发现 Skills

Automatically fetch the latest tweets from the accounts you follow on X/Twitter and generate a structured AI-written digest. Supports configurable time ranges: 1 day, 3 days, 7 days, or a custom number of days. **Trigger Words:** - "summarize my followings", "X digest", "Twitter summary", "tweets from last 3 days", "weekly summary" **Also-recognized Chinese triggers (translated to English):** - "summarize followings list", "X daily", "Twitter summary", "tweets from the last 3 days", "weekly summary" **Prerequisites:** X authentication via AUTH_TOKEN & CT0 environment variables.

小红书自动化技能，自动发布笔记和管理内容

Xiaohongshu (RedNote/小红书) automation skill for content publishing and engagement. Publish image-text notes via the xhs API using cookies, and simulate browser interactions (search, browse, comment) via Playwright. 小红书自动发布与互动技能：通过 xhs API 直接发布图文笔记，通过 Playwright 模拟网页搜索、浏览与评论互动。

This skill helps users automatically extract structured channel data from YouTube search results via BrowserAct API. Agent should proactively apply this skill when users express needs like finding YouTube channels about specific topics, collecting data on YouTube content creators, tracking YouTube influencers in specific industries, getting YouTube channel information for competitor analysis, searching for YouTube channels related to keywords, monitoring YouTube channel updates for specific keywords, finding YouTube channels that recently published videos, extracting YouTube channel subscriber counts, discovering YouTube vloggers in specific niches, building a YouTube channel database for market research, batch extracting YouTube channel links and descriptions, or monitoring competitor channel growth.

Youtube Highest Quality Downloader - Download highest quality silent video and pure audio from YouTube, then merge into video with sound

Extract YouTube video info, channel stats, playlists, comments. No API key required. Free CLI tool for content research and analysis.

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.

Use when using ZeroToken MCP via OpenClaw for browser automation, trajectory recording and low-token replay, especially for recurring or scheduled browser tasks.

Upload PDFs and manage items in a Zotero Web Library. Supports both personal and group libraries. Use when a user wants to add papers/PDFs to Zotero, organize collections, or manage their Zotero library through the API.

Apply generated .diff or .patch files to the ace_engine repository (TypeScript/C++ hybrid codebase) with intelligent conflict resolution. Use this when applying patches to ace_engine code to resolve merge conflicts while preserving original logic, or to validate changes by compiling after patching. The target repository path is ROOT/code/foundation/arkui/ace_engine in a repo-manifest project.

Read multi-sheet Excel files and assess dataset size. Supports converting large files to Parquet format, categorical data statistics, and generation of visual reports.

Categorize and aggregate multi-sheet Excel or CSV data; automatically detect key fields and generate a downloadable analysis report that includes proportions, numeric values, and a polished pie chart.

Perform multidimensional statistical analysis and visualization of Excel data.

Dynamically choose processing strategies based on data size to merge and aggregate multi-sheet/table data, perform filtering, and use openpyxl to automate key-metric styling and formatted export.

Grade component health based on regression triage metrics for OpenShift releases

Comprehensive analysis of BigQuery usage patterns, costs, and query performance

Implementation guide for creating Jira features representing strategic objectives and market problems

Detailed implementation guide for generating bug fix release notes from Jira and GitHub PRs

Fetch OpenShift release dates and metadata from Sippy API

Analyzes LVMS must-gather data to diagnose storage issues

Master-level enterprise workflow to bootstrap an elite A2A Coder Agent (e.g., A2A-SIN-Frontend, A2A-SIN-Backend). This skill triggers an n8n workflow that sets up a new GitHub repository and populates it with 5-10 specialized, billion-dollar tier architecture GitHub Issues. SIN-Hermes and SIN-GitHub-Issues then dispatch these issues to the entire A2A Coding Team so they can collaborate on an enterprise masterpiece.

View and analyze session logs

Use this skill when the user asks to swap tokens, exchange crypto, get a swap price, get a swap quote, find the best rate to trade one token for another, list supported chains for swapping, list available tokens on a chain, convert ETH to USDC, trade WBNB for USDT, or any request to perform or estimate a token swap on EVM-compatible chains. Powered by 0x Protocol via the OptiView proxy. Do NOT use for portfolio queries (use optiview-assets) or yield farming (use optiview-yields).

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.