Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
exa-upgrade-migration
Analyze, plan, and execute Exa SDK upgrades with breaking change detection.
Use when upgrading Exa SDK versions, detecting deprecations,
or migrating to new API versions.
Trigger with phrases like "upgrade exa", "exa migration",
"exa breaking changes", "update exa SDK", "analyze exa version".
majiayu000/claude-skill-registry 163
-
pinecone
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
majiayu000/claude-skill-registry 163
-
lint
Run formatting and linting checks on the codebase
majiayu000/claude-skill-registry 163
-
context7-skill
Access up-to-date, version-specific documentation and code examples from Context7. Use this skill to verify library and framework details.
majiayu000/claude-skill-registry 163
-
fix-todos
Intelligent TODO resolution with context-aware implementation
majiayu000/claude-skill-registry 163
-
mokai
majiayu000/claude-skill-registry 163
-
distributed-tracing
Implement distributed tracing with Jaeger and Tempo to track requests across microservices and identify performance bottlenecks. Use when debugging microservices, analyzing request flows, or implementing observability for distributed systems.
majiayu000/claude-skill-registry 163
-
github-pr-review
Comprehensive GitHub PR review with inline suggestions, approval/rejection criteria, and technology-agnostic checklists. Triggers when reviewing PRs, analyzing code changes, or when user requests PR review. ALWAYS approve or request changes after review.
majiayu000/claude-skill-registry 163
-
read-webpage-content-as-markdown
Read a webpage into cleaned markdown using curl + markitdown + codex exec. Use whenever asked to read a webpage or extract article content from a URL. Static HTML only; JS/client-rendered pages require a Playwright workflow.
majiayu000/claude-skill-registry 163
-
qutip
Quantum physics simulation library for open quantum systems. Use when studying master equations, Lindblad dynamics, decoherence, quantum optics, or cavity QED. Best for physics research, open system dynamics, and educational simulations. NOT for circuit-based quantum computing—use qiskit, cirq, or pennylane for quantum algorithms and hardware execution.
majiayu000/claude-skill-registry 163
-
doc-index-update
Maintain table of contents and index files across documentation. Use when adding, removing, or renaming documentation files.
majiayu000/claude-skill-registry 163
-
code-quality-guardian
Expert code reviewer that enforces best practices, clean code principles, strong typing (TypeScript), architecture guidelines, and security standards. Reviews PRs and code snippets for bugs, code smells, anti-patterns, maintainability risks, performance issues, and security vulnerabilities. Use when reviewing pull requests, analyzing code quality, conducting code audits, or improving TypeScript/JavaScript codebases.
majiayu000/claude-skill-registry 163
-
ask-multi
Present a multi-select question allowing multiple choices
majiayu000/claude-skill-registry 163
-
improve-flow
This skill should be used when users drop off mid-task, motivation fades, or experiences feel flat. Applies Peak-End Rule, Goal-Gradient Effect, and Zeigarnik Effect.
majiayu000/claude-skill-registry 163
-
dbt-coder
dbt (data build tool) patterns for model organization, incremental strategies, and testing.
majiayu000/claude-skill-registry 163
-
skill-creator
Create, update, and package Claude Code skills from scratch or from existing content. Use when the user wants to build a new skill directory with SKILL.md, scripts, references, and assets; update an existing skill; or package a skill into a distributable .skill file. Covers the full lifecycle: gather requirements, plan reusable resources, initialize via init_skill.py, implement SKILL.md and bundled resources, validate, package via package_skill.py, and iterate based on real usage.
majiayu000/claude-skill-registry 163
-
QE Chaos Resilience
Chaos engineering and resilience testing including fault injection, load testing, and system recovery validation.
majiayu000/claude-skill-registry 163
-
sequential-thinking
Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.
majiayu000/claude-skill-registry 163
-
kafka-producer-implementation
Implement type-safe Kafka producers for event streaming with msgspec serialization.
Use when building async/await producers that publish domain events (orders, transactions, etc.)
with schema validation, error handling, retry logic, and distributed tracing.
Handles producer configuration, idempotent writes, and graceful shutdown.
majiayu000/claude-skill-registry 163
-
ui-libraries-components
Integrate modern UI libraries and reusable components into the project.
majiayu000/claude-skill-registry 163
-
concurrent-rendering-orchestration
Design and validate complex concurrent rendering workflows using `useTransition`, `Suspense`, and selective hydration to preserve responsiveness under heavy workloads.
majiayu000/claude-skill-registry 163
-
secrets-scan-jwynia-agent-skills
majiayu000/claude-skill-registry 163
-
goal-setting
Use when establishing targets for defined metrics - validates metric is movable by team, assesses movement needed for company goals, evaluates aggressive vs conservative targets with trade-off analysis
majiayu000/claude-skill-registry 163
-
agentuity-cli-cloud-deployment-logs
View logs for a specific deployment. Requires authentication. Use for Agentuity cloud platform operations
majiayu000/claude-skill-registry 163