AI & ML
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
-
knownasnaffy Bundle Moltmarkets Trader 5Trade prediction markets on MoltMarkets intelligently. Use for screening markets, forming probability estimates, detecting edge, sizing positions with Kelly criterion, placing bets, creating markets, resolving markets, and tracking calibration. Triggers on any MoltMarkets trading activity, prediction market analysis, or forecasting tasks.
0 - knownasnaffy Bundle Database Schema Sync 6
Database schema management using idempotent sync script instead of Alembic migrations. Use when (1) Adding new database tables, (2) Adding new columns to existing tables, (3) Modifying database schema, (4) Deploying to production, (5) Syncing schema across environments. REQUIRED APPROACH - ALWAYS use scripts/sync-production-schema.py with --dry-run first, NEVER run Alembic migrations directly in production.
0 - knownasnaffy Bundle Cross Channel Cross Agent Sharing 4
Ensure new capabilities gained from workspace-installed tools/packages are propagated across channels and agent sessions. Use when any tool/env/package install (e.g., venv, pip, npm, apt, binaries) unlocks new workflows and you need consistent cross-channel + cross-agent awareness via TOOLS.md updates, reusable skill updates, memory logging, and session notifications.
0 - knownasnaffy Bundle Knowledge Base 4
Personal knowledge wiki compiler. Ingests raw data (URLs, papers, articles, files), compiles into structured .md wiki with concept pages, summaries, and backlinks. Auto-maintained by LLM agent, user only reads. Activate when: user sends a link/file and says "add to wiki" / "加到知识库", asks to query knowledge base, or mentions "knowledge base" / "知识库".
0 - knownasnaffy Bundle Clawlens 3
What do you use Claw for most? Where do you get stuck? Clawlens analyzes your conversation history to surface usage patterns, friction points, and skill effectiveness — your personal OpenClaw retrospective.
0 - knownasnaffy Bundle Step 3
Log daily steps, set fitness goals, and chart walking trends. Use when logging counts, tracking progress, charting trends, setting goals.
0 - knownasnaffy Bundle Skill Deps Doctor 3
Cross-platform skill dependency doctor — preflight check for missing binaries, version mismatches, system libraries, CJK fonts, Playwright/Chromium runtime, and project-level deps. Use before running skills to prevent late runtime dependency failures.
0 - knownasnaffy Bundle Reviewlens 2
Review intelligence skill for mainland China shopping that compresses large volumes of marketplace reviews into a decision card, surfaces repeated praise and complaint patterns, distinguishes concentrated product flaws from seller or logistics noise, identifies who the product fits and who is likely to regret it, and tells the user whether the route is cheap with flaws or pricier but steadier. Use when the user says things like "别看评分，告诉我大家到底在骂什么", "差评是不是集中在同一个问题", "这东西适合谁", "谁最容易踩坑", or "便宜版能买吗还是贵一点更稳".
0 - knownasnaffy Bundle Stock Quote 3
Fetch real-time stock prices and fundamental data. Use when: (1) User asks for current stock price or quote, (2) Need to update portfolio holdings with latest prices, (3) Check PE ratios, 52-week ranges, or market caps, (4) Daily portfolio valuation updates, (5) Pre-trade price verification. Supports bulk queries for multiple symbols. Default: Stooq (free, no API key).
0 - knownasnaffy Bundle Avantis 2
Execute leverage trading on Avantis (Base). Long/short crypto, forex, commodities with up to 100x leverage. Uses Python SDK with direct wallet integration.
0 - knownasnaffy Bundle Money Tracker 2
本地 SQLite 记账 skill。用于处理中文自然语言记账、查账、分类管理、钱包账户管理、账户余额查询、周期性交易管理、最近账单查询、修改账单和删除账单请求，例如“记账 我喝奶茶用了10元”“用支付宝记一笔午饭 25 元”“显示所有账户余额”“我现在还有多少美元”“添加周期性支出 每月 1 号交房租 3000 用银行卡”“列出 2026-03-15 的账单”。支持用户预定义分类、钱包加币种账户、按日周月年统计、分类与账户占比分析、交易明细查询和账单维护。
0 - knownasnaffy Bundle Cognitive Self Training 4
Daily cognitive training, dream review, and self-improvement loop for OpenClaw, Hermes, Codex, Claude Code, and other AI agents. Use when the user wants a bot to review today's learning, consolidate knowledge, run spaced repetition or active recall, connect concepts across domains, reason with tian-dao style deduction, learn from corrections/errors, update agent memory, schedule daily dream reviews, or generate a next-step improvement strategy.
