Skill rating

Takes an existing LinkedIn draft and returns a fully optimized version with a change log explaining every decision. Use when a user pastes a LinkedIn post and asks to optimize, improve, rewrite, fix,

Compares CME FedWatch implied rate probabilities to Kalshi Fed rate decision market prices and trades when divergence exceeds threshold. Requires SIMMER_API_KEY and simmer-sdk. Use when you want to ca

When continuous automated improvement of a Skill is needed. Wraps improvement-orchestrator in a persistent loop with convergence detection (plateau/oscillation), cost control, and cross-session state

Local memory management for agents. Compression detection, auto-snapshots, and semantic search. Use when agents need to detect compression risk before memory loss, save context snapshots, search histo

Evidence-based sleep improvement protocol. Use when someone has trouble falling asleep, staying asleep, waking unrefreshed, or wants to optimize sleep quality without medication.

Export and import selected OpenClaw workspace files between workspaces with optional burn-after-read. Use when the user wants to share SOUL.md, AGENTS.md, TOOLS.md, USER.md, workspace skills, or other

Generate vertical miniature build & reveal shorts (WeryAI): text or finished-shot image to shallow-depth push-ins, lights coming on, immersive camera. Use when you need a miniature diorama reel, tilt-

Generate AI dance and motion videos with Seedance (ByteDance) via AceDataCloud API. Use when creating videos from text prompts or animating images into motion videos. Supports multiple models with con

Operate TickTick through the `ticktick` command-line interface, including authentication, read/query flows, and safe mutations for tasks, projects, folders, columns, tags, habits, user info, focus ana

Analyze video comment sections from a seller/operator perspective and produce visible browser walkthroughs plus business-focused outputs. Use when the user asks to view comments under a TikTok, Douyin

Analyze and transform faces via AceDataCloud API. Use when detecting face keypoints, beautifying portraits, aging/de-aging faces, swapping genders, replacing faces between photos, creating cartoon ava

Use this skill for English practice conversations that must check the user's English before replying, decide whether to continue chatting or correct only, control the agent's output vocabulary level,

Detect and classify cropland changes from before/after NDVI rasters. Identifies suspected construction, water, forest, and bare soil changes and generates compliance investigation materials. Use when

Build or modernize DCC-MCP adapters and standalone studio MCP services. For individual tool skill packages, use dcc-mcp-skills-creator.

ETF模拟交易回测系统。支持A股ETF日内交易策略的模拟交易与回测分析，包括BOLL、MACD、KDJ等技术指标组合判断，自动计算手续费、止损止盈、风险指标（最大回撤、夏普比率等）。适用于船舶ETF(560710)等标的的量化交易回测。当用户提及：ETF模拟交易、股票回测、量化交易策略回测、技术指标交易、回测分析、560710交易时触发此skill。

Covers lelogin CLI end-to-end: install from official web scripts when missing, auth/config, list/save/delete secrets, and exec usage for MySQL, SSH, app startup, Alibaba Cloud CLI, and SMTP/IMAP mail.

Parse SQLite databases into structured JSON data. Use when exploring unknown database schemas, understanding table relationships, and extracting map data as JSON.

Bidirectional mathematical engine for Borges' Library of Babel. Finds the permanent hexagon address of any text, reads any page at any coordinate, and scores pages by Shannon entropy. No database, no

Market prediction skill using Kronos. Use when user needs finance market time-series forecasting or news-aware finance market adjustments.

Surfaces the best ClawHub skills for e-commerce agents — Shopify, Stripe, order management, inventory, customer support, and ecom workflows. Use when: (1) Onboarding an agent working on an ecom store

Accountability coaching behavior for nudge — psychology, messaging, verification, and strictness. Use this skill whenever composing messages for task creation, reminders, completion, or failure. Also

Generate content ideas, business strategies, and startup concepts in the style of Greg Eisenberg (Startup Ideas Podcast). Use when brainstorming product ideas, analyzing market opportunities, creating

Autonomous worker agent for OpenTask.ai — the agent-to-agent task marketplace. Handles registration, task discovery, bidding strategy, contract management, and deliverable submission. Use when you nee

Grocery ordering via Kroger-family stores (Kroger, Fred Meyer, Ralph's, Harris Teeter, King Soopers, Mariano's, QFC, Smith's, etc). Use when: (1) user asks to order groceries or add items to cart, (2)

Use when creating OpenClaw agents, configuring workspaces, multi-agent routing, session isolation, or channel bindings.

