Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
rbac-security
Role-based access control (RBAC) patterns, authentication wrappers, authorization checks, input validation with Zod schemas, security boundaries, server action security, real-time message validation, preventing common vulnerabilities like XSS and SQL injection, and security best practices for ree-board project
majiayu000/claude-skill-registry 163
-
abaqus-export
Export Abaqus geometry and results. Use when user mentions exporting to STL, STEP, CSV, or generating input files for external use.
majiayu000/claude-skill-registry 163
-
anki-card-generator
Generate and manage Anki flashcards in Markdown format. Trigger when user asks to create flashcards, add knowledge cards, make Anki cards, or requests cards for learning programming concepts, algorithms, or technical knowledge.
majiayu000/claude-skill-registry 163
-
sc-improve
Apply systematic improvements to code quality, performance, maintainability, and cleanup. Use when refactoring code, optimizing performance, removing dead code, or improving project structure.
majiayu000/claude-skill-registry 163
-
variation-matrix
Generate all possible ad variations from modular components (hooks, bodies, CTAs) with prioritized testing order. Use when planning creative tests, maximizing existing assets, or building a systematic variation testing schedule.
majiayu000/claude-skill-registry 163
-
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
majiayu000/claude-skill-registry 163
-
github-archive
Investigate GitHub security incidents using tamper-proof GitHub Archive data via BigQuery. Use when verifying repository activity claims, recovering deleted PRs/branches/tags/repos, attributing actions to actors, or reconstructing attack timelines. Provides immutable forensic evidence of all public GitHub events since 2011.
majiayu000/claude-skill-registry 163
-
installing-skill-tracker
Installs Claude Code hooks for automatic skill usage measurement.
Use when setting up skill tracking infrastructure in a new project.
NOT when hooks are already installed (run verify.py to check).
majiayu000/claude-skill-registry 163
-
streaming
Use when building real-time chat interfaces, displaying incremental LLM responses, or streaming output from OpenAI, Anthropic, Google, or Ollama - async iteration with usage tracking works across all providers
majiayu000/claude-skill-registry 163
-
tmdb
Search movies/TV, get cast, ratings, streaming info, and personalized recommendations via TMDb API.
majiayu000/claude-skill-registry 163
-
validate-docs
기획 문서 정합성 검증 스킬. 화면 정의서, DB 정의서, 프로젝트 기획서, API 계약서 간의 일관성을 검사합니다. 사용 시기: (1) 문서 수정 후 정합성 확인 (2) 새 화면/기능 추가 후 누락 확인 (3) 전체 문서 리뷰 시 (4) /validate-docs 호출 시
majiayu000/claude-skill-registry 163
-
reviewing-dotnet-code
Reviews and generates .NET/C# code following Microsoft conventions and modern patterns.
Use when reviewing C# files, writing .NET code, refactoring, or when user mentions
"C#", ".NET", "dotnet", "csharp", or asks about naming conventions in .NET projects.
majiayu000/claude-skill-registry 163
-
resolve-pr-feedback
Check a PR for unresolved automated review feedback (Copilot, CodeRabbit) and invoke the appropriate resolver skills. Use when the user says "resolve PR feedback", "check PR comments", "address review comments", or wants to handle all automated review feedback on a PR.
majiayu000/claude-skill-registry 163
-
hecras_explore_gui
Explores the HEC-RAS GUI to document menus, dialogs, controls, and workflows
using win32com automation with screenshot capture. Use when needing to discover
menu structure, document dialog controls, capture screenshots for documentation,
or explore unfamiliar GUI elements in HEC-RAS.
Triggers: explore GUI, screenshot, capture dialog, document menu, HEC-RAS interface,
discover controls, GUI automation, menu exploration, dialog documentation, visual documentation.
majiayu000/claude-skill-registry 163
-
github-access
Access GitHub repositories programmatically using gh CLI or REST API. Use this skill when needing to interact with GitHub issues, pull requests, workflows, discussions, or actions. The skill automatically adapts based on available tools (gh CLI or curl) and requires GH_TOKEN for authentication.
majiayu000/claude-skill-registry 163
-
ops-arango
Manage ArangoDB operations including backups with automatic retention, health checks, embedding gap detection, duplicate detection, and integrity verification. Works with local or containerized ArangoDB.
majiayu000/claude-skill-registry 163
-
legal-summary-html
Создание интерактивных HTML-документов для юридических и аналитических материалов — резюме арбитражных решений, процессуальных приказов, отчётов, аналитических записок. Использовать для создания красивых mobile-first HTML-документов с аккордеонами, таймлайнами, навигацией и профессиональным дизайном в сине-золотой цветовой гамме.
majiayu000/claude-skill-registry 163
-
create-observability-config
Setup observability platform configuration (Datadog, Prometheus, Splunk) with REQ-* dashboards and alerts. Creates monitors for each requirement with SLA tracking. Use when deploying to production or setting up monitoring.
majiayu000/claude-skill-registry 163
-
afferent-reactive-universe-levels
Fix universe level mismatch errors when defining Lean 4 structures containing Reactive.Event
or Reactive.Dynamic types in Afferent/Canopy widgets. Use when: (1) compiler error "Type 1
of sort Type 2 but expected Type of sort Type 1", (2) WidgetM won't accept your result
structure, (3) structure contains Reactive.Event Spider or Reactive.Dynamic Spider fields.
The fix is to place `open Reactive Reactive.Host` BEFORE structure definitions.
majiayu000/claude-skill-registry 163
-
manim-composer
Trigger when: (1) User wants to create an educational/explainer video, (2) User has a vague concept they want visualized, (3) User mentions "3b1b style" or "explain like 3Blue1Brown", (4) User wants to plan a Manim video or animation sequence, (5) User asks to "compose" or "plan" a math/science visualization.
Transforms vague video ideas into detailed scene-by-scene plans (scenes.md). Conducts research, asks clarifying questions about audience/scope/focus, and outputs comprehensive scene specifications ready for implementation with ManimCE or ManimGL.
Use this BEFORE writing any Manim code. This skill plans the video; use manimce-best-practices or manimgl-best-practices for implementation.
majiayu000/claude-skill-registry 163
-
inspector-customization
Create and customize inspector panels for node editors. Use when implementing custom inspector tabs, settings panels, node-specific inspectors, or using inspector UI components.
majiayu000/claude-skill-registry 163
-
py-pydantic-patterns
Pydantic v2 patterns for validation and serialization. Use when creating schemas, validating data, or working with request/response models.
majiayu000/claude-skill-registry 163
-
skill-model-updater
Update model references in skill files when new Claude models are released
majiayu000/claude-skill-registry 163
-
fetch-unresolved-comments
Fetch unresolved PR review comments using GitHub GraphQL API, filtering out resolved and outdated feedback.
majiayu000/claude-skill-registry 163