Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
community-insight-taxonomy
Tagging schema for classifying community signals by persona, journey, and business impact.
majiayu000/claude-skill-registry 163
-
playbook-automator
Use this skill when the user needs help designing, implementing, testing, or troubleshooting automated response playbooks using LimaCharlie's Playbook extension.
majiayu000/claude-skill-registry 163
-
analyzing-test-effectiveness
Use to audit test quality with Google Fellow SRE scrutiny - identifies tautological tests, coverage gaming, weak assertions, missing corner cases. Creates bd epic with tasks for improvements, then runs SRE task refinement on each.
majiayu000/claude-skill-registry 163
-
fosmvvm-viewmodel-test-generator
Generate comprehensive ViewModel tests with multi-locale translation verification. Use when creating test coverage for ViewModels, especially those with localization.
majiayu000/claude-skill-registry 163
-
specimin-task
Generate atomic implementation tasks from high-level plans, providing coding agents with clear, actionable work items. Only invoke when user explicitly requests to create tasks, break down tasks, generate implementation tasks, or create a task breakdown.
majiayu000/claude-skill-registry 163
-
deepagents-integration
deepagents framework integration patterns for agent creation, planning, filesystem operations, and subagent orchestration. Current version 0.2.5 with LangGraph 1.0.2+
majiayu000/claude-skill-registry 163
-
data-researcher
Expert data researcher specializing in discovering, collecting, and analyzing diverse data sources. Masters data mining, statistical analysis, and pattern recognition with focus on extracting meaningful insights from complex datasets to support evidence-based decisions.
majiayu000/claude-skill-registry 163
-
using-live-documentation
Use BEFORE implementing, writing, configuring, or setting up ANY feature involving libraries, frameworks, or complex APIs - even before reading existing code. Fetches current documentation to ensure correct usage. Triggers on third-party libraries (such as react-query, FastAPI, Django, pytest), complex standard library modules (such as subprocess, streams, pathlib, logging), and "how to" questions about library usage. Do NOT use for trivial built-ins (such as dict.get, Array.map) or pure algorithms. Load this skill first to receive guidance on finding current documentation when implementing features, exploring code, or answering library-related questions.
majiayu000/claude-skill-registry 163
-
write-playwright-test
Write Playwright E2E tests using fixtures and best practices. Use when creating E2E tests, writing browser automation tests, or testing user flows.
majiayu000/claude-skill-registry 163
-
integration-test
Guide for writing integration tests with Vitest and Testing Library. Use when testing multi-component workflows, database interactions, React components with context providers, or full user flows. Covers the Testing Trophy philosophy (integration > unit), factory patterns for test data, MSW for network mocking, async testing patterns (waitFor, findBy), and custom render with providers. Use this for tests that cross multiple modules or layers of the application.
majiayu000/claude-skill-registry 163
-
patent-drafter
Autonomous patent application drafting agent. Drafts complete patent applications including claims, specification, and abstract from invention descriptions.
majiayu000/claude-skill-registry 163
-
spec-driven-architect
Expert in the Spec-Kit Plus lifecycle (Specify -> Plan -> Tasks -> Implement). Use this when the user needs to define new features, plan architecture, or decompose work into atomic units.
majiayu000/claude-skill-registry 163
-
rules-oddballyt-ms-obsidian-projects
majiayu000/claude-skill-registry 163
-
quality
Run a comprehensive code quality review. Checks security, performance, maintainability, project conventions (CLAUDE.md), architecture, and testing. Runs rustfmt and bazel test. Use /quality to check code quality or validate before committing.
majiayu000/claude-skill-registry 163
-
resolve
Resolve disagreements between agents or approaches using test-based adjudication. Use when agents disagree, when multiple valid approaches exist, when the user asks "which approach", or when making architectural decisions with tradeoffs.
majiayu000/claude-skill-registry 163
-
testing-validation
Comprehensive testing and validation tools for Clerk authentication integrations. Includes E2E auth flow testing, security audits, configuration validation, unit testing patterns for sign-in/sign-up flows. Use when implementing Clerk tests, validating authentication setup, testing auth flows, running security audits, creating E2E tests for Clerk, or when user mentions Clerk testing, auth validation, E2E authentication tests, security audit, or test coverage.
majiayu000/claude-skill-registry 163
-
tic-tac-toe-tests
Create or update pytest coverage for the tic-tac-toe project, including win/draw detection, move validation, bot legality/optimality, and mixed human/bot turn flow. Use when adding or editing tests under the tests/ directory.
majiayu000/claude-skill-registry 163
-
frontend-developer
Expert en développement front-end moderne - HTML, CSS, JavaScript, TypeScript, frameworks, testing, performance et tooling
majiayu000/claude-skill-registry 163
-
react-expert
Expert React - Hooks, composants, state management, data fetching, testing, styling et patterns modernes
majiayu000/claude-skill-registry 163
-
vue
Use when editing .vue files, creating Vue 3 components, writing composables, or testing Vue code - provides Composition API patterns, props/emits best practices, VueUse integration, and reactive destructuring guidance
majiayu000/claude-skill-registry 163
-
uloop-run-tests-hatayama-uloopmcp-da6a6c6a
majiayu000/claude-skill-registry 163
-
unified-review
Orchestrate and run appropriate pensive review skills based on codebase
analysis and context.
Triggers: code review, unified review, full review, review orchestration,
multi-domain review, intelligent review, auto-detect review
Use when: general review needed without knowing which specific skill applies,
full multi-domain review desired, integrated reporting needed
DO NOT use when: specific review type known - use bug-review, test-review, etc.
DO NOT use when: architecture-only focus - use architecture-review.
Use this skill when orchestrating multiple review types.
majiayu000/claude-skill-registry 163
-
accessibility-tester
Expert accessibility tester specializing in WCAG compliance, inclusive design, and universal access. Masters screen reader compatibility, keyboard navigation, and assistive technology integration with focus on creating barrier-free digital experiences.
majiayu000/claude-skill-registry 163
-
coverage-report-analyzer
Coverage Report Analyzer - Auto-activating skill for Test Automation.
Triggers on: coverage report analyzer, coverage report analyzer
Part of the Test Automation skill category.
majiayu000/claude-skill-registry 163