Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
evaluation-methodology
PluginEval quality methodology — dimensions, rubrics, statistical methods, and scoring formulas. Use this skill when understanding how plugin quality is measured, when interpreting a low score on a specific dimension, when deciding how to improve a skill's triggering accuracy or orchestration fitness, when calibrating scoring thresholds for your marketplace, or when explaining quality badges to external partners like Neon.
majiayu000/claude-skill-registry 163
-
taxjar-automation
Automate Taxjar tasks via Rube MCP (Composio). Always search tools first for current schemas.
majiayu000/claude-skill-registry 163
-
jpa-patterns
JPA/Hibernate patterns for entity design, relationships, query optimization, transactions, auditing, indexing, pagination, and pooling in Spring Boot.
majiayu000/claude-skill-registry 163
-
observers
Centralised classes that react to Eloquent model lifecycle events. Used for side effects that should always fire regardless of where a model is mutated — such as notifications, cache invalidation, and audit logging.
majiayu000/claude-skill-registry 163
-
vocal-recording
Master vocal recording techniques including microphone placement, studio setup, acoustic treatment, and signal processing for professional vocal captures.
majiayu000/claude-skill-registry 163
-
quality-gate-calculator
Calculates context-appropriate quality gate thresholds based on work type (Feature/Bug/Hotfix/Docs/Refactor). Ensures rigorous standards for features, pragmatic standards for hotfixes, and 100% test pass rate for all work.
majiayu000/claude-skill-registry 163
-
process-ngm-lectures
Process Google Docs from Drive through VectorShift pipeline and publish to NGM preview system
majiayu000/claude-skill-registry 163
-
gate-evaluator
Avalia quality gates entre fases do SDLC. Verifica artefatos obrigatorios,
criterios de qualidade, e aprovacoes necessarias antes de permitir transicao.
Use quando: transicao entre fases, verificacao manual de gate, auditoria de qualidade.
majiayu000/claude-skill-registry 163
-
brainstorm
Brainstorm solutions with trade-off analysis and brutal honesty. Use for ideation, architecture decisions, technical debates, feature exploration, feasibility assessment, design discussions.
majiayu000/claude-skill-registry 163
-
ioc-analysis
Analyzes indicators of compromise (IOCs) to detect and respond to cybersecurity threats.
majiayu000/claude-skill-registry 163
-
orchestrator
多代理协作编排器，基于 Anthropic 工程团队架构，支持 Lead-Worker 模式、API Key 轮换、并行执行。触发词：创建团队、多代理协作、长任务、复杂任务、并行搜索。
majiayu000/claude-skill-registry 163
-
sqlalchemy
Python SQL toolkit and ORM for defining schemas and issuing SQL/ORM queries with explicit transaction control.
majiayu000/claude-skill-registry 163
-
bmad-wds-reverse-engineering
Analyze any software or website to extract specifications and design patterns
majiayu000/claude-skill-registry 163
-
asc-metadata-sync
Sync and validate App Store metadata and localizations with asc, including Fastlane format migration. Use when updating metadata or translations.
majiayu000/claude-skill-registry 163
-
azure-functions
Expert patterns for Azure Functions development including isolated worker model, Durable Functions orchestration, cold start optimization, and production patterns. Covers .NET, Python, and Node.js ...
majiayu000/claude-skill-registry 163
-
meme-launcher
Solana memecoin launch strategy and execution. Use when planning token launches, designing tokenomics, building pre-launch hype, deploying on pump.fun/Raydium, or optimizing launch mechanics. Covers: token creation, bonding curves, liquidity strategy, community building, anti-rug best practices.
majiayu000/claude-skill-registry 163
-
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.
majiayu000/claude-skill-registry 163
-
10-01-open-questions-system
Track and resolve open questions in Obsidian comments using emoji markers and block IDs.
majiayu000/claude-skill-registry 163
-
keychain
This prompt instructs an image generation/editing system to produce a high-resolution vertical portrait that preserves the subject’s exact real-world likeness while adding a physically plausible keychain in their hand featuring a small, stylized 3D cartoon version of the same person. The result should look like professional photography—natural skin texture, cinematic lighting, shallow depth of field, warm indoor background—while the mini figure reads as a toy-like 3D character with matching outfit and clear resemblance, integrated with consistent lighting, realistic metallic materials, and correct shadows, avoiding artifacts like distorted hands, mismatched identity, or watermarks.
majiayu000/claude-skill-registry 163
-
rust-mcp-server-generator
Generate a complete Rust Model Context Protocol server project with tools, prompts, resources, and tests using the official rmcp SDK
majiayu000/claude-skill-registry 163
-
cook-hard
[Implementation] Thorough implementation with maximum verification
majiayu000/claude-skill-registry 163
-
scikit-learn
Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.
majiayu000/claude-skill-registry 163
-
gwt-fix-pr
Inspect GitHub PR for CI failures, merge conflicts, update-branch requirements, reviewer comments, change requests, and unresolved review threads. Create fix plans and implement after user approval. Reply to ALL reviewer comments with action taken or reason for not addressing, then resolve threads. Notify reviewers after fixes.
majiayu000/claude-skill-registry 163
-
novelty-check
Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.
majiayu000/claude-skill-registry 163