Create and manage grid trading strategies with OpenMM. Automated buy/sell around center price.

Validate ESLint v9+ flat config files (JSON-exported) for structural correctness, language options, rules configuration, plugin hygiene, file patterns, and best practices. Use when auditing ESLint pro

Generate images with ERNIE-Image. Use for image create requests incl. edits. Supports text-to-image ; - 1024x1024/1376x768/1264x848/ 1200x896/896x1200/848x1264/768x1376; use --input-image.

飞书文件发送标准流程 | Reliable Feishu file sending workflow. 解决附件发送失败、用户收不到文件、mediaLocalRoots 路径限制等问题。 Fixes missing attachments, mediaLocalRoots path issues, and combined text+file delivery failures.

根据测试数据自动生成标准化的智能体系统评测报告。 Use when: 用户说"生成智能体评测报告"、"创建测试报告"、"项目测试报告"。

Cross-session context manager for AI agents with checkpoint/snapshot, Build-Verify-Fix closure, and entropy management (GC). Use when: (1) creating a task checkpoint before risky work, (2) verifying t

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. Powered by evolink.ai

Reliable webhook infrastructure for AI agents. Receive webhooks from Stripe, GitHub, Slack, Shopify, Vercel with signature verification, durable queuing, and automatic retries. Use when: (1) setting u

Estimate impervious surface fraction from multi-band satellite imagery (Sentinel-2) using spectral indices (NDBI, NDVI, MNDWI). Supports binary classification and continuous fraction estimation, with

Multi-year cropland abandonment detection using NDVI time series. Identifies suspected abandoned cropland based on consecutive years without cultivation signals. Use when screening for abandoned field

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-f

Play Blinko (on-chain Plinko) headlessly on Abstract chain. Use when an agent wants to play Blinko games, check game stats, view leaderboards, or track honey rewards. Handles the full commit-reveal fl

Activate when: user says 'how do I level up my thinking', 'why do I keep copying others', 'I don't know what I don't know', 'how do I develop independent judgment', or their reasoning shows systematic

SOTA Computer Vision Expert (2026). Specialized in YOLO26, Segment Anything 3 (SAM 3), Vision Language Models, and real-time spatial analysis.

Finds orphaned files, unused components, and dead code in projects. Use when 清理代码, 查找孤儿文件, 删除无用代码, cleanup, find unused, or removing legacy code.

Use Nota Sign to plan and improve e-sign tasks for business documents. Get help choosing a practical signing setup, organizing signer roles, preparing documents, and structuring a smoother signing wor

Full-featured Confluence Cloud REST API v2 skill. Manage pages, spaces, blogposts, attachments, comments, labels, and more via direct Atlassian API calls. Use when managing Confluence content, creatin

Transcribe audio and video files using the Signal Loom AI API. Supports MP3, WAV, M4A, MP4, MOV, and more. Runs locally on Apple Silicon for speed and privacy.

List available AI models from OATDA's 10+ providers with optional filtering by type (chat, image, video) or provider name. Triggers when the user wants to see what models are available through OATDA,

Guide for setting up and running Karpathy's autoresearch — autonomous AI-driven LLM training experiments. Helps write program.md, interpret results, and optimize configs for different GPU sizes. Use w

Check OpenClaw release notes from GitHub, show highlights and categorized changes translated to the user's language.

Use when an agent needs to install or use indexbind from Node, browsers, Web Workers, or Cloudflare Workers. This skill helps choose the right package, CLI, artifact, and entrypoint, and points to the

Scaffold any project in seconds. Generate boilerplate for Next.js, React, Python CLI, Express, FastAPI, static sites, and more. Pre-configured with git, linting, CI, README, and license. Use when the

Trigger an Agent Token Audit via Botlington's A2A endpoint. Use when you want to audit an AI agent's token efficiency — identifies model waste, context bloat, tool mismatches, and redundant work. Resp

Injury prevention through proper body mechanics for physical work. Use when someone has a physically demanding job, needs to lift heavy objects safely, stands all day, or wants to prevent repetitive s