Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
evaluating-skills-with-models
Evaluate skills by executing them across sonnet, opus, and haiku models using sub-agents. Use when testing if a skill works correctly, comparing model performance, or finding the cheapest compatible model. Returns numeric scores (0-100) to differentiate model capabilities.
majiayu000/claude-skill-registry 163
-
experiment-design-checklist
Generates a rigorous experiment design given a hypothesis. Use when asked to design experiments, plan experiments, create an experimental setup, or figure out how to test a research hypothesis. Covers controls, baselines, ablations, metrics, statistical tests, and compute estimates.
majiayu000/claude-skill-registry 163
-
devflow-tdd-enforcer
Enforces TDD order in TASKS.md - Tests MUST be marked complete before Implementation tasks. Blocks violations in real-time.
majiayu000/claude-skill-registry 163
-
accessibility-compliance
Implement WCAG 2.1 AA accessibility compliance with ARIA labels, keyboard navigation, screen reader support, and color contrast. Use when ensuring accessibility or fixing a11y issues.
majiayu000/claude-skill-registry 163
-
modern-web-app-architecture-ratacat-claude-skills-7b61b160
majiayu000/claude-skill-registry 163
-
architecture-review
Peer review architecture for quality, risks, and optimization opportunities. Analyzes scalability bottlenecks, security vulnerabilities, performance optimization, technology fit, and provides prioritized recommendations. Use when reviewing proposed architecture documents for quality assurance, risk identification, or architectural decision validation.
majiayu000/claude-skill-registry 163
-
td-portman
Ljung-Box portmanteau tests for model diagnostics and residual analysis
majiayu000/claude-skill-registry 163
-
benchmarking
Performance benchmarking practices using pytest-benchmark. Activated when working with benchmarks, performance testing, or optimization.
majiayu000/claude-skill-registry 163
-
targeted-testing
Pick and run the smallest correct validation step (checks → focused Jest by path → broader suites). Use whenever you modify code and need confidence quickly.
majiayu000/claude-skill-registry 163
-
matrix-theory-specialist
Advanced matrix theory expert covering spectral theory, matrix factorizations, and numerical linear algebra
majiayu000/claude-skill-registry 163
-
requirements-engineering
Transform stakeholder needs into structured, testable specifications with user stories, acceptance criteria, and business rules. Use when: (1) creating requirements documents, (2) writing user stories with acceptance criteria, (3) defining business rules and process flows, (4) analyzing feature requests.
majiayu000/claude-skill-registry 163
-
generating-tdd-tests
RGRCサイクルとBaby Steps方法論を用いたTDD。トリガー: TDD, テスト駆動開発, Red-Green-Refactor, Baby Steps, test generation, テスト生成, テスト設計, テストケース, boundary value, 境界値分析, coverage, カバレッジ, unit test
majiayu000/claude-skill-registry 163
-
space-entities-expert
Specialized skill for profiling commercial companies and private research institutions involved in lunar exploration.
majiayu000/claude-skill-registry 163
-
testing-workflows
Run, debug, and structure tests for this Go project (unit + integration), including generation prerequisites. Use when changing domain logic, repositories, HTTP handlers, or migrations.
majiayu000/claude-skill-registry 163
-
library-detection
Detect project stack from package manifests (package.json, pyproject.toml, go.mod, Cargo.toml, pubspec.yaml, CMakeLists.txt). Auto-identify frameworks, test tools, and build systems for onboarding.
majiayu000/claude-skill-registry 163
-
cocoapods-publishing-workflow
Use when publishing CocoaPods libraries to CocoaPods Trunk. Covers pod trunk registration, podspec validation, version management, and publishing best practices for successful library distribution.
majiayu000/claude-skill-registry 163
-
validation-frameworks
Problem and solution validation methodologies, assumption testing, and MVP validation experiments
majiayu000/claude-skill-registry 163
-
coverage-strategist
Defines ROI-based coverage targets with critical path identification, layer-specific targets, and explicit "don't test this" guidelines. Use for "test coverage", "coverage strategy", "test priorities", or "coverage targets".
majiayu000/claude-skill-registry 163
-
a2a-sdk-patterns
SDK installation and setup patterns for Agent-to-Agent Protocol across Python, TypeScript, Java, C#, and Go. Use when implementing A2A protocol, setting up SDKs, configuring authentication, or when user mentions SDK installation, language-specific setup, or A2A integration.
majiayu000/claude-skill-registry 163
-
delegate-climpt-agent
Use when user mentions 'climpt' or 'climpt-agent', or gives project-specific instructions where general knowledge is insufficient. Climpt provides pre-configured prompts tailored to the project's workflow.
majiayu000/claude-skill-registry 163
-
voice-apply
Applies a voice profile to transform content. Use when user asks to write in a specific voice, match a tone, apply a style, or transform content to sound like a particular voice profile.
majiayu000/claude-skill-registry 163
-
spec-initializer
Initialize spec plugin configuration
majiayu000/claude-skill-registry 163
-
tester-detective
⚡ PRIMARY TOOL for: 'what's tested', 'find test coverage', 'audit test quality', 'missing tests', 'edge cases', 'test patterns'. Uses claudemem v0.3.0 AST with callers analysis for test discovery. GREP/FIND/GLOB ARE FORBIDDEN.
majiayu000/claude-skill-registry 163
-
Testing Unit Tests
Your approach to handling testing unit tests. Use this skill when working on files where testing unit tests comes into play.
majiayu000/claude-skill-registry 163