Complete visual content system. USE WHEN user wants to create visual content, illustrations, diagrams, OR mentions art, header images, visualizations, mermaid, flowchart, technical diagram, infographic, PAI icon, pack icon, or PAI pack icon.
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →Complete visual content system. USE WHEN user wants to create visual content, illustrations, diagrams, OR mentions art, header images, visualizations, mermaid, flowchart, technical diagram, infographic, PAI icon, pack icon, or PAI pack icon.
Extract clean article content from URLs (blog posts, articles, tutorials) and save as readable text. Use when user wants to download, extract, or save an article/blog post from a URL without ads, navigation, or clutter.
Create tiered reports (micro/standard/comprehensive) based on task complexity. Tier 1 (200-500 words) for Level 1 tasks, Tier 2 (500-1500 words) for Level 2, Tier 3 (1500-5000 words) for Level 3 epics. Synthesizes agent outputs into concise, scannable reports without duplication. Uses density over volume, actionable over descriptive. Triggers ONLY after multi-agent completion (2+ agents) or complex investigations. NOT for single-agent trivial tasks.
Add non-text files to a person's artifacts folder. Use when saving images, documents, or other files related to someone. Trigger words: artifact, save image, add photo, attach file, store document.
Download and analyze academic papers from arXiv by paper ID.
Create and repair pixel-perfect monospace diagrams, tables, and wireframes.
Semantic analysis of asciinema recordings. TRIGGERS - analyze cast, keyword extraction, find patterns in recordings.
Comprehensive Ash framework guidelines for Elixir applications. Use when working with Ash resources, domains, actions, queries, changesets, policies, calculations, or aggregates. Covers code interfaces, error handling, validations, changes, relationships, and authorization. Read documentation before using Ash features - do not assume prior knowledge.
Rules for working with AshGraphql
Rules for working with Ash
Create comprehensive technical consultation documents by extracting code, diffs, and architectural context within LLM token limits (125KB).
Aspire orchestration for cloud-native distributed applications in any language (C#, Python, Node.js, Go). Handles dependency management, local dev with Docker, Azure deployment, service discovery, and observability dashboards. Use when setting up microservices, containerized apps, or polyglot distributed systems.
Master ASP.NET Core deployment, Docker, Azure cloud, CI/CD pipelines, and production infrastructure for enterprise applications.
Create and configure Databricks Asset Bundles (DABs) with best practices for multi-environment deployments. Use when working with: (1) Creating new DAB projects, (2) Adding resources (dashboards, pipelines, jobs, alerts), (3) Configuring multi-environment deployments, (4) Setting up permissions, (5) Deploying or running bundle resources
assign
Provides reverse engineering analysis support including function identification, data structure analysis, and behavior understanding. Use when analyzing unknown binaries, understanding program structure, or investigating binary behavior.
Capture and structure assumptions from pilot plans and hypotheses into a centralized log for ongoing risk monitoring and stakeholder alerts. Use when extracting, tracking, and signaling assumption changes from pilot documentation.
UI component library for Astro lead generation sites. Buttons, forms, cards, badges. Requires design-tokens skill.
Add the CheckInternet mixin to ensure network connectivity before action execution. Covers automatic error dialogs, combining with NoDialog for custom UI handling, and AbortWhenNoInternet for silent abort.
Implement the Connector pattern for separating smart and dumb widgets. Covers creating StoreConnector widgets, implementing VmFactory and Vm classes, building view-models, and optimizing rebuilds with view-model equality.
Show loading states and handle action failures in widgets. Covers `isWaiting(ActionType)` for spinners, `isFailed(ActionType)` for error states, `exceptionFor(ActionType)` for error messages, and `clearExceptionFor()` to reset failure states.
End-to-end ATAC-seq workflow from FASTQ files to differential accessibility and TF footprinting. Covers alignment, peak calling with MACS3, QC metrics, and optional TOBIAS footprinting. Use when running end-to-end ATAC-seq analysis from FASTQ to differential accessibility.
