Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
universal-industry
Use when designing animations for any industry or when industry-specific guidelines do not apply
majiayu000/claude-skill-registry 163
-
using-neural-architectures
The architecture selection router for CNNs, Transformers, RNNs, GANs, GNNs by data modality and constraints
majiayu000/claude-skill-registry 163
-
security-patterns
Implement comprehensive security patterns to protect applications against OWASP Top 10 vulnerabilities including XSS, CSRF, SQL injection, authentication bypass, and data exposure. Use when handling user data, implementing authentication and authorization, validating input, encrypting sensitive data, preventing injection attacks, securing API endpoints, managing sessions and tokens, implementing rate limiting, configuring security headers, or building security-critical features that require defense-in-depth protection.
majiayu000/claude-skill-registry 163
-
competitive-analysis
Produce a Competitive Analysis Pack (competitive alternatives map, competitor landscape, differentiation & positioning hypotheses, battlecards, monitoring plan). Use for competitor research, competitive landscape, win/loss analysis, and positioning vs alternatives.
majiayu000/claude-skill-registry 163
-
marketing-experimentation
Systematic marketing experimentation process - discover concepts, generate hypotheses, coordinate multiple experiments, synthesize results, generate next-iteration ideas through rigorous validation cycles
majiayu000/claude-skill-registry 163
-
analyze-code-structure
Examine code organization and identify structural patterns. Use when reviewing module design.
majiayu000/claude-skill-registry 163
-
latex-setup
LaTeX environment setup on macOS. TRIGGERS - install LaTeX, MacTeX, Skim viewer, SyncTeX setup.
majiayu000/claude-skill-registry 163
-
help-system-architect
Design and generate the in-app help system: havainnepolku (visual guidance path) components, help mode (apua-tila), contextual help content, and searchable help index. Use when (1) creating or updating help pages, (2) building the havainnepolku breadcrumb-path component, (3) implementing help mode overlay, (4) generating help search index, (5) adding contextual tips to pages, (6) brainstorming which guidance paths to create. Triggers: "help system", "apua", "havainnepolku", "guidance path", "help mode", "apua-tila", "contextual help", "help content", "help search", "user guidance", "breadcrumb path", "ohje", "opaste".
majiayu000/claude-skill-registry 163
-
lyric-writer
Write or review lyrics with professional prosody, rhyme craft, and quality checks
majiayu000/claude-skill-registry 163
-
one-pager-prd
Use when proposing new features/products, documenting product requirements, creating concise specs for stakeholder alignment, pitching initiatives, scoping projects before detailed design, capturing user stories and success metrics, or when user mentions one-pager, PRD, product spec, feature proposal, product requirements, or brief.
majiayu000/claude-skill-registry 163
-
sveltia-cms
Set up Sveltia CMS - lightweight Git-backed CMS successor to Decap/Netlify CMS (300KB bundle, 270+ fixes). Framework-agnostic for Hugo, Jekyll, 11ty, Astro. Prevents 10 documented errors.
Use when adding CMS to static sites, migrating from Decap CMS, or fixing OAuth, YAML parse, datetime timezone, GDPR font loading, or CORS/COOP errors.
majiayu000/claude-skill-registry 163
-
distributed-gummy
Orchestrate gummy-agents across distributed network using 'd' command for load-balanced, multi-host AI development
majiayu000/claude-skill-registry 163
-
story-based-framing
This skill should be used when describing patterns or anti-patterns for detection by LLM agents across any domain (code analysis, business processes, security audits, UX design, data quality, medical diagnosis, etc.). Uses narrative storytelling structure ("The Promise" → "The Betrayal" → "The Consequences" → "The Source") to achieve 70% faster pattern identification compared to checklist or formal specification approaches. Triggers when creating pattern descriptions for any systematic analysis, detection tasks, or when delegating pattern-finding to sub-agents.
majiayu000/claude-skill-registry 163
-
implementing-realtime-features
Implementing Supabase realtime subscriptions and live updates for StickerNest. Use when the user asks to add realtime, live updates, presence, subscriptions, postgres_changes, broadcast channels, or sync data across tabs/devices. Covers Supabase Realtime, EventBus integration, and subscription lifecycle.
majiayu000/claude-skill-registry 163
-
rendering-with-drawingvisual
Implements lightweight rendering using WPF DrawingVisual with ContainerVisual, VisualCollection, and DrawingContext. Use when rendering large-scale graphics, charts, game graphics, or custom visuals.
majiayu000/claude-skill-registry 163
-
shownotes-generator
Generate comprehensive "Shownotes" summaries from longform articles, papers, transcripts, videos, or audio content. Use when users request shownotes, episode summaries, content summaries with takeaways, or when they reference the mdynotes.com format. Creates structured summaries with metadata, hooks, takeaways, quotes, and references.
majiayu000/claude-skill-registry 163
-
context-methodology
Knowledge about the context branch methodology for separating AI configuration from project code using git worktrees. Use when users ask about worktree structure, branch organization, or the separation of concerns pattern.
majiayu000/claude-skill-registry 163
-
triton-deploy
NVIDIA Triton Inference Server 배포 및 관리. "triton 서버", "triton 실행", "모델 서빙", "inference server" 요청 시 활성화됩니다.
majiayu000/claude-skill-registry 163
-
android-app-icon
Generate Android adaptive icons from Iconify's 200k+ open source icons
majiayu000/claude-skill-registry 163
-
wiz-dev
wizプロジェクト開発支援スキル。specs/ディレクトリの仕様書を参照し、TODOタスクを実装する。
使用タイミング: (1) wizプロジェクトの開発作業、(2) specs/のTODOを進めたい時、
(3) 「次のタスク」「TODO」「実装して」などの開発リクエスト時。
作業完了後はdocs/を更新する。
majiayu000/claude-skill-registry 163
-
faion-testing-developer
Testing: unit, integration, E2E, TDD, mocking, security testing.
majiayu000/claude-skill-registry 163
-
encrypting-and-decrypting-data
This skill enables Claude to encrypt and decrypt data using various algorithms provided by the encryption-tool plugin. It should be used when the user requests to "encrypt data", "decrypt a file", "generate an encrypted file", or needs to secure sensitive information. This skill supports various encryption methods and ensures data confidentiality. It is triggered by requests related to data encryption, decryption, or general data security needs.
majiayu000/claude-skill-registry 163
-
Hacking Fundamentals
This skill should be used when the user asks to "understand hacking basics", "learn about hacker types", "understand network protocols", "learn DNS concepts", "understand attack types", or "explore security tool categories". It provides foundational cybersecurity knowledge.
majiayu000/claude-skill-registry 163
-
inv-runner
Python Invoke task automation for DTX website. This skill should be used when running repo commands, backend tests via Docker, database migrations, updating invoke tasks, Docker operations, or workflow automation. Supports dev/test/prod environments with run, exec, up, down commands. References docs/development/invoke-tasks.md for complete command reference.
majiayu000/claude-skill-registry 163