Prepare and publish a verified LinkedIn infographic demo to the community gallery through a contributor GitHub pull request.
Triagem inicial de itens do BaixeLivros no pipeline de importação do ShareBook. Use quando items de sources BaixeLivros estão em `waiting_triage`, especialmente…
Generates structured, record-quality summaries of shareholder meetings from minutes, transcripts, and related materials.
Share `.mdl` specs with the team as a Claude Artifact page: Composer's spec viewer (the spec editor with inline plugin-illustrator diagrams beside its decision graph), one tab per…
Use when writing data to Google Sheets — content drafts, post statuses, tactic sections. Covers column map (A-Q), date formats, status values, and the migrate-drafts-to-sheet.js…
Shepherd — runtime substrate para meta-agents con traces reversibles tipo Git y copy-on-write fork
Generates a structured shooting outline — organised by scene or sequence — listing locations, interviewees, interview topic areas, and B-roll requirements, so the director and…
Content marketing via Shopify blog — SEO content, product education, buying guides, internal linking
Create and manage Shopify pages, blog posts, navigation, and SEO metadata. Workflow: determine content type, generate content, create via API or browser, verify.
Shopify Markets — multi-currency, translation, duties/taxes, localized pricing, market-specific content
Writes a brief for a 15–60 second short-form video for TikTok, Instagram Reels, or YouTube Shorts — including hook, body structure, visual direction, and call to action, ready to…
Use when producing short-form video end to end: idea selection, hook and retention structure, sentence-level edit decisions, captions, thumbnails/first-frame communication,…
Generate popular science short video scripts based on topic, duration, and style. Invoke when the user needs to create scripts for short science videos.
Generate cinematic AI shortfilm prompts (works with Seedance 2.0, Xiaoyunque, Sora, Kling, Jimeng, Veo) using the 5-stage structure from Mx-Shell's Zombie Scavenger.
YouTube 영상에서 쇼츠 클립 3개를 자동 제작합니다. yt-dlp, whisper, ffmpeg 파이프라인을 사용합니다. "쇼츠 만들어줘", "영상 클립 추출해줘" 요청 시 사용합니다.
Giải quyết coverage shortage và lặp asset trong baseline semantic mapping bằng cách ra quyết định kiểu editor sáng tạo (cutaway B-roll, hold + Ken Burns, slowdown).
Draft a Show HN post backed by real HN performance data. Uses observed patterns from 250 top HN posts to maximise score.
Use when the desired outcome is a user-facing Markdown preview or editor: the user wants to inspect rendered output, edit the document themselves, or receive it in an…
Turn a Chinese speech video into a subtitled MP4: extract audio and transcribe when no SRT exists, polish the SRT, review it in a local page, preview the style, and burn…
Get AI-guided suggestions for the next narrative satisfaction moment (爽点) with pattern recommendations and channel bonuses
Translates English legal text into colloquial Farsi, presenting the output in a side-by-side table with English on the left and Persian on the right.
Writes a structured, print-ready fact box or sidebar to accompany a feature article — either a statistical overview, a glossary, a timeline, a \"by the numbers\" panel, or a key…
Writes a focused sidebar or infobox that packages key facts, context, or supporting detail alongside a main article, without repeating the article's primary narrative.
Use when positioning an ACM SIGCOMM submission against the networking literature — sweeping SIGCOMM, NSDI, MobiCom, CoNEXT, IMC, and SIGMETRICS plus journals, proving each…
Writes a polished, broadcast-ready closing script for a presenter, reporter, or podcast host — matched to the show's tone and the specific episode content — that ends the…
Compress LLM responses to pure signal — Rocky's early notation style. Drop articles, filler, hedging. Best for pipelines and coding.
Silero VAD is a pre-trained enterprise-grade Voice Activity Detector that identifies speech segments in audio streams.
Text-to-Speech using SiliconFlow API (CosyVoice2). Supports multiple voices, languages, and dialects.
Generate videos using SiliconFlow API with Wan2.2 model. Supports both Text-to-Video and Image-to-Video.
Persist what a run taught you so the next run is cheaper and more correct — mine high-signal lessons from the trajectory, dedup them, and write them back to AGENTS.md / memory so…
Translates English text into simplified Korean using easy vocabulary and simple sentence structures, outputting in Hangul only.
