Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when a teammate wants ad-hoc PredictLeads signals for a single company, asks "what's happening at [company]", "signals for [domain]", "enrich [domain] with PredictLeads", "pull jobs/funding/news for [company]", or wants to read previously cached signals from local SQLite without burning new credits.
Pull competitive intelligence on a competitor — pricing, positioning, recent changes, customer stories — via the competitive-intel CLI. Use when the user says 'analyze this competitor', 'pull competitive intel on [company]', 'compare us to [competitor]', 'what's [company] doing differently', or 'audit [competitor] pricing'. Side-effecting — calls Firecrawl + Anthropic, writes to local cache.
Reference guide for mobile app store quirks and undocumented behaviors across Apple App Store and Google Play Store. Use when the user asks about app store release management, phased/staged rollouts, version codes, version names, build versioning, TestFlight, App Bundle Explorer, App Store Connect API behavior, canceling submissions, removing apps from sale, or any question about how Apple App Store or Google Play Store handles releases, builds, and updates. Also use when comparing behavior between the two stores.
Track popular/new open-source LLMs and update docs/model_coverage.mdx with their kernel support status. Use when discovering new models to add to the coverage tracker, checking if a specific model is covered, or refreshing model coverage documentation.
This skill should be used when the user asks to "search YouTube", "find videos about", "get a transcript", "download subtitles", "extract audio from YouTube", "scan a channel", "research a topic on YouTube", "get video metadata", "what videos exist about", "download YouTube audio", "YouTube research", "summarize this video", "what is this video about", "pull captions from", "grab the audio from", or provides a YouTube/Vimeo/video URL and wants to extract information from it. Also triggers on "batch download transcripts", "analyze a channel", or any multi-video research workflow.
Recover Vine video metadata (author, user ID, title, thumbnail) from vine.co oembed endpoint even though the Vine API and pages are dead. Use when: (1) you have Vine shortcode URLs (vine.co/v/XXXXX) and need to identify the creator, (2) the Vine page only shows a loading spinner, (3) archive-api.vineapp.com returns 404, (4) need to map Vine shortcodes to user IDs for cross-referencing against the divine.video database. The oembed endpoint is a still-live metadata oracle for the otherwise-dead Vine platform.
Fix empty results when paginating Wayback Machine CDX API with wildcard URL queries. Use when: (1) CDX query with url=foo/* and page=0 returns empty/0 bytes but works without page parameter, (2) CDX pagination returns no data for wildcard prefix searches, (3) Need to paginate large CDX result sets using wildcard URL matching. Covers showResumeKey, offset, and page parameter incompatibilities.
深度A股情报调查与分析工具，支持A股情报调查、竞品分析、舆情监测、人物背景调查、信息交叉验证，生成结构化调查报告。当用户需要调查A股公司/行业/概念、调查竞品、追踪热点事件、了解人物背景、验证信息真实性时使用。触发词：A股情报、股票调查、财报分析、概念追踪、资金流向、情报调查、竞品分析、舆情调查、背景调查、信息验证、多源搜索。
B站AI信息源 — 每日扫描B站AI相关账号，按点赞量发现爆款视频，智能聚类话题后生成包含封面图、互动数据与订阅支持的HTML日报。同时基于热门话题执行AI情报调查，采用多引擎搜索与交叉验证，输出结构化调查报告。支持用户自定义关键词定向查询。⚠️数据每日15:00更新前一天数据，目标日期无数据时必须先告知用户并等待确认后才能调用接口，禁止自动获取。当用户需要AI-B站日报、B站爆款、AI-B站热点、B站AI内容、B站AI视频、B站情报或自定义关键词查询时使用。