ML Ops
Machine learning operations
replicate
by replicate
Discover, compare, and run AI models using Replicate's API
dispatch
by bassimeledath
"Dispatch background AI worker agents to execute tasks via checklist-based plans. Use when the user says 'dispatch' to delegate work to background agents, e.g. 'dispatch sonnet to review this', 'dispatch opus to fix the bug', 'dispatch a worker to research X'."
model-evaluation-benchmark
by rysweet
Automated reproduction of comprehensive model evaluation benchmarks following the Benchmark Suite V3. Auto-activates for model benchmarking, comparison evaluation, or performance testing between AI models.
agent-sdk
by rysweet
Comprehensive knowledge of Claude Agent SDK architecture, tools, hooks, skills, and production patterns. Auto-activates for agent building, SDK integration, tool design, and MCP server tasks.
ruby-on-rails-best-practices
by sergiodxa
Ruby on Rails architecture and coding patterns from Basecamp. Use when writing, reviewing, or refactoring Rails code to follow proven conventions for models, controllers, jobs, and concerns. Triggers on tasks involving Rails models, concerns, controllers, background jobs, or Turbo/Hotwire.
financial-modeling
by mfwarren
Production-ready entrepreneurship skills for Claude Code — marketing, sales, operations, finance, and leadership. 24 skills built by a founder, for founders.
check-context-communication
by dykyi-roman
Audits Bounded Context communication patterns. Checks Context Map relationships (Shared Kernel, ACL, Open Host), event vs direct calls, and anti-corruption layer usage.
charlie
by EveryInc
Your AI CFO for bootstrapped startups, named after Charlie Munger who embodied the principle that capital discipline is a competitive advantage. Provides financial frameworks for cash management, runway calculations, unit economics (LTV:CAC), capital allocation, hiring ROI, burn rate analysis, working capital optimization, and forecasting. Use for questions like "should we make this hire?", "how much runway do we need?", "what metrics should I track?", "how do I forecast revenue?", or any strategic financial decision at a self-funded company.
model-hierarchy
by zscole
Cost-optimize AI agent operations by routing tasks to appropriate models based on complexity. Use this skill when: (1) deciding which model to use for a task, (2) spawning sub-agents, (3) considering cost efficiency, (4) the current model feels like overkill for the task. Triggers: "model routing", "cost optimization", "which model", "too expensive", "spawn agent".
adk-skill
by miticojo
"Build single-agent and multi-agent systems using Google's Agent Development Kit (ADK) in Python, Java, Go, or TypeScript. Use when user says 'build an agent with ADK', 'create a Gemini agent', 'multi-agent pipeline', 'agent orchestration with Google', or mentions ADK, google-adk, google agent development kit, sequential/parallel/loop agents, agent tools, callbacks, state management, agent testing, or agent deployment with Gemini. Do NOT use for LangChain, CrewAI, AutoGen, or non-ADK agent frameworks."
summarize
by ZhihaoAIRobotic
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
feature-pipeline
by notedit
Execute implementation tasks from design documents using markdown checkboxes. Use when (1) implementing features from feature-analyzer output, (2) resuming interrupted work, (3) batch executing tasks. Triggers on 'start implementation', 'run tasks', 'resume'.
pinecone-mcp
by pinecone-io
Reference for the Pinecone MCP server tools. Documents all available tools - list-indexes, describe-index, describe-index-stats, create-index-for-model, upsert-records, search-records, cascading-search, and rerank-documents. Use when an agent needs to understand what Pinecone MCP tools are available, how to use them, or what parameters they accept.
PyTorch ML
by pacphi
Deep learning with PyTorch - model training, GPU acceleration, and data science workflows
writing-intelligence
by antonio0720
Sovereign Writing Intelligence Compiler v2.0 — 7-pass pipeline, signature-grade prose, zero AI residue. Fiction intelligence engine: chapter construction, 12 character roles, dialogue warfare (22 techniques, 9 tension elements), power dynamics, 8-phase tension compression, thriller architecture, transmedia deepening. 7 scoring systems. 16 genres. 8 voices. Trigger on: write, rewrite, edit, draft, revise, ghostwrite, prose, essay, chapter, sermon, speech, pitch, memo, narrative, dialogue, scene, thriller, suspense, tension, pacing, character voice, foreshadowing, subtext, score draft, grade writing, audit prose, anti-slop, AI detection, writing quality, improve writing, chapter construction, scene architecture, character roles, power dynamics, confined space, staging, cold open, fatal detail, silence, callback, worldbuilding, transmedia, lore bible, audio drama, scene audit, role audit, power map, plant audit, novel, short story, screenplay, creative writing, thriller writing, mystery, espionage.
testing-patterns
by majesticlabs-dev
Pytest templates and patterns for ETL pipeline testing - unit, integration, data quality.
arkit-visionos-developer
by tomkrikorian
Build and debug ARKit features for visionOS, including ARKitSession setup, authorization, data providers (world tracking, plane detection, scene reconstruction, hand tracking), anchor processing, and RealityKit integration. Use when implementing ARKit workflows in immersive spaces or troubleshooting ARKit data access and provider behavior on visionOS.
code-security-audit
by ssrsec
AI 驱动的生产级代码安全审计协议。面向企业内部授权审计，默认使用结构化 harness：项目画像、攻击面枚举、Sink/Control 双轨候选发现、验证队列、能力链、质量门、报告渲染和完整证据交付。支持 PHP、Java、C# / ASP.NET、Go、Python、JavaScript / TypeScript Node.js、Ruby、Rust、Kotlin、Deno/Bun，以及 JVM/.NET 编译产物反编译计划。用户说「开始审计 / 对 XXX 做安全审计 / 代码审计 / 安全扫描 / 找漏洞 / security audit / 红队审计」时触发。
azure-functions
by hainamchung
"Expert patterns for Azure Functions development including isolated worker model, Durable Functions orchestration, cold start optimization, and production patterns. Covers .NET, Python, and Node.js programming models. Use when: azure function, azure functions, durable functions, azure serverless, function app."
dojo-system
by dojoengine
Create Dojo systems that implement game logic, modify model state, and handle player actions. Use when implementing game mechanics, player commands, or automated logic.
dojo-review
by dojoengine
Review Dojo code for best practices, common mistakes, security issues, and optimization opportunities. Use when auditing models, systems, tests, or preparing for deployment.
dojo-model
by dojoengine
Create Dojo models for storing game state with proper key definitions, trait derivations, and ECS patterns. Use when defining game entities, components, or state structures.
dojo-test
by dojoengine
Write tests for Dojo models and systems using spawn_test_world, cheat codes, and assertions. Use when testing game logic, verifying state changes, or ensuring system correctness.
claudish-usage
by MadAppGang
CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.