Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
vue-composables
Write high-quality Vue 3 composables following established patterns and best practices. Use when creating new composables, refactoring existing ones, or reviewing composable code. Triggers include requests to "create a composable", "write a use* function", "extract logic into a composable", or any Vue Composition API reusable logic task.
majiayu000/claude-skill-registry 163
-
nd-frustration-support
Use when user shows signs of overwhelm or frustration — repeated failed attempts, tone shifts, sudden brevity, topic abandonment. Guides gentle check-ins without being patronizing or clinical.
majiayu000/claude-skill-registry 163
-
aws-ecr
Manage AWS ECR container image repositories.
majiayu000/claude-skill-registry 163
-
language-python
Python language patterns and best practices. Use when language python guidance is required or when selecting a primary language for non-trivial automation.
majiayu000/claude-skill-registry 163
-
fabric-rti-perf-remediate
Diagnose and resolve performance issues in Microsoft Fabric Real-Time Intelligence including Eventhouse, KQL databases, Eventstream, and ingestion pipelines. Use when asked to troubleshoot slow KQL queries, high Eventhouse CPU or memory, ingestion latency or failures, Eventstream throughput problems, capacity throttling (HTTP 430), cache policy tuning, materialized view lag, or Always-On configuration. Covers workspace monitoring, Fabric Capacity Metrics app, query optimization, and streaming diagnostics.
majiayu000/claude-skill-registry 163
-
respond-ransomware
Respond to a ransomware incident following PICERL methodology. Use when ransomware is detected or suspected. Orchestrates identification, containment, eradication, and recovery phases. Requires CASE_ID and initial indicators.
majiayu000/claude-skill-registry 163
-
pdf
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
majiayu000/claude-skill-registry 163
-
mcp-development
Create, test, and audit MCP (Model Context Protocol) servers, tools, resources, and prompts. Use when building MCP components, writing tool schemas, designing transport layers (stdio/http), or validating MCP servers. Includes prompt-engineered descriptions, Zod validation, authentication patterns, and `test_mcp.sh` for validation. Not for manual tool configuration or non-MCP integrations.
majiayu000/claude-skill-registry 163
-
llava
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.
majiayu000/claude-skill-registry 163
-
refine-workflow
Use when analyzing workflow effectiveness or identifying skill extraction opportunities - systematically identifies patterns worthy of new skills and improvement areas
majiayu000/claude-skill-registry 163
-
shadcn
Comprehensive shadcn/ui component library with theming, customization patterns, and accessibility. Use when building modern React UIs with Tailwind CSS. IMPORTANT - Always use MCP server tools first when available.
majiayu000/claude-skill-registry 163
-
fmod
FMOD Studio integration skill for events, parameters, and mixing.
majiayu000/claude-skill-registry 163
-
codeck-design
Designer role. Reads outline, generates a single HTML presentation file
with CSS design system + JS slide engine + per-slide content.
Accepts visual references (URLs, screenshots, design specs) and
extracts design signals to inform the isomorphic mapping.
Use whenever the user says "design slides", "generate deck",
"generate the deck", "build slides", "visual style",
"reference this style", "like this design",
"design", "generate slides", "visual style", "reference this style",
or wants to turn an outline into actual slides.
majiayu000/claude-skill-registry 163
-
doc
Generates, validates, and syncs documentation for any repository type. Produces code-maps, checks doc coverage, finds missing docs, and validates existing documentation against code. Triggers: doc, documentation, code-map, doc coverage, validate docs, generate docs, sync docs, update docs, find missing docs.
majiayu000/claude-skill-registry 163
-
remix
Remix patterns including loaders, actions, nested routing, progressive enhancement, and deployment strategies.
majiayu000/claude-skill-registry 163
-
code-quality
Provides code quality principles including SOLID, DRY, testing strategies, and best practices for implementation review. Use when reviewing code or applying quality standards.
majiayu000/claude-skill-registry 163
-
architecture-paradigm-event-driven
Asynchronous event-based communication to decouple producers/consumers for scalability and resilience. Use when real-time workloads or multiple subsystems react to same events. Do not use when selecting paradigms (use architecture-paradigms first), simple request-response.
majiayu000/claude-skill-registry 163
-
repurposing-content
Transforms single pieces of content into multiple formats across platforms. Use when the user asks about content repurposing, atomizing content, multi-format content, or creating social posts from blog content.
majiayu000/claude-skill-registry 163
-
rag-patterns
Chunking strategies, embedding model selection, hybrid search, reranking, eval metrics
majiayu000/claude-skill-registry 163
-
walking-through-the-grove
Find the right Grove-themed name for a new service or feature. Use when naming anything new in the Grove ecosystem. Involves reading the naming philosophy, creating a visualization scratchpad, and walking through the forest metaphor to find where the concept naturally fits.
majiayu000/claude-skill-registry 163
-
ts-standards
Enforces TypeScript/Effect standards with snippet-first guidance: algebraic data types, exhaustive pattern matching, schema-derived types, hard-minimal export surface, and auto-integrated internal functionality. Use when writing, refactoring, or reviewing TypeScript code.
majiayu000/claude-skill-registry 163
-
ollama
Offload simple tasks to local Ollama LLM to preserve Claude credits. Use for code summaries, file analysis, diff reviews, quick questions about syntax/APIs, and pre-screening code before deeper Claude analysis. Invoke automatically when exploring files or reviewing code.
majiayu000/claude-skill-registry 163
-
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
majiayu000/claude-skill-registry 163
-
cairo-scanner
Use when the user wants to audit Cairo smart contracts for security vulnerabilities, scan Starknet contracts for felt overflow, storage collision, or account abstraction issues, review Cairo 2.x contracts for component architecture flaws, or analyze STARK-based protocols for cryptographic and computational errors.
majiayu000/claude-skill-registry 163