All Skills

Audit and improve CLAUDE.md, rules files, and auto memory in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md or rules files. Scans for all CLAUDE.md, .claude/rules/, and auto memory files, evaluates quality, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance", "project memory optimization", "memory lint", or "rules management".

Guided framework for structuring academic Discussion sections

Guide to buying USDC via USDCtoFiat with live platform availability

Split large files into manageable chunks following language-specific best practices

Step-by-step guide to creating USDC deposits on USDCtoFiat, with live platform and market data

Create compelling investor one-pagers and email briefs that capture attention and get meetings. Distill your pitch into scannable, high-impact documents with traction-focused cold emails and distribution strategy.

Update existing .ai-context files based on codebase changes. Use when the user says "update context", "sync context", "refresh ai context", or "context update". Detects new dependencies, structure changes, and patterns.

Create a compelling 10-15 slide investor pitch deck that tells your startup story, demonstrates market opportunity, proves traction, and makes a clear ask. Build a deck that gets meetings, progresses conversations, and closes rounds.

Add images, diagrams, and video embeds to an existing blog post.

Capture structured documentation from conversation context - decisions, technical references, discussion summaries, how-to guides, and architecture docs. Auto-structures content, generates tags, and writes to .things/ for search and cross-reference.

Senior backend developer specializing in TypeScript and Rust backends. Starts projects as Bun/Hono/Drizzle/Zod monoliths, then extracts Rust/Actix microservices post-MVP. Expert in SQL optimization for memory, security, and cost efficiency. Uses PostgreSQL primarily, with gRPC/REST APIs and RabbitMQ/Kafka for messaging. Use for API development, database design, microservice architecture, performance optimization.

Web scraping, screenshots, form filling, file downloads/uploads, Google/DuckDuckGo image search, YouTube video downloading, and TikTok video downloading.

This skill should be used when the user asks about Hotwire, Turbo Drive, Turbo Frames, Turbo Streams, Stimulus controllers, frontend interactivity, server-rendered HTML updates, websocket updates, progressive enhancement, data attributes, importing JavaScript modules, or building interactive UIs without React/Vue. Also use when discussing the "HTML over the wire" approach or NO BUILD philosophy. Examples:

Add support for a new AI tool with adapters, CLI, completion, and tests.

Log what happened after delivering a pitch -- capture results, reflections, and push learnings back to audience profiles and professional profile. Use when user says 'log outcome', 'how did it go', 'it went well/badly'.

Create custom deliverable types with templates, tool requirements, and instructions for the deliverable agent. Use when user says 'create deliverable type', 'add a type', 'custom deliverable'.

This skill should be used when the user asks about testing Rails applications, Minitest, test-driven development (TDD), unit tests, integration tests, system tests, fixtures, factories, mocking, stubbing, test coverage, continuous integration, test organization, or Rails testing best practices. Also use when discussing testing philosophy, test speed, or debugging failing tests. Examples:

READ this skill when implementing or configuring animation-style shaders (Toon/Cel Shaders) — including outlines, rim lighting, toon shading, MatCap, emission, dissolve, hatching, or any stylized rendering effect. Contains preset styles and feature-to-reference mappings for lilToon, Poiyomi, UTS2, RToon, SToon, and ToonShadingCollection. Works as a domain knowledge plugin alongside workflow skills (OpenSpec, SpecKit) or plan mode of an agent.

Use when you want to systematically upgrade a skill's quality through TDD-based evaluation. 복수 평가 + 신뢰구간으로 유의미한 향상 검증.

Conduct benchmarking analysis comparing performance against peers, industry standards, and best-in-class organizations. Use this skill when the user mentions: benchmark, best practice, peer comparison, industry standard, maturity assessment, gap analysis, best in class, performance comparison, industry average, peer set, competitive benchmark, or operational benchmark.

Senior desktop developer specializing in cross-platform apps using Tauri 2.0 (preferred) or Electron when needed. Expert in Rust and TypeScript, with deep knowledge of Linux, Windows, and macOS platform specifics. Leverages existing Frontend codebase for desktop apps. Use for desktop application development, native OS integrations, system tray apps, file system access, and cross-platform distribution.

Autonomous task management via git-native-issue. When Claude needs to track work, create issues, update progress, or close completed tasks, this skill provides the full protocol and CLI reference. Activates when task management context is detected.

This skill should be used when the user asks about Rails routing, URL patterns, RESTful routes, route helpers, controller actions, strong parameters, before_action callbacks, rendering, redirecting, the params hash, nested resources, route constraints, controller concerns, or request/response handling. Also use when discussing how URLs map to code, route organization, or controller best practices. Examples:

Generate or refine deliverables for an existing campaign goal, run Q&A prep sessions, and advance prep level. Use when user says 'prep for', 'practice my pitch', 'refine my strategy', 'run me through it'.