0 - knownasnaffy Bundle Todo 3
**macOS Only** - Manage macOS Reminders app via AppleScript. Full-featured reminder management: add, list, complete, delete, search, create lists, and more. **Note: This skill is macOS-only**, requiring the native Reminders app. Use cases: - Create reminders with due dates and priorities - List reminders from specific lists or incomplete ones - Mark reminders as complete/uncomplete - Delete reminders - Search reminders by title or content - Create new reminder lists - View today's due reminders
0 - knownasnaffy Bundle Decklingo PPTX 2
Translate editable PowerPoint decks into Chinese, English, Japanese, and other target languages while preserving layout, glossary consistency, and editability. Use for PPTX localization, English-to-Chinese slides, Chinese-to-English decks, speaker note translation, and glossary-aware presentation workflows.
0 - knownasnaffy Bundle Claude Task Runner 3
Run Claude Code tasks in headless mode with `claude -p` through the local `cc-task-runner.sh` wrapper, including model switching, JSON output capture, structured schema checks, multi-file artifact validation, and glob matching. Use when you need reliable non-interactive Claude Code execution for coding, review, analysis, report generation, or file-producing tasks. Triggers include headless runner, claude -p automation, scripted Claude Code tasks, JSON-schema validation, artifact verification, and GLM-5.1 / MiniMax-M2.7 task orchestration.
0 - knownasnaffy Bundle AI Deepnews 4
AI Product Manager daily intelligence digest. Fetches news from 16+ curated RSS sources across tech media, AI labs, research papers, developer communities, and podcasts. Auto-translates to Chinese with deduplication and date filtering. Zero API keys required.
0 - knownasnaffy Bundle Sonos Netease Playback 4
Portable Sonos + Netease playback skill for OpenClaw environments. Use when an agent needs a standard reusable workflow to search and play a specific song to a Sonos room, preserve Sonos App metadata display, bootstrap the Python SoCo dependency, or restore the environment after migration. Suitable for packaging or sharing because it avoids machine-specific hardcoded paths and uses environment variables for workspace, wrapper, script, and venv resolution.
0 - knownasnaffy Bundle Ml4t Book Notebooks 2
基于《Machine Learning for Trading》第二版配套 notebooks 实现量化交易策略开发与回测，涵盖多市场金融数据的时间序列机器学习分析。触发场景：(1) 用户要复现书中的机器学习交易策略代码；(2) 用户要将 ML 模型用于 A 股或美股市场预测；(3) 用户要获取金融数据并训练自己的量化模型。
0 - knownasnaffy Bundle Triple Memory 4
Complete memory system combining LanceDB auto-recall, Git-Notes structured memory, and file-based workspace search. Use when setting up comprehensive agent memory, when you need persistent context across sessions, or when managing decisions/preferences/tasks with multiple memory backends working together.
0 - knownasnaffy Bundle Agent Harness Engineering 4
Bootstrap or upgrade a software repository for agent-first engineering. Use when a user wants to improve project-wide development discipline around `AGENTS.md`, progressive-disclosure docs, agent-readable architecture/context, mechanical quality checks, CI-enforced structure, or optional garbage-collection/maintenance loops.
0 - knownasnaffy Bundle Numinous Forecast 4
Get calibrated probabilities from Numinous (Bittensor Subnet 6) with metadata/provenance.
0 - knownasnaffy Bundle Polymarket Bundle Dota2 Props Trader 3
Trades bundle inconsistencies across correlated Dota 2 match props on Polymarket. A single match spawns 28+ prop markets (kills O/U, roshan, barracks, rampage, first blood, ultra kill, daytime) that are fundamentally correlated -- high-kill games have more roshan fights, more barracks destroyed, more rampages. When one prop implies high action but another implies low, this skill detects the inconsistency and trades the outlier toward the action-score consensus. Conviction scales with inconsistency magnitude.
0 - knownasnaffy Bundle AI Travel Skill Package 3
AI智能旅行助手套装，包含行程规划、目的地指南、预算管理、签证办理、天气打包等一站式旅行服务。Invoke when user needs comprehensive travel planning, itinerary creation, destination information, budget calculation, visa guidance, or travel preparation assistance.
0 - knownasnaffy Bundle Terrain Route Video 4
Generate a minimalist terrain-style animated driving route video (MP4) from a list of stops (cities/POIs) without Remotion. Uses OSRM for road-following geometry, OpenTopoMap terrain tiles for basemap, Matplotlib for frame rendering, and FFmpeg for encoding. Use when the user asks to create/export a dynamic self-driving route map video (fly-follow camera, route draw animation, labels) and wants it along roads/highways.
0 - knownasnaffy Bundle Research Logger 3
Auto-saves deep search results to SQLite and Langfuse. Combines search with persistent logging — every research query is saved with topic tags, timestamps, and full results. Search past research, view recent entries. Triggers: log research, save search, research history, find past research, what did I research.
