Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
verilog-sv-language
Expert-level Verilog and SystemVerilog knowledge following IEEE 1800 standards. Generates synthesizable RTL code with proper coding styles and constructs.
majiayu000/claude-skill-registry 163
-
language-shell
Shell scripting standards and safety practices. Use when language shell guidance is required or when selecting Shell as a thin wrapper or OS-near glue layer.
majiayu000/claude-skill-registry 163
-
hello-skill
每次对话开始时,声明"[Skills✏️已加载]"
majiayu000/claude-skill-registry 163
-
godot-modernize-gdscript
Modernizes GDScript 1.0 (Godot 3.x) code to GDScript 2.0 (Godot 4.x) syntax. Converts yield to await, onready to @onready, export to @export, setget to property syntax, and adds optional static typing. Essential for Godot 3.x to 4.x migration projects.
majiayu000/claude-skill-registry 163
-
daily-summary
End of session summary. What got done, what got fixed, what comes next, progress delta.
majiayu000/claude-skill-registry 163
-
evo-party-mode
Orchestrates group discussions between all installed EVO agents, enabling natural multi-agent conversations. Use when user requests party mode.
majiayu000/claude-skill-registry 163
-
Claude Code Guide
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
majiayu000/claude-skill-registry 163
-
script-organization
Script organization for data science analysis projects with numbered scripts, data/outs/ directories, and reproducibility conventions. Use when creating new analysis scripts in projects that follow data science conventions (numbered XX_ prefix scripts, outs/ directories, BUILD_INFO.txt). Do NOT load for documentation projects (Quarto books), infrastructure repos, or projects without data/outs/ directory structure.
majiayu000/claude-skill-registry 163
-
discord-bot-architect
Specialized skill for building production-ready Discord bots. Covers Discord.js (JavaScript) and Pycord (Python), gateway intents, slash commands, interactive components, rate limiting, and sharding.
majiayu000/claude-skill-registry 163
-
speaking
Golden path /speak — generate RLM-isolated follow-ups with chronicle temporal context injection.
majiayu000/claude-skill-registry 163
-
project-health
AI-agent readiness auditing for project documentation and workflows. Evaluates whether
future Claude Code sessions can understand docs, execute workflows literally, and resume
work effectively. Use when onboarding AI agents to a project or ensuring context continuity.
Includes three specialized agents: context-auditor (AI-readability), workflow-validator
(process executability), handoff-checker (session continuity). Use PROACTIVELY before
handing off projects to other AI sessions or team members.
majiayu000/claude-skill-registry 163
-
plan-forge
Use when a task needs an implementation plan that is iteratively created and stress-tested through review-and-revise cycles before implementation begins — catches blind spots, incorrect codebase assumptions, unnecessary complexity, and performance pitfalls while changes are still cheap
majiayu000/claude-skill-registry 163
-
dispatch
Dispatch agents to GKE Autopilot K8s Jobs or local worktrees for GitHub issues. Use when the user says 'dispatch', 'spawn agent', 'send to GKE', or when /fire-next-up needs to spawn an agent. Supports parallel dispatch, agent selection, branch override, and prompt customization.
majiayu000/claude-skill-registry 163
-
nemo-guardrails
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
majiayu000/claude-skill-registry 163
-
e2e-testing
End-to-end testing with Cypress and Playwright for IntelliFill. Use when writing E2E tests, custom commands, or CI integration.
majiayu000/claude-skill-registry 163
-
agent-tdd-london-swarm
Agent skill for tdd-london-swarm - invoke with $agent-tdd-london-swarm
majiayu000/claude-skill-registry 163
-
qwen-asr
Transcribe audio files using Qwen ASR. Use when the user sends voice messages and wants them converted to text.
majiayu000/claude-skill-registry 163
-
ef-core
Get best practices for Entity Framework Core
majiayu000/claude-skill-registry 163
-
mojo-memory-check
Verify memory safety in Mojo code including ownership, borrowing, and lifetime management. Use when reviewing code or debugging memory issues.
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
-
sdrplay-service-fix
Fix stuck SDRplay API service that causes device enumeration to hang. Use when SoapySDRUtil --find hangs, SDRplay device times out, or the SDRplay RSP is unresponsive.
majiayu000/claude-skill-registry 163
-
web-i18n-react-intl
ICU message format internationalization
majiayu000/claude-skill-registry 163
-
execute
EXECUTION PHASE - Run tasks via isolated subagents. Requires completed task DAG from plan phase.
majiayu000/claude-skill-registry 163
-
opentelemetry
majiayu000/claude-skill-registry 163