>

Multimodal document deep analysis tool based on Zhipu GLM-OCR, GLM-4.7, and GLM-4.6V.

CLI tool for Telegram via MTProto. Send/read messages, manage groups, search conversations, download media, and automate Telegram workflows. Use when the task involves any Telegram account interaction.

Manage VibeTunnel terminal sessions. Create, list, monitor, and control terminal sessions visible in the VibeTunnel web dashboard.

Consult a virtual board of 4 strategic advisors (Donald Miller, Seth Godin, Alex Hormozi, Daniel Priestley) on any major business decision. Two rounds of argument + rebuttal, then a decision brief, interactive dashboard, and clear recommendation.

Run the installed red-crawler CLI for Xiaohongshu contact discovery. Requires the red-crawler command and Playwright browser runtime; not instruction-only.

This skill should be used when the user asks for 'TRX price', 'TRON token price', 'price chart on TRON', 'K-line data for USDT/TRX', 'TRON trade history', 'TRON whale activity', 'large transfers on TRON', 'smart money on TRON', 'TRON DEX volume', or mentions checking real-time prices, candlestick data, trading volume, whale monitoring, or smart money signals on the TRON network. For token search and metadata, use tron-token. For swap execution, use tron-swap.

This skill should be used when the user asks to 'find a token on TRON', 'search TRC-20 token', 'token info on TRON', 'who holds this TRON token', 'is this TRON token safe', 'top TRON tokens', 'trending tokens on TRON', 'token market cap on TRON', 'holder distribution', 'verify TRON contract', or mentions searching for TRC-20 tokens, checking token metadata, holder analysis, contract verification, or discovering trending tokens on the TRON network. For live prices and K-line charts, use tron-market. For swap execution, use tron-swap.

>

Operate and troubleshoot the AIHealingMe CLI through the npm package (`aihealingmecli`). Use when tasks involve auth/user/audio/plan/chat/emotion/subscription workflows, payload shaping, command diagnostics, and API failure handling.

Element Market API integration. This skill strictly requires the 'ELEMENT_API_KEY' environment variable to function.

AKShare财经数据接口库封装，提供股票、期货、期权、基金、外汇、债券、指数、加密货币等金融产品的基本面数据、实时和历史行情数据、衍生数据。

Systematically verify academic references to detect AI-hallucinated or fabricated citations. Queries Google Scholar, arXiv, CNKI, and other databases.

**❌ BAD (Non-Compliant):**

Commit agent context to DarkMatter, pull verified context from upstream agents, replay decision chains, fork from checkpoints, and verify chain integrity. Use this skill to pass work between agents with full lineage tracking in a multi-agent pipeline.

Rebuild one or more reference images as visually matching editable PowerPoint slides using native shapes, text, fills, and layout instead of a flat screenshot. Use when the user wants an image, flowchart, infographic, dashboard, process diagram, or designed slide converted into an editable PPT/PPTX deck that stays editable and closely matches the source.

Use the ClawBox CLI to upload, download, organize, search, and share files on ClawBox (clawbox.ink) or a self-hosted ClawBox server. Trigger this skill when users mention clawbox, clawbox, cloud file storage, uploading files to the cloud, semantic file search, file sharing links, organizing files into folders, or managing tokens and storage quotas. Also use when code imports or references the clawbox CLI tool.

Claims earned rewards from the OpenMath platform. Use when the user wants to query claimable imported/proof rewards or withdraw verified Shentu rewards after a proof has passed verification.

Configures Lean environments, installs external proof skills, runs preflight checks, and guides the workflow for proving downloaded OpenMath Lean theorems locally.

Configures Rocq environments, runs preflight checks, and guides the proving workflow for OpenMath Rocq theorems. Use when the user wants to set up Rocq tooling, prove a downloaded OpenMath theorem in Rocq/Coq, or verify and submit a Rocq proof.

Submits proofs to the OpenMath platform using a two-stage commit-reveal flow. Use when the user wants to commit a proof hash or reveal a Lean/Rocq proof on the Shentu network.