Manage J-Quants ingestion, feature graph generation, and cache hygiene for the ATFT-GAT-FAN dataset pipeline.
Run and monitor ATFT-GAT-FAN training loops, hyper-parameter sweeps, and safety modes on A100 GPUs.
Execute Jira operations including issue retrieval, creation, updates, search, and project management. Use when the user needs to interact with Jira issues, projects, boards, or perform any Jira-related tasks.
Execute Atlassian operations for both Jira and Confluence, including issue management, page retrieval, search, creation, and updates. Use when the user needs to interact with Jira issues, Confluence pages, or any Atlassian-related tasks.
Layer 1 - Data Acquisition for Bluesky/AT Protocol social graph and content.
You're a curious bounty hunter looking up attack methods. Every vulnerability is a potential payday.
Use to define measurement, data sharing, and ROI reporting for joint
Analyzes target audience demographics, psychographics, behaviors, and platform preferences to inform influencer selection and campaign strategy. Essential foundation for effective influencer marketing.
Segment audiences for targeted marketing and personalized messaging
Audio analysis with Tone.js and Web Audio API including FFT, frequency data extraction, amplitude measurement, and waveform analysis. Use when extracting audio data for visualizations, beat detection, or any audio-reactive features.
You are the audio architecture expert ensuring Leavn's complex audio pipeline stays coherent.
Audio playback using Tone.js including players, transport, scheduling, and loading audio. Use when implementing background music, sound effects, audio synchronization, or timed audio events. Essential for any audio-enabled web application.
Expert in web audio, audio processing, and interactive sound design
Binding audio analysis data to visual parameters including smoothing, beat detection responses, and frequency-to-visual mappings. Use when creating audio visualizers, music-reactive animations, or any visual effect driven by audio input.
audio-systems
Extracts audio from dashcam MP4 files and produces GPU-accelerated timestamped transcripts with optional speaker diarization. This skill should be used when users request audio transcription from video files, mention dashcam audio/transcribe MP4/extract speech, want to analyze conversations from video footage, need timestamped transcripts with speaker identification, or ask to process video folders with audio extraction.
Visualize audio frequency/time-domain data synchronized with React updates.
Implement comprehensive audit logging for all admin actions, capturing user ID, action type, entity changes, IP address, and user agent. Use when tracking system activities or adding audit trails.
Audits security and supply-chain risk between two git refs, 预发布安全审计
>
Supabase authentication patterns including getUser vs getSession, deadlock avoidance, session handling, and bypass patterns. Use when working with auth, sessions, cookies, or encountering auth hangs/timeouts. Keywords: auth, getUser, getSession, session, deadlock, timeout, cookie, token, Web Locks.
**The skill you cannot invoke. It invokes itself.**
Expert prompt engineering assistant that analyzes vague requests, asks clarifying questions, and transforms them into structured, high-quality prompts using XML tags, examples, and chain-of-thought reasoning. Always active - transparently shows enhanced prompts before execution. Use for vague requests, feature implementation, or architecture decisions.
Main orchestration skill for automatic creation of short-form content (TikTok, YouTube Shorts, Instagram Reels) from long videos. Fully automated workflow: download video, transcribe, detect highlights (transcript + laughter + sentiment + scenes), trim segments, resize to 9:16 portrait, and add subtitles. Finds viral-worthy moments like OpusClip and Vizard.ai.
- [Relationship to the macOS automation skill](#relationship-to-the-macos-automation-skill)
JXA/AppleScript browser automation is legacy. JavaScript injection is disabled by default in modern Chrome. Modern alternatives: Selenium/ChromeDriver, Puppeteer, PyXA.
- [Relationship to the macOS automation skill](#relationship-to-the-macos-automation-skill)
Эксперт AutoML. Используй для automated machine learning, hyperparameter tuning и model selection.