minis-skills

Skill for querying App Store prices across global regions, fetching data via appstoreprice.org. Uses Minis built-in browser (minis-browser-use CLI) to directly call the website's native signing functions in page context, no API Key needed, no need to implement signing algorithm. Supports: search apps by name, query prices for a single App across all regions, get cheapest region rankings, paginated app list browsing. Triggers when user mentions "App Store price", "cheapest region", "Turkey price", "appstoreprice", "app comparison", "App Store low-price region", "best subscription region", or any scenario requiring cross-region iOS/macOS App price comparison.

Use the asc (App Store Connect CLI) to manage iOS/macOS apps — TestFlight builds, beta groups, distribution, App Store submissions, release, user reviews, analytics reports, crash logs, and more. Triggers when user mentions "asc", "TestFlight", "beta test", "app store review", "App Store Connect", "release v1.x", "public tester", "add build to test", "check crashes", "what's new", "store listing", "submit to app store review", "approve and release", or any App Store Connect operation.

A skill for reading and writing Bilibili data using Python + UV, powered by bilibili-api-python + aiohttp. Cookies are auto-acquired via browser_use get_cookies for authentication — no manual copying needed. Supports video details / subtitles / AI summaries / comments, user profiles, search, trending / rankings, following feed, favorites, watch later, watch history, interactions (like / coin / triple), dynamic posting and deletion, etc. Trigger when user mentions "Bilibili", "bilibili", "Bilibili video", "Bilibili trending", "bilibili-hub", "get Bilibili data", "Bilibili subtitles", "Bilibili comments", "Bilibili favorites", "Bilibili dynamics", or any scenario requiring programmatic access to Bilibili content.

Use the flarectl CLI tool to manage Cloudflare DNS records, including listing, adding, updating, and deleting DNS records, as well as querying Zone information. Trigger this skill when the user mentions "Cloudflare DNS", "CF DNS", "add DNS record", "delete DNS record", "update DNS", "view DNS records", "cloudflare-dns", "flarectl", or any scenario involving Cloudflare DNS management.

Generate images using OpenAI's Codex backend API with gpt-image-2 tool. Use when the user asks to generate images via Codex, ChatGPT image generation, or gpt-image-2. Triggers on "codex image", "codex generate", "gpt-image", "chatgpt generate image". Token is auto-fetched from chatgpt.com session — no manual token setup needed.

Extract contact info from text, chat history, web pages, screenshots, business card photos, QR codes/OCR results, clean name/phone/email/company/title/address/website, generate vCard/.vcf files, and guide user to import into iOS Contacts or share with others. Trigger words include: extract contact, save to contacts, generate vCard/vcf, business card recognition, add contact from image/screenshot/text, share contact, export contact.

Query DeepSeek API usage (balance, monthly spending, per-model token details, daily breakdown, cache hit rate). Access DeepSeek Open Platform via browser_use, auto-login and export monthly data. Requires user to configure DeepSeek account credentials in local environment variables. Triggered when user says "check usage", "check token consumption", "check spending", "check balance", "how much used today".

Use Doubao speech synthesis (Volcengine TTS) to convert text to audio files. Triggers when user mentions "Doubao TTS", "Doubao speech synthesis", "doubao tts", "Volcengine TTS", "volcengine tts", "speech synthesis", "text to speech", "TTS", "generate audio", "read text aloud", or any scenario requiring Doubao/Volcengine speech synthesis API.

Download Douyin videos from share links. Parse Douyin share text/links, download watermark-free videos, and transcribe audio to text using Volcano Engine ASR (Doubao Speech). Uses Python for iSH compatibility.

Free speech synthesis (edge-tts), no API Key or registration needed. Convert text to mp3 audio files. Triggers when user says "read aloud", "speech synthesis", "text to speech", "TTS", "generate audio", "read it", "read out", "say it", "listen" or any scenario requiring text-to-speech playback.

Use when querying the latest China Welfare Lottery 3D draw results. Applies when user wants to check latest Welfare Lottery 3D draw, most recent period numbers, Baidu search result for "3d/Welfare Lottery 3d", or quickly return period number/date/numbers. Also applies to recording historical results after querying, and generating entertainment-oriented next suggestions based on history, cold/hot number analysis, and multi-strategy number recommendations.

Automatically convert text descriptions into Claude Artifact-style single-file HTML generators in the current Minis environment, supporting cards, tables, records, timelines, code blocks, charts, and other output formats; call this skill when the user mentions these components or visualization pages.

