Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
state-machine-driven-ui
Model complex UI flows using finite state machines to ensure deterministic behavior.
majiayu000/claude-skill-registry 163
-
fpga
FPGA development guidelines covering Vivado, SystemVerilog, timing closure, AXI interfaces, and hardware optimization.
majiayu000/claude-skill-registry 163
-
aws-patterns
AWS infrastructure patterns and best practices for Terraform. Provides VPC, IAM, S3, and security group scaffolds. Use when developing AWS infrastructure.
majiayu000/claude-skill-registry 163
-
midjourney-prompting
majiayu000/claude-skill-registry 163
-
form-security
Security patterns for web forms including autocomplete attributes for password managers, CSRF protection, XSS prevention, and input sanitization. Use when implementing authentication forms, payment forms, or any form handling sensitive data.
majiayu000/claude-skill-registry 163
-
rust-crate-creator
majiayu000/claude-skill-registry 163
-
fastmcp-server-setup
Create MCP (Model Context Protocol) servers using FastMCP Python SDK. Define tools that AI agents can call to perform task operations. Use when building MCP servers for Phase 3 AI chatbot integration.
majiayu000/claude-skill-registry 163
-
platform-frameworks
Use when tailoring content formats, hooks, and publishing mechanics for each social platform.
majiayu000/claude-skill-registry 163
-
efficiency-tracker
Tracks workflow status and generates a flow report.
majiayu000/claude-skill-registry 163
-
corder-code-templates
Generate code templates for common patterns: REST API endpoints, React components, database models, authentication, error handling. Use when implementing new features or creating boilerplate code.
This skill provides production-ready code templates:
- REST API endpoints (Express, FastAPI)
- React/Vue components with best practices
- Database models (Sequelize, TypeORM, Mongoose)
- Authentication middleware (JWT, OAuth)
- Error handling patterns
Triggers: "create API", "new component", "implement auth", "add model", "generate code", "コードテンプレート", "API作成", "コンポーネント作成"
majiayu000/claude-skill-registry 163
-
sdd-next
Task preparation skill for spec-driven workflows. Reads specifications, identifies next actionable tasks, and creates detailed execution plans. Use when ready to implement a task from an existing spec - bridges the gap between planning and coding.
majiayu000/claude-skill-registry 163
-
oauth-config-generator
Generate OAuth 2.0 configuration for social login providers (Google, GitHub, etc.). Triggers on "create oauth config", "generate oauth setup", "social login config", "oauth2 integration".
majiayu000/claude-skill-registry 163
-
figma-prototyping
Use when implementing Disney's 12 animation principles in Figma prototypes and Smart Animate
majiayu000/claude-skill-registry 163
-
gitlab-ci-job-configuration
Use when defining GitLab CI jobs, configuring scripts, setting up environments, or managing job dependencies. Covers job structure and execution options.
majiayu000/claude-skill-registry 163
-
data-export-excel
Export analysis results, data tables, and formatted spreadsheets to Excel files using openpyxl. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).
majiayu000/claude-skill-registry 163
-
syncpack-configuration
Use when setting up or configuring syncpack for a monorepo. Covers configuration files, workspace detection, and custom rule definitions for dependency version management.
majiayu000/claude-skill-registry 163
-
project-brief-writer
Transform rough project ideas into problem-focused briefs that preserve learning opportunities and feed into the Skills workflow (tech-stack-advisor -> deployment-advisor -> project-spinup).
majiayu000/claude-skill-registry 163
-
llm-architect
Expert LLM architect specializing in large language model architecture, deployment, and optimization. Masters LLM system design, fine-tuning strategies, and production serving with focus on building scalable, efficient, and safe LLM applications.
majiayu000/claude-skill-registry 163
-
Error Management
This skill should be used when the user asks about "Effect errors", "typed errors", "error handling", "Effect.catchAll", "Effect.catchTag", "Effect.mapError", "Effect.orElse", "error accumulation", "defects vs errors", "expected errors", "unexpected errors", "sandboxing", "retrying", "timeout", "Effect.cause", "TaggedError", "Schema.TaggedError", or needs to understand how Effect handles failures in the error channel.
majiayu000/claude-skill-registry 163
-
parallel-decompose
Decompose PRDs and Tech Specs into parallel-executable tasks with contracts, prompts, and dependency graphs. Use when breaking down a PRD for multi-agent execution.
majiayu000/claude-skill-registry 163
-
plan-then-execute
Frozen plans with human approval gates.
majiayu000/claude-skill-registry 163
-
multi-tool-pipeline
Advanced MCP skill demonstrating multi-tool orchestration with git repository analysis
majiayu000/claude-skill-registry 163
-
electron-chromium-upgrade
Guide for performing Chromium version upgrades in the Electron project. Use when working on the roller/chromium/main branch to fix patch conflicts during `e sync --3`. Covers the patch application workflow, conflict resolution, analyzing upstream Chromium changes, and proper commit formatting for patch fixes.
majiayu000/claude-skill-registry 163
-
tarot-mode
Use when session returns mode.type='tarot' - tarot archetypes collaborate via roundtable dialogue with instruction-engineering embedded
majiayu000/claude-skill-registry 163