Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
weekly-report
MLシステム開発共同研究プロジェクトの週報を自動作成するスキル。先週の週報をベースにNotionから今週の更新情報を収集し、差分を反映して新しい週報をNotionに発行する。Use when: (1) 週報を作成したい、(2) weekly reportを作りたい、(3) 週次報告を作成したい、(4) create weekly report
majiayu000/claude-skill-registry 163
-
neon-db-setup
Set up Neon Serverless PostgreSQL database, configure connection strings, manage database credentials, and integrate with SQLModel ORM. Use when setting up database infrastructure for Phase 2 or configuring database connections.
majiayu000/claude-skill-registry 163
-
policyengine-design
PolicyEngine visual identity - colors, fonts, logos, and branding for web apps, calculators, charts, and research
majiayu000/claude-skill-registry 163
-
unit-testing-requirement
majiayu000/claude-skill-registry 163
-
signal-party
Parallel metrics collection using G-6 SIGNAL. Deploy 6 probes to gather metrics from all sources for data-driven decisions.
majiayu000/claude-skill-registry 163
-
authentic-voice
Transform AI-sounding writing into natural, human prose. Use when creating or editing any written content—articles, essays, reports, emails, social posts, scripts, or marketing copy—to avoid patterns that signal AI authorship. Triggers on requests to "make it sound human," "less AI," "more natural," improve voice/tone, or any writing task where authentic style matters.
majiayu000/claude-skill-registry 163
-
sniffable-python
Structure Python so LLMs can understand it in 50 lines.
majiayu000/claude-skill-registry 163
-
feature-engineering-kit
Auto-generate features with encodings, scaling, polynomial features, and interaction terms for ML pipelines.
majiayu000/claude-skill-registry 163
-
dev-workflow-planning
Structured development workflows using /brainstorm, /write-plan, and /execute-plan patterns. Transform ad-hoc conversations into systematic project execution with hypothesis-driven planning, incremental implementation, and progress tracking.
majiayu000/claude-skill-registry 163
-
semtech
Semtech Corporation MPN encoding patterns, LoRa transceiver decoding, ESD protection, and handler guidance. Use when working with Semtech components or SemtechHandler.
majiayu000/claude-skill-registry 163
-
worldmat-tidar
worldmat-tidar
majiayu000/claude-skill-registry 163
-
quality-code-review
Perform systematic self-review of code changes before commits using structured checklist. Validates architecture boundaries, code quality, test coverage, documentation, and project-specific anti-patterns. Use before committing, creating PRs, or when user says "review my changes", "self-review", "check my code". Adapts to Python, JavaScript, TypeScript, Go, Rust projects.
majiayu000/claude-skill-registry 163
-
respectfully
Wraps any prompt with a reminder to respect CLAUDE.md files
majiayu000/claude-skill-registry 163
-
anndata
This skill should be used when working with annotated data matrices in Python, particularly for single-cell genomics analysis, managing experimental measurements with metadata, or handling large-scale biological datasets. Use when tasks involve AnnData objects, h5ad files, single-cell RNA-seq data, or integration with scanpy/scverse tools.
majiayu000/claude-skill-registry 163
-
sync
Real-time sync with Supabase, Loro CRDT, and IndexedDB. Use when working on files in src/lib/sync/.
majiayu000/claude-skill-registry 163
-
theming-components
Provides design token system and theming framework for consistent, customizable UI styling across all components. Covers complete token taxonomy (color, typography, spacing, shadows, borders, motion, z-index), theme switching (CSS custom properties, theme providers), RTL/i18n support (CSS logical properties), and accessibility (WCAG contrast, high contrast themes, reduced motion). This is the foundational styling layer referenced by ALL component skills. Use when theming components, implementing light/dark mode, creating brand styles, customizing visual design, ensuring design consistency, or supporting RTL languages.
majiayu000/claude-skill-registry 163
-
radflow-compliance
Audit and fix AI-generated or existing code for RadOS design compliance. Use after generating UI code or when reviewing PRs. Catches common mistakes like wrong shadows, hardcoded colors, missing components, and incorrect radius hierarchy.
majiayu000/claude-skill-registry 163
-
component-refactoring
Refactor high-complexity React components. Use when complexity is high, when the user asks for code splitting, hook extraction, or complexity reduction.
majiayu000/claude-skill-registry 163
-
V3 QE DDD Architecture
Domain-Driven Design architecture for Agentic QE v3. Implements modular, bounded context architecture with clean separation of concerns for quality engineering domains.
majiayu000/claude-skill-registry 163
-
label-context-mapping
Maps GitHub labels to Skills and Context documents. Use when creating issues (github-issue-creation) or working on issues (fix-issue command).
majiayu000/claude-skill-registry 163
-
agent-iot-engineer
Expert IoT engineer specializing in connected device architectures, edge computing, and IoT platform development. Masters IoT protocols, device management, and data pipelines with focus on building scalable, secure, and reliable IoT solutions.
majiayu000/claude-skill-registry 163
-
gworkspace-mcp
gworkspace-mcp - Google Workspace MCP Integration with Temporal Consistency
majiayu000/claude-skill-registry 163
-
audit-process
Run a comprehensive multi-stage automation audit with parallel agents
majiayu000/claude-skill-registry 163
-
gemini-cli
Google Gemini CLI orchestration for AI-assisted development. Capabilities: second opinion/cross-validation, real-time web search (Google Search), codebase architecture analysis, parallel code generation, code review from different perspective. Actions: query, search, analyze, generate, review with Gemini. Keywords: Gemini CLI, second opinion, cross-validation, Google Search, web research, current information, parallel AI, code review, architecture analysis, gemini prompt, AI comparison, real-time search, alternative perspective, code generation. Use when: needing second AI opinion, searching current web information, analyzing codebase architecture, generating code in parallel, getting alternative code review, researching current events/docs.
majiayu000/claude-skill-registry 163