Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
code-necromancer
Systematic framework for resurrecting and modernizing legacy codebases through archaeology, resurrection, and rejuvenation phases. Activate on "legacy code", "inherited codebase", "no documentation", "technical debt", "resurrect", "modernize". NOT for greenfield projects or well-documented active codebases.
majiayu000/claude-skill-registry 163
-
moai-lang-kotlin
Kotlin 2.0 Multiplatform Enterprise Development with KMP, Coroutines, Compose Multiplatform, and Context7 MCP integration. Advanced patterns for mobile, backend, and cross-platform development.
majiayu000/claude-skill-registry 163
-
home-assistant
Control Home Assistant smart home devices and automations. Use when:
(1) User asks to turn on/off lights, switches, or devices,
(2) User asks about the state of sensors, devices, or entities,
(3) User says "turn on the lights", "set temperature", "lock the door",
(4) User asks to run a scene or script,
(5) User asks "what devices are on?" or "is the door locked?",
(6) User mentions smart home, IoT, or home automation.
There are TWO Home Assistant deployments: ha-london (default) and ha-sofia.
Always use Home Assistant for smart home control.
majiayu000/claude-skill-registry 163
-
using-superpowers
using-superpowers
majiayu000/claude-skill-registry 163
-
blog-writing
Blog post writing for technical content and thought leadership
majiayu000/claude-skill-registry 163
-
simpy
Process-based discrete-event simulation framework in Python. Use this skill when building simulations of systems with processes, queues, resources, and time-based events such as manufacturing systems, service operations, network traffic, logistics, or any system where entities interact with shared resources over time.
majiayu000/claude-skill-registry 163
-
wrds
This skill should be used when the user asks to "query WRDS", "access Compustat", "get CRSP data", "pull Form 4 insider data", "query ISS compensation", "download SEC EDGAR filings", "get ExecuComp data", "access Capital IQ", "write SAS code for WRDS", "SAS ETL", "SAS hash merge", "SGE array job", "qsas", "qsub SAS", or needs WRDS PostgreSQL query patterns or SAS ETL performance patterns.
majiayu000/claude-skill-registry 163
-
azure-devops-pipelines
Build Azure DevOps YAML pipelines for CI/CD, manage releases, artifacts, and deployment environments. Create build and release pipelines, configure triggers, templates, and integrate with Azure services. Use when automating builds, tests, and deployments in Azure DevOps. (project)
majiayu000/claude-skill-registry 163
-
azure-aigateway
Configure Azure API Management (APIM) as AI Gateway to secure, observe, control AI models, MCP servers, agents. Helps with rate limiting, semantic caching, content safety, load balancing.
USE FOR: AI Gateway, APIM, setup gateway, configure gateway, add gateway, model gateway, MCP server, rate limit, token limit, semantic cache, content safety, load balance, OpenAPI import, convert API to MCP.
DO NOT USE FOR: deploy models (use microsoft-foundry), Azure Functions (use azure-functions), databases (use azure-postgres).
majiayu000/claude-skill-registry 163
-
sentencepiece
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
majiayu000/claude-skill-registry 163
-
fetch-library-docs
Fetches official documentation for external libraries and frameworks (React, Next.js, Prisma, FastAPI, Express, Tailwind, MongoDB, etc.) with 60-90% token savings via content-type filtering. Use this skill when implementing features using library APIs, debugging library-specific errors, troubleshooting configuration issues, installing or setting up frameworks, integrating third-party packages, upgrading between library versions, or looking up correct API patterns and best practices. Triggers automatically during coding work - fetch docs before writing library code to get correct patterns, not after guessing wrong.
majiayu000/claude-skill-registry 163
-
Zod Schema Management
Create and modify Zod schemas for runtime validation with proper type inference.
majiayu000/claude-skill-registry 163
-
denylist-stuck-messages
Add message IDs to the relayer denylist. Use after investigating stuck messages with /investigate-stuck-messages, or when you have specific message IDs to denylist.
majiayu000/claude-skill-registry 163
-
bloodhound-scout
Track code through the forest with unerring precision. Pick up the scent, follow the trail, and map the territory. Use when exploring unfamiliar codebases, finding patterns, or understanding how systems connect.
majiayu000/claude-skill-registry 163
-
check-patterns
Check code follows established patterns from CONVENTIONS.md
majiayu000/claude-skill-registry 163
-
agent-v3-integration-architect
Agent skill for v3-integration-architect - invoke with $agent-v3-integration-architect
majiayu000/claude-skill-registry 163
-
clrs-algorithms
Data structures and algorithms reference based on CLRS. Use this skill when implementing, discussing, or choosing data structures or algorithms. Auto-activates for algorithm selection, complexity analysis, and performance optimization. Comprehensive coverage of fundamental and advanced data structures with pseudocode examples.
majiayu000/claude-skill-registry 163
-
planning-with-files
Manus-style file-based planning for complex tasks. Creates and maintains task_plan.md, findings.md, and progress.md under .kiro/plan/. Use when planning, breaking down work, resuming a multi-step task, tracking phases, or restoring context after compaction. Trigger phrases include start planning, continue task, resume work, current phase, restore context.
majiayu000/claude-skill-registry 163
-
government-ai-policy-report-writing
A reusable skill for drafting factual, plain-language, Word-compatible government policy reports and regulatory documents on AI topics — enforcing technical accuracy, strict regulatory alignment, actionable governance insights, and zero technical hallucination within China's official framework.
majiayu000/claude-skill-registry 163
-
riverpod-cancel
Cancel or debounce Riverpod async requests with ref.onDispose; cancel when user leaves the page, debounce rapid refreshes. Use when the user asks about cancelling requests, debouncing, or cleaning up when a provider is disposed.
majiayu000/claude-skill-registry 163
-
improving-streamlit-design
Improving visual design in Streamlit apps. Use when polishing apps with icons, badges, spacing, or text styling. Covers Material icons, badge syntax, divider alternatives, and text casing conventions.
majiayu000/claude-skill-registry 163
-
maestro-create-test
Interactively create a Maestro E2E test flow by inspecting the live device screen and building the YAML step by step. Use when the user wants to create a new Maestro test, write a new E2E flow, build a test from the device, or says "create a maestro test" or "record a test flow".
majiayu000/claude-skill-registry 163
-
gohome
Use when Moltbot needs to test or operate GoHome via gRPC discovery, metrics, and Grafana.
majiayu000/claude-skill-registry 163
-
launch-checklist
Complete launch readiness validation covering every department: code, content, store, marketing, community, infrastructure, legal, and go/no-go sign-offs.
majiayu000/claude-skill-registry 163