Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
mock-infrastructure-engineer
Creates and optimizes MSW (Mock Service Worker) handlers for Playwright E2E tests, implementing handler caching, fixture management, and AI Gateway mocking patterns. Use when mock setup is slow or test data needs centralization.
d-oit/do-novelist-ai
-
task-decomposition
Break down complex tasks into atomic, actionable goals with clear dependencies and success criteria. Use this skill when you need to plan multi-step projects, coordinate agents, or decompose complex user requests into manageable sub-tasks.
d-oit/do-novelist-ai
-
testing-anti-patterns
Use when writing or changing tests, adding mocks, or tempted to add test-only methods to production code - prevents testing mock behavior, production pollution with test-only methods, and mocking without understanding dependencies
d-oit/do-novelist-ai
-
frontend-design-system
Design and refactor React/Tailwind frontends using the project design system. Use this Skill when working on UI components, pages, layouts, or UX improvements and you want distinctive, accessible, non-generic designs that avoid AI slop.
d-oit/do-novelist-ai
-
ci-optimization-specialist
Optimizes GitHub Actions CI/CD workflows through test sharding, intelligent caching, and workflow parallelization. Use when CI execution time exceeds limits, costs are too high, or workflows need parallelization.
d-oit/do-novelist-ai
-
ux-designer
Expert UX Designer that enforces flat, minimal design, strict accessibility (WCAG 2.1 AA), and collaborative design decisions. Use this skill for all UI/UX tasks to avoid "AI slop".
d-oit/do-novelist-ai
-
database-schema-manager
Manages LibSQL/Turso database schemas with Zod validation, creates migrations, and ensures type-safe database operations. Use when creating database tables, writing migrations, or implementing schema validation.
d-oit/do-novelist-ai
-
gemini-websearch
Performs web searches using Gemini CLI headless mode with google_web_search tool. Includes intelligent caching, result validation, and analytics. Use when searching for current information, documentation, or when the user explicitly requests web search.
d-oit/do-novelist-ai
-
debugger
Diagnose and fix runtime issues, errors, and bugs through systematic reproduction, root cause analysis, and targeted fixes. Use for debugging production issues, test failures, performance problems, and any type of software defect.
d-oit/do-novelist-ai
-
feature-module-architect
Scaffolds feature modules following feature-based architecture with colocation principle and 500 LOC file limit. Use when creating new features or refactoring large files into modular structure.
d-oit/do-novelist-ai
-
goap-agent
Invoke for complex multi-step tasks requiring intelligent planning and multi-agent coordination. Use when tasks need decomposition, dependency mapping, parallel/sequential/swarm/iterative execution strategies, or coordination of multiple specialized agents with quality gates and dynamic optimization.
d-oit/do-novelist-ai
-
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
d-oit/do-novelist-ai
-
skill-creator
Create new Claude Code skills with proper directory structure, SKILL.md file, and YAML frontmatter. Use this skill when you need to create a new reusable knowledge module for Claude Code.
d-oit/do-novelist-ai
-
frontend-dev-guidelines
Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSWR, file organization with features directory, shadcn/ui components, Tailwind CSS styling, Next.js App Router, performance optimization, and TypeScript best practices. Use when creating components, pages, features, fetching data, styling, routing, or working with frontend code.
Rylaa/claude-agent-workflows 2
-
figma-to-code
This skill handles pixel-perfect Figma design conversion to production code (React/Tailwind, SwiftUI, Vue, Kotlin) using Pixelbyte Figma MCP Server. It should be used when a Figma URL or design selection needs to be converted to production-ready code. The skill employs a 5-phase workflow with framework detection and routing to framework-specific agents.
Rylaa/claude-agent-workflows 2
-
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
ryanmoran/workspace
-
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
ryanmoran/workspace
-
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
ryanmoran/workspace
-
development-workflow
Use when starting work on features, bugs, or significant changes requiring multiple commits and coordination of design, implementation, testing, and documentation
ryanmoran/workspace
-
frontend-styleguide
Use when asked to create or edit style guides, design systems, component libraries, or update existing frontend components for web projects
wzkariampuzha/claude-skills
-
test-execution-manager
Use when running tests via test-runner subagents - delegates test execution to background agents with incremental timeout escalation
wzkariampuzha/claude-skills
-
plone-frontend-developer
Senior Plone Volto frontend engineering for debugging Volto add-ons, fixing UI bugs, adjusting blocks/components, and handling all Plone 6.1 + Volto 17 frontend tasks (theme, routing, tokens, build/test issues). Use when the request involves Volto/Plone frontend behavior, add-on code, or UI fixes.
avoinea/eea-website
-
plone-backend-developer
Senior Plone backend development for the EEA website. Use when working on Plone 6.1 server behavior, backend add-ons, Python code, configuration in `backend/develop/`, or when debugging backend bugs and tests.
avoinea/eea-website
-
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.
avoinea/eea-website