Home / lynricsy / hyperskills · GitHub

ai-engineering SKILL.md skillA

ai-engineering from lynricsy/hyperskills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add lynricsy/hyperskills/ai-engineering@v2026.10.15

Pins v2026.10.15 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: lynricsy/hyperskills
Path: skills/ai-engineering/SKILL.md
Versions recorded: 5
Latest version: v2026.10.15, committed Oct 15, 2026
First version recorded: Sep 29, 2026
Size: 21,069 bytes
Repository stars: 25
License: MIT

Builds LLM apps: prompts, tool-using agents, RAG context and evals; not vector-index tuning.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# ai-engineering

Paths below are relative to this skill's directory.

## Scope

The code around the model call: what goes into the prompt, what shape comes
back, which tools the model may reach, how retrieved text is selected and
budgeted, how the loop stops, and how any of it is measured.

Calling a model someone else trained is the `ai-engineering` skill's job; changing the weights is the `ml-training` skill's.

The rules below hold for the OpenAI, Anthropic and Google SDKs and wrappers
over them; where a provider genuinely differs, the reference says so. Use the
SDK the repository already has.

Not covered — do not answer from this skill:

- Fine-tuning, LoRA, RLHF, quantisation, distillation, dataset curation for
  training, and GPU training runs: the `ml-training` skill.
- Models that emit or read pixels, video frames or audio samples — image
  generation and editing, video generation, speech synthesis and
  recognition, local diffusion: the `generative-media` skill. The prompt,
  tool and injection rules here still apply when an agent calls one.
- Vector index internals and query tuning — HNSW/IVF parameters, recall
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add lynricsy/hyperskills/ai-engineering@sha256:c5a713fa3897359b

The line at the top of this page pins the label v2026.10.15, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_pxea2g6nl47nspsj.svg)](https://markdownregistry.com/a/art_pxea2g6nl47nspsj)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Sep 29, 2026 and Oct 15, 2026, about one every 4 days.

version	committed	commit	size	audit
v2026.10.15 latest	2026-10-15	d5dabaa	21,069 B	A	view · diff
v2026.10.15	2026-10-15	b7c481f	21,066 B	A	view · diff
v2026.10.15	2026-10-15	77a04d3	21,046 B	A	view · diff
v2026.09.30	2026-09-30	624fd7e	21,046 B	A	view · diff
v2026.09.29	2026-09-29	5c78d6c	21,046 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (21069 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

lynricsy/hyperskills · 25 stars · license MIT · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_pxea2g6nl47nspsj
GET https://markdownregistry.com/api/v1/resolve?ref=lynricsy/hyperskills/ai-engineering
GET https://markdownregistry.com/api/v1/blob/c5a713fa3897359bac8bc4feb0b2ded462297e7b33f730b1293e7b5466c9d49a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from lynricsy/hyperskills

AGENTS.md AGENTS.md file

lynricsy/hyperskills · AGENTS.md

git:20261015.8cec18e · audit A · 25 stars

android SKILL.md skill

lynricsy/hyperskills · skills/android/SKILL.md · Develops native Android apps with Kotlin, Jetpack Compose and Gradle.