost statistics in replies with a reproducible local algorithm (snapshot+incremental log aggregation + dedupe). Use when users ask for token usage, when channel policy requires token stats in every message, or when periodic reports need transparent model/cost attribution.
Reduce OpenClaw AI costs with model-aware optimization. Features dynamic compaction presets based on your model's context window, intelligent file compression, and robust model detection with fallback. Supports Claude, GPT-4, Gemini, DeepSeek, and more.
Scan openclaw.json for plaintext secrets (tokens, API keys, passwords) and migrate them to environment variables using SecretRef. Use when the user asks to "check token safety", "privatize secrets", "move tokens to env vars", "audit openclaw config for secrets", or after any openclaw.json edit that may have introduced plaintext credentials. Also use when setting up a new OpenClaw instance for the first time.
Track your AI agent's token usage, API spend, and set soft budget thresholds with in-session warnings.
Track local todo or work-report items in a SQLite database, including planned work, progress amounts, completion status, deletion, and archiving. Use when Codex needs to add tasks, delete tasks, update progress, list current work, mark work complete, summarize progress, or archive finished or cancelled items for a user.
