Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
postgres-optimization
Unconventional PostgreSQL optimization techniques
majiayu000/claude-skill-registry 163
-
java-core
Core Java development patterns including code organization, modern features, performance patterns, and implementation verification
majiayu000/claude-skill-registry 163
-
pytorch-onnx
Exporting PyTorch models to ONNX format for cross-platform deployment. Includes handling dynamic axes, graph optimization in ONNX Runtime, and INT8 model quantization. (onnx, onnxruntime, torch.onnx.export, dynamic_axes, constant-folding, edge-deployment)
majiayu000/claude-skill-registry 163
-
calendly
Automated scheduling for meetings and appointments.
majiayu000/claude-skill-registry 163
-
supreme-mathematics-agentgptsmith-monadframework-a93c8a1c
majiayu000/claude-skill-registry 163
-
transformers
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
majiayu000/claude-skill-registry 163
-
Project Principles
Core architectural and code quality principles that guide all development decisions in the vm0 project
majiayu000/claude-skill-registry 163
-
modal
Guide for building serverless Python applications on Modal - a cloud platform for running AI/ML workloads, GPU-accelerated code, web endpoints, scheduled jobs, and batch processing with minimal configuration. Use when deploying Python code to Modal's infrastructure, running GPU inference, creating web APIs, processing data at scale, or building AI applications.
majiayu000/claude-skill-registry 163
-
hevy
Query workout data from Hevy including workouts, routines, exercises, and history. Use when user asks about their workouts, gym sessions, exercise progress, or fitness routines.
majiayu000/claude-skill-registry 163
-
bundle-analysis
Analyze and optimize JavaScript bundle size, identify large dependencies, and improve load times. Use when bundles are large, investigating performance issues, or optimizing frontend assets.
majiayu000/claude-skill-registry 163
-
Bug Fixing Assistant
Systematic debugging workflow for CircleTel - analyzes errors, identifies root causes, proposes fixes, and validates solutions with tests
majiayu000/claude-skill-registry 163
-
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
majiayu000/claude-skill-registry 163
-
update-changelog
Orchestrate complete changelog workflow. Invoke `init-changelog` (if needed), `edit-changelog`, and `cleanup-changelog` skills in sequence. Use when the user or agent needs to update the changelog.
majiayu000/claude-skill-registry 163
-
markitdown
Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.
majiayu000/claude-skill-registry 163
-
project-architect
**PROJECT ARCHITECT** - '새 프로젝트', '프로젝트 시작', '폴더 구조', '아키텍처 설계', '구조 잡아줘', '프로젝트 세팅' 요청 시 자동 발동. 프로 개발자 수준의 확장 가능한 프로젝트 구조 설계. 레이어 분리, 모듈화, 베스트 프랙티스 적용.
majiayu000/claude-skill-registry 163
-
frontend-ui
Frontend UI-specific patterns. For generic patterns, see: typescript, react-19, nextjs-15, tailwind-4. Trigger: When working inside src/react-app.
majiayu000/claude-skill-registry 163
-
signup-flow-cro
When the user wants to optimize signup, registration, account creation, or trial activation flows. Also use when the user mentions "signup conversions," "registration friction," "signup form optimization," "free trial signup," "reduce signup dropoff," or "account creation flow." For post-signup onboarding, see onboarding-cro. For lead capture forms (not account creation), see form-cro.
majiayu000/claude-skill-registry 163
-
container-optimize
Docker/container optimization for size, layers, caching, and security
majiayu000/claude-skill-registry 163
-
server-skills
Server-specific best practices for FastAPI, Celery, and Pydantic. Extends python-skills with framework-specific patterns.
majiayu000/claude-skill-registry 163
-
python3-development
The model must use this skill when : 1. working within any python project. 2. Python CLI applications with Typer and Rich are mentioned by the user. 2. tasked with Python script writing or editing. 3. building CI scripts or tools. 4. Creating portable Python scripts with stdlib only. 5. planning out a python package design. 6. running any python script or test. 7. writing tests (unit, integration, e2e, validation) for a python script, package, or application. Reviewing Python code against best practices or for code smells. 8. The python command fails to run or errors, or the python3 command shows errors. 9. pre-commit or linting errors occur in python files. 10. Writing or editing python code in a git repository.\n<hint>This skill provides : 1. the users preferred workflow patterns for test-driven development, feature addition, refactoring, debugging, and code review using modern Python 3.11+ patterns (including PEP 723 inline metadata, native generics, and type-safe async processing). 2. References to favored modules. 3. Working pyproject.toml configurations. 4. Linting and formatting configuration and troubleshooting. 5. Resource files that provide solutions to known errors and linting issues. 6. Project layouts the user prefers.</hint>
majiayu000/claude-skill-registry 163
-
fix-bad-practices
Fix bad coding practices identified by audit, following fail-fast principles
majiayu000/claude-skill-registry 163
-
graphql-architect
Master modern GraphQL with federation, performance optimization, and enterprise security. Build scalable schemas, implement advanced caching, and design real-time systems. Use PROACTIVELY for GraphQL architecture or performance optimization.
majiayu000/claude-skill-registry 163
-
ai-ad-prompt-structurer
majiayu000/claude-skill-registry 163
-
clay-advanced-troubleshooting
Apply Clay advanced debugging techniques for hard-to-diagnose issues.
Use when standard troubleshooting fails, investigating complex race conditions,
or preparing evidence bundles for Clay support escalation.
Trigger with phrases like "clay hard bug", "clay mystery error",
"clay impossible to debug", "difficult clay issue", "clay deep debug".
majiayu000/claude-skill-registry 163