hermes
01Agent
"Hermes" is overloaded, and getting it wrong causes real confusion. In an agents context it refers to two related-but-distinct things from Nous Research.
233 14d ago A 0 tokens
original MIT
openclaw
02Agent
OpenClaw is the personal-AI-assistant track of Week 17: an open-source assistant that runs on your devices and meets you in the messaging channels you already use. This guide walks through what it is, how it's architected, how to install and run it, how to point it at a local model, and how to wire it to your Week-16…
233 14d ago C 0 tokens
original MIT
Skill Claude CodeCodex
Wrap an agent loop with step limits, cost caps, human approval gates, and a full trace. Use whenever building or reviewing any tool-calling agent before it touches real systems.
233 14d ago A 41 tokens
original MIT
Skill Claude CodeCodex
Move an agent from laptop demo to operated system, tracing, cost dashboard, scheduled runs, alerting, and rollback. Use when an agent is about to run unattended or serve real users.
233 14d ago A 44 tokens
original MIT
Skill Claude CodeCodex
Review AI-generated code or text before accepting it, spec diff, verifier run, secret scan, and the AI smell list. Use before merging any agent-produced change.
233 14d ago A 37 tokens
original MIT
Skill Claude CodeCodex
The pre-deployment gate for managed AI platforms (Azure AI Foundry, Google Vertex AI, AWS Bedrock), evals packed, budget set, guardrails on, owner named. Use before any cloud deployment.
233 14d ago A 49 tokens
original MIT
Skill Claude CodeCodex
Audit the seven claimants on an LLM call's context window, set a working ceiling, and cut in the right order. Use when prompts grow, agents drift, or token bills surprise you.
233 14d ago A 45 tokens
original MIT
Skill Claude CodeCodex
Read 50 real failures by hand, cluster them into classes, fix the largest class, and extend the golden set. Use whenever an AI system's score stalls or its failures are 'mysterious'.
233 14d ago A 46 tokens
original MIT
Skill Claude CodeCodex
Build the golden set and the automated scorer before touching the prompt, model, or pipeline. Use whenever an AI output's quality will need to be measured, extraction, RAG, agents, classification.
233 14d ago A 44 tokens
original MIT
Skill Claude CodeCodex
Decide whether fine-tuning is justified versus prompting or RAG, and gate the training dataset before any LoRA/SFT/DPO run. Use when someone says 'let's fine-tune'.
233 14d ago A 46 tokens
original MIT
Skill Claude CodeCodex
Compute the VRAM/RAM budget and pick a model size and quantization before downloading anything. Use when choosing local models, planning GPU hardware, or hitting out-of-memory errors.
233 14d ago A 40 tokens
original MIT
Skill Claude CodeCodex
Design and build an MCP server whose tools are narrow, typed, idempotent, and documented. Use when exposing any system to AI agents via the Model Context Protocol.
233 14d ago A 40 tokens
original MIT
Skill Claude CodeCodex
Improve a prompt as a versioned artifact with a score, change one variable at a time, keep the diff, read the failures. Use whenever editing prompts that must stay measurably good.
233 14d ago A 44 tokens
original MIT
Skill Claude CodeCodex
Verify a RAG pipeline end-to-end, chunking, embeddings, retrieval quality, reranking, grounded answers with citations. Use when building or debugging retrieval-augmented generation.
233 14d ago A 42 tokens
original MIT
Skill Claude CodeCodex
Write the one-page spec for an AI feature, user, golden set, metric, gate, refused tradeoffs, before any code or prompt work. Use when starting any AI feature, agent, or pipeline.
233 14d ago A 47 tokens
original MIT
Skill Claude CodeCodex
How to pick, run, and amend Zorost agent skills. Use at the start of any task when this catalog is installed, or when a skill seems not to fit.
233 14d ago A 43 tokens
original MIT