martinholovsky/sota-skills · skills/sota-llm-engineering/SKILL.md

sota-llm-engineering skillA

State-of-the-art LLM application engineering rules (mid-2026 baseline) for BUILDING and AUDITING LLM-powered features. Claude should use this skill whenever it is building, modifying, or reviewing anything that calls a language model — chat features, RAG pipelines, agents and tool use, structured extraction, classification, summarization, embeddings/vector search, evals and regression gates, prompt or context engineering, model selection/routing, fine-tuning decisions, or LLM cost/latency/observ

Latest version
mdr add martinholovsky/sota-skills/sota-llm-engineering@git:20260903.36172e4
Exact content
mdr add martinholovsky/sota-skills/sota-llm-engineering@sha256:44998239d948263b
Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_jgtyk5axlbysgjwk.svg)](https://markdownregistry.com/a/art_jgtyk5axlbysgjwk)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260903.36172e4 latest2026-09-03 36172e4 12,748 BA view · diff
git:20260903.02cb41e2026-09-03 02cb41e 12,669 BA view · diff
git:20260827.8610b012026-08-27 8610b01 12,489 BA view · diff
git:20260724.d1f5ab02026-07-24 d1f5ab0 12,461 BA view · diff
git:20260617.c5d2c7b2026-06-17 c5d2c7b 12,362 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.

Source

GitHub

martinholovsky/sota-skills · 18 stars · license CC-BY-4.0 · pushed 2026-09-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_jgtyk5axlbysgjwk
GET https://markdownregistry.com/api/v1/resolve?ref=martinholovsky/sota-skills/sota-llm-engineering
GET https://markdownregistry.com/api/v1/blob/44998239d948263b1e32a95c65fc0c9262f35130e8d5085be14824fbb1701f05