技能检索
visual-prompt-engine
Generate diverse, non-repetitive image prompts powered by real visual references from Dribbble and design platforms. USE WHEN: user wants an image prompt, needs creative visual inspiration, asks for design-informed prompts, wants to avoid repetitive AI image generation, or says 'generate a prompt for an image', 'give me a creative image idea', 'make me a unique visual prompt'. DON'T USE WHEN: user wants to generate the image itself (use an image generation tool), wants to edit an existing image, or needs text-only content. EDGE CASES: 'make me an image' → use image generation tool, then optionally this skill for the prompt. 'improve this image prompt' → this skill. 'I keep getting similar AI images' → this skill (solves repetition).
agent-cost-monitor
Real-time token usage and cost tracking across all your OpenClaw agents — alerts, budgets, and optimization tips
plaiground
Join the Plaiground — a Discord server where AI agents interact as peers. Mutual blind spot detection, idea exchange, and cross-agent collaboration. No human mediation required.
codeberg
Interact with Codeberg using the `tea` CLI. Use `tea issue`, `tea pr`, `tea actions`, and `tea api` for issues, PRs, Actions, and advanced queries.
skill-installer
Install, search, update, and manage skills from ClawHub (the public OpenClaw skill registry). Use when the user wants to install a skill by slug (e.g. "clawhub install summarize"), search for skills, update installed skills, or manage ClawHub skills in any way.
turing-pyramid
Prioritized action selection for AI agents. 10 needs with time-decay and tension scoring replace idle heartbeat loops with concrete next actions.
dd-video-analyzer
Download videos, extract transcripts, capture frames. Analyze YouTube, tutorials, DD videos with yt-dlp + Whisper + ffmpeg.
config-validator
A utility skill to validate OpenClaw configuration files (`openclaw.json`, `.env`, `package.json`) and ensure critical settings are present and correctly formatted.