Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
conducting-user-interviews
Plan, conduct, and synthesize high-signal user interviews and produce a User Interview Pack (recruiting plan, screener, discussion guide, notes template, synthesis report). Use for user interview, customer interview, discovery interview, JTBD switch interview, concept interview.
majiayu000/claude-skill-registry 163
-
reply-to-text
Review text message conversations with a specified contact and send appropriate replies with cheerful tone and humor using Arlen's authentic writing style. This skill should be used when the user says "reply to [name]'s text", "respond to [name]", "text [name] back", or wants to send contextual replies to contacts. Automatically handles contact lookup and conversation review via subagent delegation. Integrates email skill writing style guide for authentic voice. Considers ALL messages received from contact since last reply (not just latest). TRIGGER PHRASES - "reply to", "respond to", "text back", "answer [name]'s message".
majiayu000/claude-skill-registry 163
-
multi-region-deployment
Use when designing globally distributed systems, multi-region architectures, or disaster recovery strategies. Covers region selection, active-active vs active-passive, data replication, and failover patterns.
majiayu000/claude-skill-registry 163
-
drizzle-migration
Execute the proper Drizzle Kit workflow for database schema migrations in asset-forge. Use this when the user asks to create a database migration, update the database schema, or when schema changes need to be applied to the database.
majiayu000/claude-skill-registry 163
-
ai-sdk
Comprehensive guide to AI SDK v6 for agent development, tool definitions, multi-step agentic workflows, and result extraction patterns
majiayu000/claude-skill-registry 163
-
Fluxwing Screenshot Importer
Import UI screenshots and generate uxscii components automatically using vision analysis. Use when user wants to import, convert, or generate .uxm components from screenshots or images.
majiayu000/claude-skill-registry 163
-
defi-protocol-templates
Implement DeFi protocols with production-ready templates for staking, AMMs, governance, and lending systems. Use when building decentralized finance applications or smart contract protocols.
majiayu000/claude-skill-registry 163
-
react-performance-patterns
React performance optimization patterns for TMNL. Covers useMemo, useCallback, React.memo, virtualization, and when optimization matters vs premature optimization. Use for performance-critical components.
majiayu000/claude-skill-registry 163
-
writing-adrs
Document architectural decisions. Use when making significant technical decisions that should be recorded. Covers ADR format and decision documentation.
majiayu000/claude-skill-registry 163
-
binary-triage
Performs initial binary triage by surveying memory layout, strings, imports/exports, and functions to quickly understand what a binary does and identify suspicious behavior. Use when first examining a binary, when user asks to triage/survey/analyze a program, or wants an overview before deeper reverse engineering.
majiayu000/claude-skill-registry 163
-
features
majiayu000/claude-skill-registry 163
-
yjs
Yjs CRDT patterns, shared types, conflict resolution, and meta data structures. Use when building collaborative apps with Yjs, handling Y.Map/Y.Array/Y.Text, implementing drag-and-drop reordering, or optimizing document storage.
majiayu000/claude-skill-registry 163
-
anchor
Create and distribute podcasts with Anchor (Spotify for Podcasters) - manage episodes, analytics, and distribution
majiayu000/claude-skill-registry 163
-
aws-sdk-java-v2-messaging
Implement AWS messaging patterns using AWS SDK for Java 2.x for SQS queues and SNS topics. Send/receive messages, manage FIFO queues, implement DLQ, publish messages, manage subscriptions, and build pub/sub patterns.
majiayu000/claude-skill-registry 163
-
nav-loop
Run tasks until complete with structured completion signals. Auto-invoke when user says "run until done", "keep going until complete", "iterate until finished", "loop mode", "autonomous mode".
majiayu000/claude-skill-registry 163
-
writing-for-llms
Use when writing prompts, agent instructions, SKILL.md, commands, system prompts, Task tool prompts, prompt engineering, or LLM-to-LLM content
majiayu000/claude-skill-registry 163
-
agent-mlops
Production deployment and operationalization of AI agents on Databricks. Use when deploying agents to Model Serving, setting up MLflow logging and tracing for agents, implementing Agent Evaluation frameworks, monitoring agent performance in production, managing agent versions and rollbacks, optimizing agent costs and latency, or establishing CI/CD pipelines for agents. Covers MLflow integration patterns, evaluation best practices, Model Serving configuration, and production monitoring strategies.
majiayu000/claude-skill-registry 163
-
mcp-tripartite
MCP tripartite integration for orchestrating distributed tool protocols
majiayu000/claude-skill-registry 163
-
structure-check
majiayu000/claude-skill-registry 163
-
angle-generator
Generate 10-20 ad angles for an offer using direct response principles and cross-industry ideation. Use when you need fresh angle ideas, want to explore new messaging approaches, or are starting creative development for a campaign.
majiayu000/claude-skill-registry 163
-
document-writer
Expert in creating technical documentation, architectural decision records (ADRs), and RFCs. Specializes in structured knowledge management and system documentation. Use when writing technical docs, ADRs, RFCs, or system design documents.
majiayu000/claude-skill-registry 163
-
RAG Expert
Expert in Retrieval-Augmented Generation systems - knowledge bases, chunking strategies, embedding optimization, and production RAG architectures
majiayu000/claude-skill-registry 163
-
swiftui-testing
Test SwiftUI apps with XCTest, UI tests, snapshot testing, and async testing. Use when writing unit tests for ViewModels, creating UI automation tests, implementing snapshot tests, or testing async code.
majiayu000/claude-skill-registry 163
-
budget-tracker-patterns
Backend budget tracking patterns for AI generation. Awareness-based tracking (not blocking), tool timeouts, per-tool rate limits, token estimates, context window management, truncation strategies, search quality detection. Triggers on "budget", "tool timeout", "rate limit", "token estimate", "truncation", "context window", "search quality", "diminishing returns".
majiayu000/claude-skill-registry 163