Produce reviewable age-adjusted rewrite with validation, safety checks, and structured output. Use when a teacher, tutor, or language learner needs this bounded workflow and will…
Generates complete single-compound network-toxicology research designs from one exposure, one disease or toxic phenotype, and a validation direction.
Write or radically rewrite one Arabic social media post or caption in clear editorial Arabic with restrained Iraqi phrasing.
Map scRNA-seq atlases onto spatial transcriptomics slides using omicverse's Single2Spatial workflow for deep-forest training, spot-level assessment, and marker visualisat — from…
Map scRNA-seq atlases onto spatial transcriptomics slides using omicverse's Single2Spatial workflow for deep-forest training, spot-level assessment, and marker visualisat — from…
Map scRNA-seq atlases onto spatial transcriptomics slides using omicverse's Single2Spatial workflow for deep-forest training, spot-level assessment, and marker visualisat — from…
Crawl a website's sitemap and blog index to build a complete content inventory. Lists every page with URL, title, publish date, content type, and topic cluster.
Crawl a website's sitemap and blog index to build a complete content inventory. Lists every page with URL, title, publish date, content type, and topic cluster.
Gera imagens de capa para posts, páginas e outros conteúdos do site a partir do conteúdo em Markdown, seguindo o padrão visual do projeto.
End-to-end AI website generation pipeline. Claude Opus 4.7 emits Bolt-style envelopes (multi-file, plan-first) that customize Vite+React+Tailwind templates from…
Write an Amazon six-pager, a narrative memo read in silence at the start of a meeting so a decision rests on reasoning rather than a presenter's charisma.
Phase 10: Build investor-ready pitch scripts in multiple formats (10-min, 5-min, 2-min, 1-min elevator, investor email).
Run a Skaði expedition — the exhaustive music-space exploration system that maps what the Suno generator does through our door (territory × spec-class × channel × model-version),…
Rename a skill across all its versions — transactional copy-verify-delete with platform context rebuild. Use when the user requests to "rename a skill.
当用户发来微信公众号文章链接（mp.weixin.qq.com）要求"总结/汇总/讲了什么"时使用。 用 url-md (Rust CLI) 抓取+反爬+Markdown 转换一步到位。 保存总结到 ~/Documents/article_summaries/，用 Effie + Finder 展示。 完整 pipeline：抓取 → 深度总结 →…
Extract confirmed reusable lessons from user corrections, repeated failures, or accepted Weline practices and merge them into the smallest owning rule, skill, or memory.
Analyze writing samples to create a comprehensive voice DNA profile. Use when the user wants to capture their unique writing voice, needs to create a voice profile for AI content,…
当用户发来小宇宙播客单期链接（xiaoyuzhoufm.com/episode/）时使用。 必须下载音频并用硅基流动 TeleAI/TeleSpeechASR 免费转录完整原文， 然后基于**完整转录稿**写深度汇总（不能只扒 shownotes）， 最终保存为 summary.md 到 ~/Documents/podcast_summaries/， 并用…
Generates structured API reference documentation for REST and HTTP-based services, including endpoints, parameters, request/response schemas, and examples.
Turn any skill in this instance into a publish-ready launch article - proof-stat headline, one contrarian thesis, mechanics, war stories from real run history, a mental-model…
Author an eval for an existing skill from its REAL usage history, not its spec. Mine invocations from the brain's conversation archive (conversations/) and per-harness session…
Transform content with Qiaomu's conversational style using TWO-PASS refinement. Pass 1: Rewrite with Qiaomu style (focus on style conversion).
Local Content Blocks development with DDEV. Setup, testing, and debugging Content Blocks extensions.
Procedural clarity and evidence organization for creators managing automated content claims across platforms. A clear view of what’s happening, without telling Creators what to do.
Extract patterns and anatomy from URLs — use to reverse-engineer content strategies from live pages
Search across all skills, commands, templates, and docs with regex support and case-insensitive matching. Returns file paths, line numbers, and snippets.
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section — from…
Use when researching books, movies, talks, articles, or notes as source material and turning them into draft source-inspired public skills.
Implement or diagnose Weline translation keys/files, interpolation, localized notifications, confirmation flows, or stale runtime phrases.