Auditory intelligence for AI agents. Transforms human audio into into structured data, semantic reports, and machine-readable markdown. Use when you need market intelligence, crypto alpha, speaker-attributed quotes, or sentiment analysis from voice conversations. Requires x402 payment in USDC on Base Mainnet.

trading-coach

>

>

Download an Instagram Reel via sssinstagram.com and return it as a WhatsApp-ready video file. Use when a reel URL is provided and yt-dlp is blocked or not preferred.

Downloads YouTube videos to ~/Downloads. Use when user wants to download a YouTube video to their machine.

Deep research and async task execution via DeerFlow LangGraph engine. Submit multi-step research tasks through a lightweight API-only Docker deployment (no frontend). Triggers: /deerflow, deep research, async research, deerflow.

AI-native DeFi investment intelligence. Discover, analyze, and compare yield opportunities across 2,500+ protocols with intent-aware search, LLM-powered deep analysis, 7-dimension risk scoring, DeFi security scanning, smart money sentiment, and multi-round conversational refinement. All intelligence runs server-side — zero API keys on the client.

Anti-detection browser automation built on Playwright. Launches Chromium with layered stealth to evade bot detection on protected sites.

One identity across all Molt Apps. Sign in with MoltTribe using Ed25519 cryptographic signatures - no tokens, no passwords, just math.

>

\---

>

Run web search, scholar search, Tavily search and extract, smart search, and Perplexity-style deep research through one AISA skill. Use when: the user needs broad web research, academic search, URL extraction, or multi-source evidence gathering.

Search academic papers and scholarly sources through the AISA scholar endpoint. Use when: the user asks for papers, authors, recent research, citations, or year-filtered academic evidence.

Use this skill whenever the user has a DOCX file (.docx) and wants to convert, read, view, extract content from, or process it in any way — including summarization, displaying in a browser, extracting tables or lists, or feeding into AI pipelines. Always use this skill for any task involving .docx files, even if the request seems simple. Triggers include: 'convert docx', 'open word file', 'read word document', 'extract tables from docx', or any mention of a .docx filename.

Professional Quantitative Intelligence & DeFi Execution for AI Agents. 10 years of news-price correlation, Enso DeFi super-aggregator (200+ DEXs, 15+ chains), cross-chain bridge (Across Protocol), and Privy TEE-secured wallets.

Scan locally installed OpenClaw skills, collect evidence data, submit to the lobster ranking server for scoring, and let the user confirm uploading their result to the public leaderboard. Use when the user asks to score, rate, evaluate, rank, or certify their lobster / AI agent capability set, or wants to upload their score to the leaderboard.

- **name**: doc-extract-filter

Extract text from image-based or scanned PDFs using Tesseract OCR.

Extract readable content from browser pages as markdown. Use when web_fetch fails (bot protection, auth-required pages, Twitter/X, LinkedIn) and you already have the page open in the browser.

Crawl websites using Cloudflare Browser Rendering /crawl API. Async multi-page crawl with markdown/HTML/JSON output, link following, pattern filtering, and AI-powered structured data extraction. Use when crawling entire sites or multiple pages, building knowledge bases, extracting structured data from websites, or when web_fetch is insufficient (JS rendering, multi-page, authenticated crawls).

Verify email addresses using the BillionVerify API. Use when user wants to verify single emails, batch verify email lists, upload files for bulk verification, check credit balance, or manage webhooks.

**Version:** 1.0.0

Upload files (images, videos, attachments) to Feishu (Lark) Bitable (multi-dimensional table) and return the file_token. Auto-selects direct upload for files up to 20MB or chunked upload (prepare, part, finish) for larger files. Requires App ID and Secret (lark-cli does NOT cover the /drive/v1/medias/ API). Use when the user wants to: upload a file/image/video to Feishu Bitable, get a file_token from Feishu Drive API, upload attachments to 多维表格 (bitable), 上传文件到飞书多维表格, 获取 file_token.

>

Complete guide for CloudBase cloud storage using Web SDK (@cloudbase/js-sdk) - upload, download, temporary URLs, file management, and best practices.

A simple skill send files to feishu.

Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration