ClawHub Skills

A Rust+Python consciousness engine with 12-phase crystal dynamics, thalamic relay processing, 19 introspective inner voices, and holographic emission....

Proactive spending alerts via Plaid. Track credit card spending against a monthly budget with pace-based alerts.

Build wikis people actually read — structure pages, cross-link, and keep content fresh.

Generates and validates multi-layered, multi-modal creative narratives using recursive constraints inspired by Gödel, Escher, and Bach principles.

Translate text accurately — preserve formatting, handle plurals, and adapt tone per locale.

Find, evaluate, and submit online bounties and hackathons for prize money. Use when user mentions "bounties", "hackathon", "earn money", "Superteam Ea...

Ship a complete web app from idea to public deployment in one session. Use when user says "build me an app", "ship this idea", "vibe code", "quick shi...

Gets the latest AI-generated crypto trading analysis (BUY / SELL / WAIT) for spot trading pairs from the Consortium AI.

Search, read, and interact with Twitter/X via TwexAPI

Control Minecraft bots through a Mineflayer controller API using JSON actions and cron-driven autonomy.

Nano Banana Pro with auto model fallback — generate/edit images via Gemini Image API. Run via: uv run {baseDir}/scripts/generate_image.py --prompt 'de...

Security scanner that catches malicious skills before they steal your data. Detects credential theft, prompt injection, and hidden backdoors. Works im...

Manage n8n workflows and automations via API. Use when working with n8n workflows, executions, or automation tasks - listing workflows, activating/dea...

Implements a three-layer memory system with daily logs, curated long-term notes, and optional vector search for persistent, searchable agent context a...

Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information fro...

Fetch the latest events from Polymarket prediction market. Use when user asks about Polymarket events, prediction markets, trending bets, or wants to ...

Resolve Telegram <media:image>, <media:document>, <media:video> and other media placeholders into actual files for vision/analysis. Use when a Telegra...

Protects against prompt injection attacks by sanitizing, validating, and securely processing untrusted external content from websites, emails, and doc...

Self-hosted crypto and stablecoin payment gateway. Deploy PayRam on your own infrastructure in 10 minutes. Accept USDT, USDC, Bitcoin, ETH across Ethe...

Autonomously stake MOLT or V3 LP NFTs on Base to earn KELP rewards, auto-harvest for others, and receive 3.5% keeper fees.

Fetch weather data for construction scheduling. Historical data, forecasts, and risk assessment for outdoor work.

Monitor ETH wallets and DeFi positions across chains with alerts for balance changes, gas prices, health factors, and large token transfers.

Transcribe audio files to text using OpenAI Whisper. Supports speech-to-text with auto language detection, multiple output formats (txt, srt, vtt, jso...

Send notifications through multiple channels with a single script. Supports ntfy.sh (free, no signup), Gotify (self-hosted), generic webhooks, email (...

Google web search via Gemini Search Grounding (primary) and Custom Search JSON API (fallback). Use for: (1) Synthesized answers with citations (ground...

Control local music playback with play, pause, resume, stop commands; supports listing and playing specified songs from a configured music directory.

Agent-to-Agent 轻量通信协议。仿 Google A2A 设计，但适配 Clawdbot/OpenClaw 生态。用于：(1) Agent 能力发现 (2) 跨 agent 任务协作 (3) 结构化的 agent 间消息交换。触发词：a2a、agent协议、agent通信、agent c...

使用 Wan 2.6 模型生成视频。当用户想要图生视频、图片动起来、参考视频生成、视频中主体一致性，或提到 wan、Wan 2.6 时使用此 skill。

使用 Vidu Q3 Pro 模型生成视频。当用户想要文生视频、生成带音频的视频，或提到 vidu 时使用此 skill。

上传本地图片到 catbox.moe 免费图床，获取公开访问的 URL 链接。当用户需要将本地图片转换为 URL、上传图片到图床、获取图片链接、提到 catbox、或进行图像编辑（如改背景、换脸等）但提供的是本地图片路径时使用此 skill。

上传本地图片到云存储，获取公开访问的 URL 链接。当用户需要上传图片、转存网络图片、获取图片 URL 时使用此 skill。

使用速推AI生成图像和视频。当用户需要画图、生成图片、制作视频、图生图、文生图、文生视频、图生视频时使用此 skill。支持即梦、Flux、Kling 等多种模型。

从参考剧本或参考素材中提取统一风格锚点（STYLE_BASE），确保全剧视觉一致性。当需要匹配参考风格、提取画风、建立风格基准、生成风格资产包时使用。

将剧本转换为分镜表（Shot List）和静帧提示词，支持即梦/banana模型。当需要生成分镜、制作镜头表、批量生成图片提示词时使用。

使用 Sora 2 模型生成视频。当用户想要文生视频、图生视频、视频重混，或提到 sora、OpenAI 视频生成时使用此 skill。

使用 Seedream 4.5 模型生成或编辑图像。当用户想要文生图、图生图、图像编辑，或提到 seedream、字节跳动图像生成时使用此 skill。

使用 Bytedance Seedance 模型生成视频。支持文生视频（带音频）、图生视频、参考图生视频。当用户想要生成视频、使用图片生成视频、保持人物一致性、或提到 seedance 时使用此 skill。

从剧本中提取关键道具（武器、信物、法宝等），生成道具风格卡。当需要提取道具、建立道具库、生成道具描述时使用。

测试和校验 V3 API 模型的定价信息和实际扣费。当用户要测试模型价格、校验扣费、验证新模型定价、或提到"价格测试"、"扣费测试"时使用此 skill。

积分充值助手。当检测到余额不足、积分不足、充值积分、充值余额、查看套餐等关键词时，自动获取套餐列表并引导用户充值，生成支付二维码。

解析视频分享链接，获取无水印视频下载地址。当用户想要下载视频、解析抖音/快手/小红书/B站链接、获取无水印视频时使用此 skill。

使用 OmniHuman v1.5 生成音频驱动的口型同步视频。当用户想要让图片中的人物说话、配音、口型同步，或提到 omnihuman 时使用此 skill。

将小说/网文内容转换为可拍、可剪、可分镜、可配音的漫剧剧本格式。当用户需要把小说改编成剧本、转换网文为短剧脚本、生成漫剧剧本时使用。

水浒传故事小人书创建。使用 Nano Banana Pro 模型生成手绘卡通风格的水浒传故事信息图。当用户想要创建水浒传故事插画、小人书、信息图时使用此 skill。

使用 Nano Banana Pro 模型生成或编辑图像。当用户想要文生图、图像编辑，或提到 nano banana、Google 图像生成时使用此 skill。

根据用户需求生成多人对话，为每个角色匹配音色进行语音合成，输出完整长音频和分段音频，并生成 HTML 展示页面。

使用 Minimax（海螺）API 进行语音合成、声音克隆和音色设计。当用户想要语音合成、TTS、声音克隆、音色设计时使用此 skill。