agentsclimarketplace
Sign in

Super ai ml foundation

Skill arpitexplores/super-ai-ml-foundation

AI/ML foundations: model selection, prompt design, RAG, embeddings, and vector search. Use for core AI app design and build.From its SKILL.md

Install
npx -y skills add arpitexplores/super-ai-ml-foundation

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.8 KB, 376 tokens by cl100k_base, as published. Nobody here has run it

Super AI/ML Foundation

Overview

Establish the core AI/ML architecture before building agents or ops layers.

User Intent Examples

  • "Need help with AI Engineering for my product/site."
  • "Create a plan for Prompt Engineering."
  • "Audit or improve RAG Engineering."

Workflow

  1. Confirm use case, success criteria, latency, and cost targets.
  2. Select model family and deployment approach (hosted vs self-hosted).
  3. Design prompts, tool interfaces, and guardrails.
  4. Plan and implement RAG: chunking, embeddings, indexing, retrieval.
  5. Validate relevance, quality, and failure modes with small tests.
  6. Document tradeoffs, risks, and next experiments.

Minimal Intake Questions

  • Primary goal or outcome
  • Scope (pages, systems, teams, or timeframe)
  • Constraints (tools, budget, timeline)

Output Format

  • Use-case brief and success metrics
  • Model choice with rationale
  • Prompt and tool plan
  • RAG architecture plan
  • Risks, mitigations, and next steps

Routing Map (Modules)

  • AI Engineering -> references/modules/ai-engineer.md
  • Prompt Engineering -> references/modules/prompt-engineering-patterns.md
  • RAG Engineering -> references/modules/rag-engineer.md

Bundled References

  • references/modules/
  • scripts/
  • assets/
  • agents/

Compatibility Notes

  • If any module references slash commands or tool-specific paths, translate them into plain-language steps.
  • Keep outputs platform-agnostic unless the user specifies a specific tool, stack, or agent.

Guardrails

  • Do not claim benchmark results without data.
  • Separate measured results from hypotheses.
  • Prefer the smallest viable model and simplest retrieval setup.

What ships with it: 13 files

192.6 KB alongside SKILL.md

agents/

examples/

references/

Keep looking

Skills are one crate of 326,401. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.