Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
safe-refactoring
Systematic code refactoring while preserving all external behavior.
Use when identifying code smells, planning refactoring sequences,
executing safe structural improvements, or validating behavior preservation.
Includes code smell catalog (reference.md) and refactoring execution protocol.
majiayu000/claude-skill-registry 163
-
aico-frontend-implement
Execute frontend implementation with TDD. Read all constraint files before coding, write failing test first, verify after each step.
Use this skill when:
- User asks to "implement this", "implement the plan", "start implementation", "execute plan"
- Have an implementation plan ready and need to execute it
- Executing steps from /frontend.plan output
- User says "start coding", "write the code", "begin implementation"
- User asks to "use TDD", "write test first", "test-driven" for frontend code
- User asks to "write tests", "add tests", "create tests"
- Fixing UI bugs (write failing test that reproduces bug first)
TDD Iron Law: NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST
TDD Cycle: RED (write failing test) → Verify fails → GREEN (minimal code) → Verify passes → REFACTOR
Prerequisites:
- MUST have task file in docs/reference/frontend/tasks/ (use /frontend.tasks first if not exists)
- MUST read design-system.md, constraints.md, and design spec before writing any code.
Flow: Check Task File → Read Constraints → TDD Cycle (RED→GREEN→REFACTOR) → Verify Each → Test → Update Task Status → Notify PM
majiayu000/claude-skill-registry 163
-
code-flow-viz
用于梳理和可视化代码流程，生成清晰的 ASCII 流程图、数据流图和表格分析。适用于已有代码的梳理、新功能设计的说明、以及技术文档的编写。
majiayu000/claude-skill-registry 163
-
n8n-code-javascript
Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting Code node errors, or choosing between Code node modes.
majiayu000/claude-skill-registry 163
-
skill-upgrader
Upgrade any skill to v5 Hybrid format using decision theory + modal logic
majiayu000/claude-skill-registry 163
-
skill-cookiecutterproject-slug
majiayu000/claude-skill-registry 163
-
multi-model-discovery
Use Gemini to find existing solutions before building from scratch. Leverages Google Search grounding to discover code examples, libraries, and best practices to avoid reinventing the wheel.
majiayu000/claude-skill-registry 163
-
tech-lead
Technical leadership and code review
majiayu000/claude-skill-registry 163
-
astro-images
Width-based responsive image patterns for Astro. Aspect ratio independent.
majiayu000/claude-skill-registry 163
-
ai-dev-orchestration
Coordinate multi-agent software delivery with guardrails for planning, implementation, testing, and release.
majiayu000/claude-skill-registry 163
-
logger-messages
Writes user-friendly logger messages in active voice for Simple History event logs. Fixes passive voice issues. Use when creating or modifying logger classes in loggers/ directory, writing getInfo() messages, fixing passive voice, reviewing log message clarity, or adding new events to the activity log.
majiayu000/claude-skill-registry 163
-
plan-management
Expert in creating, updating, and managing feature implementation plans. Use when creating new plans with /plan command, updating plan status, marking phases in_progress or completed, checking plan progress, or understanding plan structure. Ensures plans are created correctly and updated efficiently using the plan-update.py utility.
majiayu000/claude-skill-registry 163
-
game-experience-core
ゲームの「面白さ」を再現可能な構造として言語化するスキル。
以下の場面で使用: (1)新規ゲーム設計時に体験コアを定義する (2)既存ゲームの面白さを構造的に分析する (3)「ゲームの面白さを言語化したい」「体験を設計したい」と言われた時。
判断・行動・学習ループを中心に、リソース設計と失敗設計を含む包括的な体験定義書を生成する。
majiayu000/claude-skill-registry 163
-
render-info
Using the RendererInfo class in Blazor to detect rendering context and interactivity.
majiayu000/claude-skill-registry 163
-
analyze-video
Adds visual descriptions to transcripts by extracting and analyzing video frames with ffmpeg. Creates visual transcript with periodic visual descriptions of the video clip. Use when all files have audio transcripts present (transcript) but don't yet have visual transcripts created (visual_transcript).
majiayu000/claude-skill-registry 163
-
Code Template Library
Maintain and organize a curated library of code templates, boilerplate, and scaffolds for rapid project initialization
majiayu000/claude-skill-registry 163
-
roastplus-ui
ローストプラスアプリのUIデザインシステム。Tailwind CSS v4ベースの配色、コンポーネントパターン、レイアウト、アニメーションを提供。新規ページ作成、コンポーネント実装、デザイン一貫性チェックに使用。通常モードとクリスマスモードの両方に対応。
majiayu000/claude-skill-registry 163
-
rithum
Rithum B2B patterns and distribution API
majiayu000/claude-skill-registry 163
-
x-trend-architecture
Use when implementing X-Trend or attention-based trading models. Covers LSTM encoders, cross-attention, self-attention, sequence representations, entity embeddings, Variable Selection Networks, encoder-decoder patterns, Deep Momentum Networks, and interpretable predictions for trend-following strategies.
majiayu000/claude-skill-registry 163
-
wp-performance
Use when investigating or improving WordPress performance (backend-only agent): profiling and measurement (WP-CLI profile/doctor, Server-Timing, Query Monitor via REST headers), database/query optimization, autoloaded options, object caching, cron, HTTP API calls, and safe verification.
majiayu000/claude-skill-registry 163
-
wiql-queries
Build and execute WIQL (Work Item Query Language) queries for Azure DevOps. Use when the user wants to query work items, find bugs, list tasks, search by assignee, filter by state, find items in a sprint, or build custom work item queries. Use when user mentions "query", "find work items", "list bugs", "my tasks", "assigned to", "in sprint", or "WIQL".
majiayu000/claude-skill-registry 163
-
unknown-adelabdelgawad-support-center
majiayu000/claude-skill-registry 163
-
graphql-apollo-client
Build React apps with Apollo Client - queries, mutations, cache, and subscriptions
majiayu000/claude-skill-registry 163
-
notion-md-sync
Batch upload local Markdown files to Notion via Python script. Optimized for single or multiple files with zero token cost. Direct script execution bypasses LLM parsing, saving significant tokens on large files while preserving formatting (tables, code blocks, rich text).
majiayu000/claude-skill-registry 163