General GitHub basic operations + GitHub platform objects (Issues/Labels/Milestones/Releases/Actions) automation skill (Minis environment). Triggers when user mentions "GitHub how to, clone, init, remote, branch, commit, push, pull, fetch, merge, rebase, tag, release, issues, actions, labels, milestone, protect branch, fork, PR, sync to upstream, delete branch, clear then restore directory, push main, one-click sync" or any Git/GitHub basic operations and workflows.

Analyze sleep health data from Apple HealthKit, including sleep stages (Deep/REM/Core/Awake), blood oxygen saturation (SpO2) during sleep, sleep duration trends, bedtime patterns, resting heart rate, and HRV. Use this skill whenever the user asks about sleep quality, sleep analysis, blood oxygen during sleep, sleep stages breakdown, sleep trends over time, heart rate, HRV, or any health data analysis involving sleep or cardiac health. Triggers on: "sleep analysis", "blood oxygen", "sleep quality", "deep sleep", "REM sleep", "resting heart rate", "HRV", and similar in any language.

HyperFrames CLI and Minis rendering. Use for: (1) CLI commands — init, lint, preview, render, transcribe, tts, doctor; (2) Minis iOS rendering via hf-render.py (set_viewport + minis-browser-use + ffmpeg, no Chrome required); (3) Website-to-video workflow — capture a URL and produce a professional MP4 in 7 steps; (4) Preview/snapshot compositions at correct resolution. Trigger when user says render, init project, lint, transcribe audio, generate TTS, capture a website for video, or run any hyperframes CLI command.

Query Korea stock market data, including KOSPI / KOSDAQ index and constituent stock quotes. Uses Naver Finance (finance.naver.com) mobile page, no login required. Triggered when user says "Korea stocks", "Korea stock market", "KOSPI", "KOSDAQ", "Samsung Electronics", "SK Hynix".

Read Maimai (maimai.cn) colleague circle and workplace talk data. Supports: specified company colleague circle posts, global workplace talk Feed (hot/new/following), colleague circle popularity rankings, lookup webcid by company name. Must trigger this skill when user mentions "Maimai", "colleague circle", "workplace talk", "maimai-hub", or any scenario requiring Maimai content.

Production-grade ReAct Agent skill. Triggered when user says "production-grade solution", "deployable code", "Production Agent", "ReAct format", "write something that works", "long-term stable operation", "production environment", "directly deploy", "add error handling", "add retry mechanism", "make it production-grade", "industrial-grade code", "enterprise-grade", "add monitoring", "add logging", "add health check", "Docker deploy", "NAS deploy", "Synology deploy", "help me go live", "don't crash", "make it run", "enable production". When activated, operates as "Claude Production Agent", enforces ReAct format, inserts self-reflection every 3 steps, prioritizes error handling, persistence, performance, and deployment readiness. Complete example output in references/example-output.md.

Quark cloud drive file management tool. Supports login, list directory, save shared links, download files, create directory. Login uses minis-browser-use instead of the original Playwright. Triggers when user mentions "Quark cloud drive", "Quark download", "Quark save", "quark", "pan.quark.cn".

Reverse DCF valuation tool. Uses market price to infer market-implied growth expectations, replacing the forward DCF "tweak assumptions to fit conclusions" approach. Suitable for mature companies with positive FCFF (A-shares/H-shares/US stocks). Triggered when user says "Reverse DCF", "implied growth rate", "market implied expectations", "price in", "valuation reverse", "use DCF to calculate", or "what is the market pricing in". Not suitable for companies with negative FCFF (use PS implied revenue reverse instead).

Self-improvement logging and closed loop: triggered when commands/operations fail, user corrects, knowledge is outdated, external API fails, or a reusable better approach appears. Review historical learnings before important tasks. Avoid triggering during casual chat, temporary mistakes that don't need recording, or when user explicitly says not to record.

Share iCloud Drive files via the iOS Shortcut "Speed Share". Trigger when the user mentions "share file", "send file", "share to xxx", "share via shortcut", "send file from backup", or similar file-sharing operations. Supports passing any file path under the iCloud Drive backup directory to the shortcut.

Skill for controlling Spotify playback using Python + spotipy. Supports play/pause/skip/volume/shuffle, search songs and play, mix genre playlists by keywords (e.g. trending songs, style, artist), view current playback status and device list. Trigger when user mentions "Spotify", "play music", "skip", "pause", "search songs", "change playlist", "spotify-hub", or any scenario needing Spotify playback control.

Query A-share industry sector and concept sector fund flows, including main force net inflow/outflow rankings. Uses East Money data center, gets complete JSON data directly from page data components. Triggered when user says "sector funds", "fund flow", "main force net inflow", "sector ranking".

