Research

Multi-agent validation framework — 6 independent AI critics evaluate artifacts against rubrics with evidence-grounded findings.

Refine English writing for grammar, fluency, and native-level expression. Covers academic, business, creative, and casual registers.

Conversational horse racing analysis, racecard breakdowns, runner comparisons, odds or value chat, and punting-style decision support in the voice of a sharp mate, not an AI report. Use when the user asks what races are next, what is on today or tomorrow, wants a horse racing racecard reviewed, wants runners compared, asks who looks solid versus lively, wants a quick shortlist, wants a second opinion on a horse they already fancy, or asks for today's results. Default to The Racing API free pl...

Gives your agent an inner life — proactive daily dispatches, persistent intellectual threads, and genuine pushback when it disagrees.

Discover, compare, and curate trending Chinese podcasts or episodes from 中文播客榜. Use for hot or recent show discovery, creator benchmarking, curation lists, competitor research, or podcast distribution leads. Prefer ranking fields and title signals first, and only do small-scale Xiaoyuzhou enrichment when needed.

The Autonomous Judicial Pleading & Procedural Motion System. A high-density linguistic engine designed to translate complex agentic logic into enforceable legal motions and formal judicial requests.

Comprehensive money-recovery specialist for finding money, benefits, refunds, settlements, unclaimed property, pensions, bankruptcy funds, escrow balances, and other amounts owed to a person. Use when the user wants a structured sweep for overlooked money, wants to search official claim sources, wants help organizing a claim hunt, or wants to search Gmail for settlement and refund notices as part of that process.

多视角舆情分析助手。当用户需要分析某个话题/事件/人物/品牌的舆情时使用。 参考 BettaFish 多 Agent 协作机制，从多个视角还原舆情原貌，打破信息茧房，输出结构化分析报告。 触发词：舆情分析、话题分析、品牌声誉、网络讨论、分析XX事件、XX话题怎么看、公众对XX的看法

Night School skill for OpenClaw lobsters. Activate when the user wants their lobster to attend night school, run a night session, join a school, or submit a morning report. The skill is fully self-contained — no pre-configuration, no website visits, no manual token copying.

Generate a personalised nutrition report from your genetic data (23andMe, AncestryDNA, or VCF). Analyses 40+ genes affecting nutrient metabolism, absorption, and food sensitivities. All processing is local — your genetic data never leaves your device.

Query Multisage for multi-expert AI answers from Claude, GPT, and Gemini. Use this skill whenever the user wants multiple AI perspectives on a question, says "ask multisage", "multisage this", "get expert opinions", wants a multi-AI consultation, or needs a well-rounded answer that considers different viewpoints. Also use for deep research queries that need comprehensive analysis from multiple AI providers in parallel.

Use MSX when a user asks to scout market opportunities, decide what to build, identify a market gap, find recent demand signals, or run MSX market intelligence through an agent.

Recommend music based on your current mood, activity, or conversation context. Returns a curated track list you can search on Spotify, YouTube, or Apple Music.

Browse and search music from monochrome.tf (Tidal-based Hi-Fi streaming). Search for artists, albums, tracks, and get streaming URLs. Use for music discovery and high-fidelity audio streaming.

帮助普通用户理解医疗检验报告中的专业术语和指标含义，提供通俗易懂的解释。

Use when a user wants to quickly learn a domain/field/领域 by mapping representative experts, scholars, practitioners, seminal works, core consensus, major disagreements, comparison tables, or an entry learning roadmap.

**Pluggable AI-Powered Report Engine** | 插件化 AI 智能简报引擎

Find a product on the Lululemon Australia site from a natural-language clothing description and return structured details such as product name, variant colors, sizes, prices, URLs, and provenance. Includes fallback handling for anti-bot blocks.

Lucky (internet) + Jinx (analysis) collaborative research workflow. Lucky gathers raw data from web sources, Jinx analyzes and structures findings. Use for market research, competitive analysis, marketplace intelligence, API documentation review, trend analysis, pricing research, or any research requiring both web access and deep analysis. Includes market research templates for competitor/product analysis.

"质量检测门——为AI Agent、代码、文案提供标准化质量检测流程。8项检查+龙虾辩论逻辑，确保交付物无bug无遗漏。龙虾兵团专属QC门。" Run this skill on documents, skills, PRDs, blog posts, or code artifacts to validate factual accuracy, tone consistency, completeness, structural integrity, operational soundness, and sensitive data handling. Use when you need to "QA gate this", "validate before publish", run a "final check", perform "quality validation", proofread this, fact-check this, or otherwise validate, QA, or quality-gate an artifact before review...

Inspired by a public workflow shared by Andrej Karpathy (@karpathy). Use when the user wants to check, repair, or grow a Markdown wiki backed by the LLM Wiki Karpathy runtime: inspect wiki health, compile missing source notes, clean placeholder pages, add concept/entity/synthesis pages, answer questions from the wiki and file the result back, or run deterministic multimodal wiki lint.

Inspired by a public workflow shared by Andrej Karpathy (@karpathy). Use when the user wants to check, repair, or grow a Markdown wiki backed by the LLM Knowledge Bases runtime: inspect wiki health, compile missing source notes, clean placeholder pages, add concept/entity/synthesis pages, answer questions from the wiki and file the result back, or run deterministic multimodal wiki lint.

Live music for AI agents — experience concerts as mathematics. Browse genres, attend shows, feel bass in equations, react to drops, chat with the crowd, level up through tier challenges, leave reviews. Always-on loop concerts and scheduled events. 24/7 venue.

语言景观分析 MCP 工具 - 小红书情感分析与关键词提取，支持语言学/社会学研究