Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
zod-validation
Runtime type validation with Zod for schema definition, form validation, API contracts, and TypeScript type inference. Use when validating user input, defining API schemas, or building type-safe data pipelines. Triggers on zod, schema validation, form validation, type inference, runtime validation, typescript validation.
majiayu000/claude-skill-registry 163
-
lea
Use when writing or modifying Lea code - pipe-oriented functional language with tree-walk interpreter
majiayu000/claude-skill-registry 163
-
fullstack-guide
全栈开发规范百科全书 (React/TS/Node/Supabase). Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organization with features directory, performance optimization, and TypeScript best practices. Use when creating components, pages, features, fetching data, styling, routing, or working with frontend/backend code.
majiayu000/claude-skill-registry 163
-
AILANG Sprint Executor
Execute approved sprint plans with test-driven development, continuous linting, progress tracking, and pause points. Use when user says "execute sprint", "start sprint", or wants to implement an approved sprint plan.
majiayu000/claude-skill-registry 163
-
polars
Lightning-fast DataFrame library written in Rust for high-performance data manipulation and analysis. Use when user wants blazing fast data transformations, working with large datasets, lazy evaluation pipelines, or needs better performance than pandas. Ideal for ETL, data wrangling, aggregations, joins, and reading/writing CSV, Parquet, JSON files.
majiayu000/claude-skill-registry 163
-
strategic-sourcing
When the user wants to develop category strategies, execute sourcing events, or implement strategic procurement initiatives. Also use when the user mentions "category management," "sourcing strategy," "value levers," "should-cost analysis," "RFx management," "e-sourcing," "strategic procurement," or "category sourcing." For supplier evaluation, see supplier-selection. For spend analysis, see spend-analysis.
majiayu000/claude-skill-registry 163
-
cfn-error-management
Unified error handling, batching, and logging for CFN Loop. Use when you need to capture agent errors, batch multiple errors for processing, log structured error data, or categorize and recover from agent failures.
majiayu000/claude-skill-registry 163
-
terraform-troubleshooting
Debug and fix Terraform errors systematically. Use when encountering Terraform failures, state lock issues,
provider errors, syntax problems, or unexpected infrastructure changes. Includes debugging workflows, error
categorization, common GCP-specific issues, and recovery procedures.
majiayu000/claude-skill-registry 163
-
address-github-comments
Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI.
majiayu000/claude-skill-registry 163
-
shared-validation-feedback-loops
Type-check, lint, test, build validation sequence. Use proactively before every commit across all agents.
majiayu000/claude-skill-registry 163
-
denario
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.
majiayu000/claude-skill-registry 163
-
evaluate-diagram
majiayu000/claude-skill-registry 163
-
backend-patterns
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
majiayu000/claude-skill-registry 163
-
mybatis-debugging
majiayu000/claude-skill-registry 163
-
scripts-config
Utility scripts directory configuration (/scripts) for MetaSaver monorepos including setup automation, environment management, and cross-platform support. Includes 4 critical standards (setup scripts, cross-platform support, error handling, documentation). Use when creating or auditing /scripts directory with Node.js and shell utility scripts.
majiayu000/claude-skill-registry 163
-
triangle-metrics
Triangle Metrics Skill
majiayu000/claude-skill-registry 163
-
opportunity-scorer-vuralserhat86-antigravity-agentic-
majiayu000/claude-skill-registry 163
-
prd-v07-epic-scoping
Transform v0.6 specifications into context-window-sized work packages (EPICs) during PRD v0.7 Build Execution. Triggers on requests to create epics, scope work, break down implementation, or when user asks "create epics", "scope work", "break down work", "context window sizing", "what to build first?", "implementation planning", "epic breakdown". Consumes API-, DBT-, FEA-, ARC-. Outputs EPIC- entries with objectives, ID references, dependencies, and context windows. Feeds v0.7 Test Planning.
majiayu000/claude-skill-registry 163
-
Video Content Accessibility
Accessibility guidelines for video content including contrast, timing, and readable typography. Use this when designing video layouts, choosing colors/fonts, setting animation durations, or ensuring emoji and visual elements are accompanied by text alternatives.
majiayu000/claude-skill-registry 163
-
validate-mojo-patterns
Validate Mojo code patterns (out self, mut, List, etc.) against best practices. Use to ensure code follows project standards.
majiayu000/claude-skill-registry 163
-
create-bff-layer
Step-by-step guide for creating Backend for Frontend layers that aggregate multiple bounded contexts.
majiayu000/claude-skill-registry 163
-
bknd-protect-endpoint
Use when securing specific API endpoints in Bknd. Covers protecting custom HTTP triggers, plugin routes, auth middleware for Flows, checking permissions in custom endpoints, and role-based endpoint access.
majiayu000/claude-skill-registry 163
-
ralph-worker-techartist
Tech Artist worker loop - execute visual asset tasks assigned by coordinator
majiayu000/claude-skill-registry 163
-
say-ducklake-xor
Parallel thread/DuckLake discovery with XOR uniqueness from gay_seed. Finds "say" or MCP usage, cross-refs with all DuckDB sources, launches bounded parallel ops.
majiayu000/claude-skill-registry 163