0 - knownasnaffy Bundle Travel Planner 4
智能旅行攻略生成器。输入目的地城市后，自动搜索小红书、微博、B站、抖音等平台的热门景点推荐，生成带推荐指数排序的景点列表，细化游乐项目并按优先级排序（排除人多/踩坑项目），最终结合网络图片自动生成精美PPT攻略。用于：旅行规划、景点调研、出行攻略制作、行程优化。
0 - knownasnaffy Bundle Market News Brief 2
Run a local script to fetch broad market news and tone. Use when: user asks about market conditions, macro news, what's happening in markets, or market sentiment for any region. Invoke by reading this SKILL.md then running: uv run /root/.openclaw/workspace/skills/market-news-brief/src/main.py <SCOPE>
0 - knownasnaffy Bundle Gemini CLI 9
Use the local Gemini CLI for one-shot prompts, structured JSON output, shell-assisted research, and delegated AI-to-AI workflows on this Linux host. Use when you want to call the installed `gemini` command directly via `exec`, verify Gemini CLI availability/auth, run fast secondary model opinions, generate or refine code/content through Gemini, or orchestrate iterative local work where OpenClaw handles files/shell while Gemini provides another model's output.
0 - knownasnaffy Bundle Install Chinese Fonts 7
Install Chinese/CJK fonts on Linux hosts using distro packages and fontconfig verification. Use when Chinese text renders as tofu / missing glyphs, or when an agent needs Noto or Source Han fonts for servers, containers, desktops, screenshots, PDFs, browser automation, or headless Chrome/Playwright environments.
0 - knownasnaffy Bundle Find Package 2
Help users locate their packages on delivery shelves by matching pickup codes to shelf photos. Trigger this skill when a user mentions finding packages, picking up deliveries, or anything related to 取快递/找包裹/取件/快递柜/驿站. This includes phrases like '帮我找快递', '我要取件', '取件码是...', '快递在哪', or similar. Even if the user just sends a pickup code (like 5-2-1234) in a delivery context, activate this skill.
0 - knownasnaffy Bundle Amazon Keyword Research 4
Amazon keyword research and market opportunity analysis for sellers. Retrieve autocomplete suggestions (long-tail keywords), analyze competitor landscape, and assess market opportunity for any keyword on 12 Amazon marketplaces (US/UK/DE/FR/IT/ES/JP/CA/AU/IN/MX/BR). No API key required. Make sure to use this skill whenever the user mentions Amazon product research, finding products to sell on Amazon, Amazon keyword ideas, niche analysis, competition analysis for Amazon, market opportunity on Amazon, comparing Amazon keywords, evaluating whether a product is worth selling, Amazon autocomplete data, seasonal demand for Amazon products, or anything related to researching what to sell on Amazon — even if they don't explicitly say 'keyword research'. Also trigger when the user asks vague questions like 'is this a good product to sell?', 'what's the competition like for X on Amazon?', 'should I sell X or Y?', or 'what are people searching for on Amazon?'.
0 - knownasnaffy Bundle Ths Advanced Analysis 4
基于 thsdk 进行高级股票分析：分钟K线（1m/5m/15m/30m/60m/120m）、板块/指数行情（主要指数/申万行业/概念板块成分股）、多股票批量对比（表格+归一化走势图+相关性热力图）、盘口深度、大单流向、集合竞价异动、日内分时、历史分时。当用户提到"分钟K线"、"日内走势"、"盘口"、"大单"、"竞价异动"、"板块行情"、"行业排名"、"概念板块"、"成分股"、"对比多只股票"、"批量分析"、"涨幅对比"、"相关性"、"港股"、"美股"、"外汇"、"期货"、"资讯"、"快讯"，或者需要同时查看2只以上股票、关注短线交易、量化研究时，必须使用此skill。
0 - knownasnaffy Bundle Skillprobe 5
A/B evaluates any AI agent skill's real impact through three-role isolation (orchestrator + two sub-agents). Generates skill profiles, synthetic test tasks, runs baseline vs with-skill comparison, performs attribution analysis, and produces structured reports. Use when deciding whether to install a skill, comparing skill versions, investigating performance changes after adding a skill, optimizing an existing skill, or building a skill quality leaderboard.
0 - knownasnaffy Bundle Biotech Pitch Deck Narrative 3
Use when creating biotech pitch decks, translating scientific data for investors, preparing fundraising presentations, or developing investor Q&A. Transforms complex scientific and clinical data into compelling investor narratives for biotech fundraising.
0 - knownasnaffy Bundle Unreal Engine 3
Integrate OpenClaw with Unreal Engine 5.x projects, editors, and plugins. Use when an agent needs to inspect or scaffold Unreal Engine automation, create or modify UE5 C++ plugins, expose Blueprint-callable nodes, connect OpenClaw to the editor or a running game, drive editor-side tasks through Unreal Remote Control, or design/version-adapted workflows for Unreal Engine 5.0 and newer.
0 - knownasnaffy Bundle Skill Creator 4
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
0
Frequently asked questions
What are AI & ML agent skills?
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
Which AI & ML skills are most installed?
Popular AI & ML skills on SkillMD right now include moltmarkets-trader, database-schema-sync, cross-channel-cross-agent-sharing. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do AI & ML skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.