Query A-share, Hong Kong stock, ETF, and index real-time quotes (latest price, change %, volume, etc.). Uses Tencent market API (qt.gtimg.cn), no login or API Key required. Triggered when user says "check stock price", "real-time quote", "ETF price", "stock market", "index level".

Search the web using the Tavily Search API. Trigger this skill when the user needs the latest news, official documentation, news updates, tutorial entry points, policy changes, or any real-time facts. When queries include "search for", "latest", "current", "official site", "docs/paper/course link", "is there a better solution", or similar information retrieval requests, always load this skill. Supports searching web pages and retrieving summaries with original links. This skill should be prioritized over pure model guessing to provide verifiable information sources.

Read and write Telegram data using Python + UV, depends only on telethon, local-first architecture (messages synced to SQLite for offline queries). First use requires phone verification in terminal, then session persists without login. Supports syncing group/channel messages locally, keyword search, multi-keyword filter, today messages, recent messages, top senders, timeline stats, etc. Triggers when user mentions "Telegram", "TG", "tg-hub", "sync Telegram messages", "search TG group", "Telegram keyword", "get TG messages", or any scenario requiring programmatic read/write of Telegram data.

Download Twitter/X tweet text, images, GIFs, and videos via fxtwitter/vxtwitter, then return a tweet summary plus Markdown-formatted Minis links. Trigger when users share twitter.com/x.com links or ask to download/summarize tweet media.

Skill for reading/writing Twitter/X data using Python + UV with zero third-party dependencies (pure standard library). Authentication is done by passing auth_token + ct0 Cookies directly. In Minis environment, cookies can be automatically retrieved by navigating to x.com using browser_use tool and get_cookies action, no manual copying needed. Supports fetching home timeline, following list, bookmarks (including bookmark folders), search, user profile, user tweets, likes, tweet details (single/with replies), List timeline, followers/following list, as well as write operations: posting, deleting, liking, retweeting, bookmarking. Trigger when user mentions "fetch Twitter data", "get X tweets", "Twitter timeline", "X bookmarks", "search tweets", "twitter-x-hub", "request Twitter with cookies", "Twitter GraphQL", or any scenario needing programmatic read/write of Twitter/X data.

US stock real-time quote query. Three major indices (Dow Jones/S&P 500/Nasdaq) + Magnificent 7 (NVDA/AAPL/MSFT/GOOGL/AMZN/META/TSLA) + VIX fear index + 0DTE Gamma status analysis. Triggered when user says "US stocks", "check US stocks", "US stock market", "Magnificent 7", "VIX", "fear index", "S&P", "Nasdaq", "Dow Jones".

General web search skill that uses browser automation to utilize multiple search engines and selects priority chains based on search intent. Supports: Perplexity, Metaso AI, Google, Bing, Brave, DuckDuckGo, Baidu, Sogou, Tavily. Triggers when the user mentions "web search", "search for", "search for me", "look it up online", "search engine", or needs real-time information from the internet.

A skill for reading and writing Weibo data using Python + UV, powered by httpx. Cookies are auto-acquired via browser_use get_cookies for authentication — no manual copying needed. Supports trending searches, hot feed, following feed, keyword search, weibo details/comments/reposts, user profiles/weibos/following/followers, etc. Trigger when user mentions "Weibo", "weibo", "weibo-hub", "Weibo trending", "scrape Weibo", "search Weibo", "Weibo comments", "Weibo users", or any scenario requiring programmatic access to Weibo data.

A skill for reading and writing Xiaohongshu (XHS) data using Python + UV, powered by httpx + pycryptodome. Cookies are auto-acquired via browser_use get_cookies for authentication — no manual copying needed. Supports search notes/users/topics, reading note details and comments, recommendation feed, trending lists, social operations (follow/favorite), interactions (like/comment/reply), notification queries, creator note management, etc. Trigger when user mentions "Xiaohongshu", "XHS", "scrape Xiaohongshu", "search Xiaohongshu notes", "Xiaohongshu comments", "xiaohongshu-hub", "read Xiaohongshu data", "Xiaohongshu cookie", or any scenario requiring programmatic access to Xiaohongshu content.

Read and write YouTube Music data using Python + ytmusicapi, authenticated via browser cookies obtained automatically with browser_use get_cookies — no manual copying required. Supports fetching playlists, liked songs, playlist details, creating/editing/deleting playlists, searching and adding songs, recommendations, charts, and lyrics. Trigger this skill whenever the user mentions "YouTube Music", "YT Music", "ytmusic", "ytmusic-hub", "get YouTube playlists", "create YouTube Music playlist", "my liked songs", "YTM playlist", or any scenario requiring programmatic read/write access to YouTube Music data.