ML Training
2190 skills · sorted by GitHub stars
brainstorming
Brainstorming Ideas Into Designs Purpose Turn raw ideas into clear, validated designs and specificat
using-superpowers
If you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUS
using-git-worktrees
Using Git Worktrees Overview Git worktrees create isolated workspaces sharing the same repository, a
dispatching-parallel-agents
Dispatching Parallel Agents Overview When you have multiple unrelated failures (different test files
verification-before-completion
Verification Before Completion Overview Claiming work is complete without verification is dishonesty
agent-architecture-audit
Agent Architecture Audit A diagnostic workflow for agent systems that hide failures behind wrapper l
agent-eval
Agent Eval Skill A lightweight CLI tool for comparing coding agents head-to-head on reproducible tas
agent-harness-construction
Agent Harness Construction Use this skill when you are improving how an agent plans, calls tools, re
agent-introspection-debugging
Agent Introspection Debugging Use this skill when an agent run is failing repeatedly, consuming toke
agentic-os
Agentic OS Treat Claude Code as a persistent runtime / operating system rather than a chat session.
ai-first-engineering
AI-First Engineering Use this skill when designing process, reviews, and architecture for teams ship
autonomous-agent-harness
Autonomous Agent Harness Turn Claude Code into a persistent, self-directing agent system using only
autonomous-loops
Autonomous Loops Skill > Compatibility note (v1.8.0): autonomous-loops is retained for one release.
blender-motion-state-inspection
Blender Motion State Inspection When to Use - A Blender character looks twisted, mirrored, flattened
blueprint
Blueprint — Construction Plan Generator Turn a one-line objective into a step-by-step construction p
canary-watch
Canary Watch — Post-Deploy Monitoring When to Use - After deploying to production or staging - After
ck
ck — Context Keeper You are the Context Keeper assistant. When the user invokes any /ck: command, ru
claude-devfleet
Claude DevFleet Multi-Agent Orchestration When to Use Use this skill when you need to dispatch multi
codehealth-mcp
Code Health MCP (CodeScene) Structural maintainability feedback for AI-assisted coding. Complements
compose-multiplatform-patterns
Compose Multiplatform Patterns Patterns for building shared UI across Android, iOS, Desktop, and Web
configure-ecc
Configure Everything Claude Code (ECC) An interactive, step-by-step installation wizard for the Ever
context-budget
Context Budget Analyze token overhead across every loaded component in a Claude Code session and sur
continuous-agent-loop
Continuous Agent Loop This is the v1.8+ canonical loop skill name. It supersedes autonomous-loops wh
cost-aware-llm-pipeline
Cost-Aware LLM Pipeline Patterns for controlling LLM API costs while maintaining quality. Combines m
taste
--- name: taste description: A creative-direction (taste) layer for music videos and short-form edit
mcp-server-patterns
--- name: mcp-server-patterns description: Build MCP servers with Node/TypeScript SDK — tools, resou
kotlin-exposed-patterns
--- name: kotlin-exposed-patterns description: JetBrains Exposed ORM 模式,包括 DSL 查询、DAO 模式、事务、HikariCP
healthcare-emr-patterns
--- name: healthcare-emr-patterns description: EMR/EHR development patterns for healthcare applicati
homelab-pihole-dns
--- name: homelab-pihole-dns description: ホームラボ用Pi-hole DNS設定、広告ブロック、プライバシー、およびカスタムドメイン解決。 origin: c
llm-trading-agent-security
--- name: llm-trading-agent-security description: 具有钱包或交易权限的自主交易代理的安全模式。涵盖提示注入、支出限制、发送前模拟、断路器、MEV保护和
regex-vs-llm-structured-text
--- name: regex-vs-llm-structured-text description: 选择在解析结构化文本时使用正则表达式还是大型语言模型的决策框架——从正则表达式开始,仅在低置信度
council
--- name: council description: Convene a four-voice council for ambiguous decisions, tradeoffs, and
jpa-patterns
--- name: jpa-patterns description: JPA/Hibernate patterns for entity design, relationships, query o
fal-ai-media
--- name: fal-ai-media description: Unified media generation via fal.ai MCP — image, video, and audi
santa-method
--- name: santa-method description: "Multi-agent adversarial verification with convergence loop. Two
nanoclaw-repl
--- name: nanoclaw-repl description: Operate and extend NanoClaw v2, ECC's zero-dependency session-a
template-skill
Replace with description of the skill and when Claude should use it.
claude-api
Building LLM-Powered Applications with Claude This skill helps you build LLM-powered applications wi
theme-factory
Theme Factory Skill This skill provides a curated collection of professional font and color themes t
web-artifacts-builder
Web Artifacts Builder To build powerful frontend claude.ai artifacts, follow these steps: 1. Initial
docx
A .docx file is a ZIP archive containing XML files.
mcp-builder
MCP Server Development Guide Overview Create MCP (Model Context Protocol) servers that enable LLMs t
skill-creator
skill-creator Purpose To create new CLI skills following Anthropic's official best practices with ze
template
AI agent skill: template. Install to enhance your coding agent capabilities.
handoff
When to Use Use when this workflow matches the user request: Compact the current conversation into a
edit-article
1. First, divide the article into sections based on its headings. Think about the main points you wa
obsidian-vault
/mnt/d/Obsidian Vault/AI Research/ Mostly flat at root level. - Index notes: aggregate related topic
scaffold-exercises
Create exercise directory structures that pass pnpm ai-hero-cli internal lint, then commit with git
git-guardrails-claude-code
Sets up a PreToolUse hook that intercepts and blocks dangerous git commands before Claude executes t
setup-matt-pocock-skills
Setup Matt Pocock's Skills When to Use Use when this workflow matches the user request: Configure th