← ClaudeAtlas

ai-engineeringlisted

Authoritative source of truth on AI tooling and how to choose it - the knowledge behind building AI agents and AI systems. Use when choosing between agent frameworks, harnesses, memory, RAG, ingestion, serving or eval components; when weighing an architecture for an agent/LLM system; when asked "what's the current state of X", "what are my options for Y", "is Z still maintained", or "what license is Z"; and when reviewing whether an AI design honors sound engineering practice. Answers come from the bundled dated corpus, not from training memory. Standing up a new AI project or adding an AI subsystem to an existing repo goes to ai-agent-project-scaffold; updating the corpus goes to ai-engineering-update; general engineering discipline to agent-skills; MCP servers to build-mcp-server.
thefilesareinthecomputer/dotagents · ★ 0 · AI & Automation · score 72
Install: claude install-skill thefilesareinthecomputer/dotagents
# AI Engineering The knowledge layer for **AI systems: what exists, what it costs to adopt, and which component fits a given job - especially OSS.** It carries a curated, deduplicated catalog of the agent-stack ecosystem and an opinionated map for choosing components. This is the read path. It advises; it does not run intake or generate repos. **Read the bundled resources instead of answering from training memory.** Versions, licenses, maintenance status and governance all move after a model's training data is fixed. The resources below are dated and verifiable, which is what lets them be more current than the model reading them. ## Scope - and what this skill is NOT **This skill owns:** - **Stack selection** - picking framework / harness / memory / retrieval / ingestion / serving / frontend components, with the tradeoff that decides each. - **Component judgment** - what a tool is for, what it costs to adopt, where it breaks, what its license obliges. - **Tooling currency** - being right about what's GA, abandoned, source-available-with-conditions, or newly relevant. - **Architecture review** - whether a proposed AI design honors the engineering principles below. **This skill is the read path. Three neighbours own the rest:** - **Standing up a project** - intake, committing to a full stack, generating the repo → `ai-agent-project-scaffold`. That includes adding an AI subsystem to an existing codebase. Advising on components stays here; the moment the job is to *build* o