This skill should be used when user wants to learn from their collected references, synthesize patterns across sources, or turn research into frameworks from curated reference collections (Are.na channels, bookmarks, saved articles).
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 →This skill should be used when user wants to learn from their collected references, synthesize patterns across sources, or turn research into frameworks from curated reference collections (Are.na channels, bookmarks, saved articles).
Use after completing a session to identify genuine learnings from mistakes, corrections, or rework - focuses only on patterns that were actually wrong, not things that worked correctly the first time
Guidance for extracting text-based game commands, moves, or inputs from video recordings using OCR and frame analysis. This skill applies when extracting user inputs from screen recordings of text-based games (Zork, interactive fiction), terminal sessions, or any video where typed commands need to be recovered. It covers OCR preprocessing, region-of-interest extraction, domain-aware validation, and deduplication strategies.
Extract and explain formulas used in Physical AI and Humanoid Robotics from text, lecture notes, or papers. Use when user asks to identify or understand relevant formulas.
Extract text from PDF files using PyMuPDF. Use this skill when you need to read the contents of a PDF file, such as a resume, report, or manual, into plain text for analysis or processing.
>
Extract wisdom, insights, and actionable takeaways from text sources. Use when asked to analyse, summarise, or extract key learnings from blog posts, articles, markdown files, or other text content.
**Typically runs automatically via SessionStart hook.**
Figmaデザインからデザイントークン（色、タイポグラフィ、スペーシング、シャドウ等）を抽出・整理するスキルです。
Figmaデザインからインタラクション仕様（hover状態、遷移、アニメーション、トリガー）を抽出するスキルです。
Locates, lists, filters, and extracts structured data from Claude Code native session logs. Supports both single and multiple session analysis.
Systematic AI extraction prompt design expert with Socratic methodology
Load, validate, and resolve FABER configuration and workflows with inheritance support
Native Fabric pattern execution for Claude Code. USE WHEN processing content with Fabric patterns (extract_wisdom, summarize, analyze_claims, threat modeling, etc.). Patterns run natively in Claude's context - no CLI spawning needed. Only use fabric CLI for YouTube transcripts (-y) or pattern updates (-U).
Verify factual claims against database sources
Reprend le pipeline depuis la dernière phase/task
Pipeline complet requirements → release
CI/CD: GitHub Actions, GitLab CI, Jenkins, ArgoCD, GitOps, monitoring.
Universal orchestrator: 54 skills, 1297 methodologies. Development, DevOps, AI/ML, Product, Marketing, PM, BA, UX, Research.
Complete fal.ai serverless deployment system. PROACTIVELY activate for: (1) Creating fal.App class, (2) GPU machine selection (T4/A10G/A100/H100), (3) setup() for model loading, (4) @fal.endpoint decorators, (5) Persistent volumes for weights, (6) Secrets management, (7) Scaling configuration (min/max concurrency), (8) Multi-GPU deployment, (9) fal deploy commands, (10) Local development with fal run. Provides: App structure, Dockerfile patterns, deployment commands, scaling config. Ensures production-ready serverless ML deployment.
Build comprehensive FAQ databases from support data, documentation, and user interactions
This skill should be used when implementing secure, reusable JWT verification dependency for FastAPI routes. It ensures strict user isolation and identity verification using Better Auth secrets.
This skill provides patterns for WebSockets, file uploads to S3, and email/notification services.
Use after research (Z01 files exist) to create implementation plan - follow structured workflow
Transform overwhelming client feature wish lists into structured MVP/Phase 2/Phase 3 plans with time estimates, preventing scope creep and creating profitable upsell opportunities.
基于 docs/ARCHITECTURE.md 的规范，安全地实现新功能或优化现有代码。
Analyze skill effectiveness through usage feedback, metrics analysis, and outcome assessment. Task-based operations for feedback collection, effectiveness measurement, trend analysis, and insight extraction. Use when analyzing skill effectiveness, measuring ROI, understanding usage patterns, or evaluating toolkit impact based on real usage data.
ux-feedback-patterns
Transform user feedback into structured Linear issues with AI-enhanced parsing for labels, priority, acceptance criteria, and estimates
Load minimal relevant context for the current task
fetching-library-docs
Advanced file finder with type detection and filesystem extraction for analyzing firmware and extracting embedded filesystems. Use when you need to analyze firmware files, identify file types, or extract ext2/3/4 or F2FS filesystems.
FFmpeg video and audio processing patterns. Use when transcoding video/audio, extracting clips, adding filters, merging media, creating thumbnails, or batch processing media files.
A complete system for writing fiction—from initial concept through final draft.
Clerk for Crown fiduciary breaches, fund mismanagement, conflicts of interest, and failure to protect reserve lands; use for Fiduciary_Duty_Negligence queue.
Extract structured fields from unstructured log data using OPAL parsing functions. Covers extract_regex() for pattern matching with type casting, split() for delimited data, parse_json() for JSON logs, and JSONPath for navigating parsed structures. Use when you need to convert raw log text into queryable fields for analysis, filtering, or aggregation.
Run ML model inference (YOLO, YOLOv8, CLIP, SAM, Detectron2, etc.) on FiftyOne datasets. Use when running models, applying detection, classification, segmentation, embeddings, or any model prediction task. Also use for end-to-end workflows that include importing data then running inference.
Parse Figma design files into structured screen hierarchies. Use when working with Figma API, extracting text/labels from design nodes, traversing node trees, detecting cover frames, or parsing screen IDs (AUTO_0001, PSET_0002, etc.).
figma-design-rule-extractor
Figma design-to-code, design system extraction ve component generation rehberi.
Extract and save Figma screenshots from Codex session logs when user needs to recover images captured by the Figma MCP server
创建和解压ZIP、TAR和GZIP压缩包，支持密码保护。
Reusable logic for categorizing files as Command, Agent, Skill, or Documentation based on structure and content analysis
Audit all filename and naming conventions in the codebase against CLAUDE.md standards and common patterns. Use when user asks to check naming conventions, audit filenames, find naming inconsistencies, or validate file naming patterns.
Convert files (PDF, images) to Base64 encoding with MIME type detection for API attachments. Use when you need to prepare file attachments for the FreeAgent API or any other API that requires Base64-encoded files.
Complete guide for implementing file uploads in IntelliFill with React-dropzone frontend, Multer backend, file validation, Bull queue processing, and security best practices
Production-grade secure file upload pipeline with multi-stage validation, malware scanning (ClamAV), hash-based duplicate detection, and race condition protection using distributed locks.
Passthrough filter agent. Calls data sub-agents, validates responses, returns only clean data.
fin-core
Complete and merge feature branch