80 tagged production, measured the same way as everything else here.
Browse within: fastapi 10ai-framework 8architecture 8pydantic-ai 8NVIDIA 6Orchestration 6agentskills 6ai-research 6best-practices 6observability 6rust 6DSPy 5Prompt Optimization 5RAG 5
Skill Claude CodeCodex
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…
Skill Claude CodeCodex
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
Orchestra-Research/AI-Research-SKILLs
Skill Claude CodeCodex
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance…
Skill Claude CodeCodex
Use for debugging DSPy programs, inspecthistory, tracing LLM calls, custom callbacks, observability, monitoring, and cost tracking.
Skill Claude CodeCodex
Production-ready Express.js development covering middleware architecture, error handling, security hardening, testing strategies, and deployment patterns.
Skill Claude CodeCodex
Add a new API endpoint following the project's layered architecture.
Skill Claude CodeCodex
Skill "add-migration" from gruberb/bulletproof-rust-web, covering skill: add migration and steps.
Skill Claude CodeCodex
Review a pull request for architecture, correctness, security, and operational readiness.
gmaxxxie/ai-native-product-agent-skills
Skill Claude CodeCodex
A method for operating an AI product after launch or during preparation for launch. It covers monitoring, metrics, failure handling, human corrections, feedback, and business or customer feedback loops.
Skill Claude CodeCodex
Guidelines for building production-ready Convex apps covering function organization, query patterns, validation, TypeScript usage, error handling, and the Zen of Convex design philosophy.
Skill Claude CodeCodex
Use when adding pause/resume, human approval, provider routing, tool scoping, or knowledge search to an existing agent — covers all optional Agent2 framework capabilities with implementation patterns.
Skill Claude CodeCodex
Use when a domain expert wants to clone their professional brain into an Agent2 agent — interactive multi-phase interview that extracts identity, Chain-of-Thought, tools, knowledge, examples, and output format, then generates a complete production agent with a Sachbearbeiter-style Chain-of-Thought prompt, Pydantic…
Skill Claude CodeCodex
Use when building an agent that needs deep domain expertise — reads documents, checks them against professional knowledge, asks clarifying questions, and produces structured domain-specific output. Covers knowledge-backed agents, document processing, multi-turn workflows with human approval, and per-context knowledge…
Skill Claude CodeCodex
Design where, when, and how a human gates, reviews, or rescues an LLM agent — without turning the agent into a button labelled "approve". Use when the user is building an agent that takes irreversible actions or operates in regulated workflows and mentions human-in-the-loop, HITL, approval gate, escalation, review…
Skill Claude CodeCodex
Design and validate LLM-as-judge scoring — pairwise vs pointwise, bias correction, anchor calibration, and the cases where a judge is the wrong tool. Use when the user is building an eval, scoring open-ended outputs, or comparing model versions and mentions LLM-as-judge, model grader, pairwise comparison, position…
Skill Claude CodeCodex
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance…
Skill Claude CodeCodex
Guidelines for building production-ready Convex apps covering function organization, query patterns, validation, TypeScript usage, error handling, and the Zen of Convex design philosophy.
Skill Claude CodeCodex
Plan a production day end to end — order of day, categorised shot list, equipment checklist and a WhatsApp-ready crew briefing so nobody shows up asking where the call sheet is.
Skill Claude CodeCodex
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance…
Skill Claude CodeCodex
Use this skill to verify that an AI system is ready for production before deployment. Covers model abstraction, cost/latency, retries, fallbacks, structured logging, tracing, observability, evaluation in CI/CD, monitoring, and rollback planning. Activates as a mandatory gate before production deployment of any AI/LLM…
OctopusDeploy/octopus-claude-plugins
Skill Claude CodeCodex
Use this skill when a user asks to produce audit reports or compliance evidence from Octopus Deploy event data through the Octopus MCP server. It covers questions about who deployed, who edited which variables, when a release shipped, why a permission changed, and what activity happened in a Space over a given window.…
OctopusDeploy/octopus-claude-plugins
Skill Claude CodeCodex
Comprehensive knowledge about Octopus Deploy, including core concepts, deployment processes, variables, releases, lifecycles, tenants, runbooks, AI-powered features, and best practices. Trigger when user mentions Octopus Deploy or general software deployment concepts.
OctopusDeploy/octopus-claude-plugins
Skill Claude CodeCodex
Guides a user through their first Octopus Deploy setup — connecting a code repository, registering a deployment target (Kubernetes, Azure App Service, AWS ECS, Lambda, on-prem Tentacle, etc.), wiring up packages from their existing CI, and reaching their first real deployment. Prefers the Octopus MCP server's tools…
Skill Claude CodeCodex
Typography system compiler that generates structured type scales, font stacks, and typographic tokens. Use when users request type systems, font scales, typography tokens, design system typography, or ask to create/export typographic styles. Pairs with hexed for complete design systems.