atai-manual-generation-agent SKILL.md skillA

atai-manual-generation-agent from archetypeai/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add archetypeai/agent-skills/atai-manual-generation-agent@git:20261030.0e5182a

Pins git:20261030.0e5182a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
archetypeai/agent-skills
Path
skills/atai-manual-generation-agent/SKILL.md
Versions recorded
5
Latest version
git:20261030.0e5182a, committed Oct 30, 2026
First version recorded
Oct 1, 2026
Size
37,556 bytes
Repository stars
7
License
Apache-2.0

Run Archetype AI's managed Manual Generation (MGA) agent over the Agents API — upload a procedure video, create a bundle from the canonical `mga` blueprint, run it, poll, download an ordered, timestamped manual. Use when the user has a recording of a procedure (a repair, an assembly, a workflow) and wants the platform to turn it into step-by-step instructions traceable back to the video. Covers video suitability (the ~5-minute ceiling, the audio-track requirement), the bundle request shape…

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

# MGA Agent — Managed Manual Generation via the Agents API

The MGA agent turns a procedure video into an ordered manual with timestamps. You hand the platform an `.mp4`; it samples frames, transcribes the audio, fuses both in one pass, and returns steps you can trace back to the recording:

```
video ─► sample frames ─┐
                        ├─► newton-fusion f1-0 ─► parse ─► steps + timestamps
        whisper ASR ────┘
```

MGA V1 is **zero-shot**. The `mga` blueprint pins its own models (`newton-fusion-1-0` and `whisper-base` on production as of 2026-10-27; older versions used `newton-fusion:1.0` and `whisper:large-v3`), so unlike `osm`/`red` there is **no classifier to fit and no `artifacts` map to pass**. A run is upload → bundle → run → download.

> **Availability.** The canonical `mga` blueprint resolves by key on the
> production deployment (`https://platform.u1.archetypeai.app/api`) — set
> `ATAI_API_ENDPOINT` to it and the full upload → bundle → run → score cycle
> works as documented here. Re-verified **2026-10-27** on `blp_7vc935…`: four
> runs on the same 173 s video took **610–618 s** each — ~13 s queued, whisper
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add archetypeai/agent-skills/atai-manual-generation-agent@sha256:6409651d937e7009

The line at the top of this page pins the label git:20261030.0e5182a, 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 badge

[![mdr](https://markdownregistry.com/badge/art_s3gli5nnfmcvry2n.svg)](https://markdownregistry.com/a/art_s3gli5nnfmcvry2n)

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

Versions

The registry has recorded 5 versions of this file, between Oct 1, 2026 and Oct 30, 2026, about one every 7 days.

versioncommittedcommitsizeaudit
git:20261030.0e5182a latest2026-10-30 0e5182a 37,556 BA view · diff
git:20261027.4139bd52026-10-27 4139bd5 37,257 BA view · diff
git:20261027.e45ac002026-10-27 e45ac00 37,535 BA view · diff
git:20261019.d648daa2026-10-19 d648daa 30,226 BA view · diff
git:20261001.ee141522026-10-01 ee14152 30,216 BA 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 (37556 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

archetypeai/agent-skills · 7 stars · license Apache-2.0 · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_s3gli5nnfmcvry2n
GET https://markdownregistry.com/api/v1/resolve?ref=archetypeai/agent-skills/atai-manual-generation-agent
GET https://markdownregistry.com/api/v1/blob/6409651d937e700948bfc2fb0c01dd374a2b810fe5de8a3ee24bb4a3a9ce2f30

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 archetypeai/agent-skills

atai-anomaly-discovery-agent-data-prep SKILL.md skill
archetypeai/agent-skills · skills/atai-anomaly-discovery-agent-data-prep/SKILL.md · Prepare sensor recordings for Archetype AI's Anomaly Discovery (AD) agent, locally and with no API key: put every…
git:20261101.aee212a · audit A · 7 stars
atai-anomaly-discovery-agent SKILL.md skill
archetypeai/agent-skills · skills/atai-anomaly-discovery-agent/SKILL.md · Run Archetype AI's Anomaly Discovery (AD) agent over the Agents API, on two paths. Path 1 — run the maintained "AD…
git:20261101.8ac6f2c · audit B · 7 stars
atai-design-system SKILL.md skill
archetypeai/agent-skills · skills/atai-design-system/SKILL.md · Build the front-end for a Newton demo with the Archetype AI Design System — the published, versioned packages…
git:20260818.d447df4 · audit A · 7 stars
atai-newton-fusion-model SKILL.md skill
archetypeai/agent-skills · skills/atai-newton-fusion-model/SKILL.md · Call Newton's C 2.6 fusion model (`Newton::c2_6_8b_fp8_260424d7a55d5e`) on the prod `/query` endpoint with text, image…
git:20261019.153f693 · audit B · 7 stars
atai-newton-omega-model-data-prep SKILL.md skill
archetypeai/agent-skills · skills/atai-newton-omega-model-data-prep/SKILL.md · Clean, split, and featurize multivariate time-series data before embedding it with the Omega model. Bundles three…
git:20261001.a0b5603 · audit A · 7 stars
atai-newton-omega-model SKILL.md skill
archetypeai/agent-skills · skills/atai-newton-omega-model/SKILL.md · Get time-series embeddings from Archetype AI's Omega encoder (`OmegaEncoder::omega_embeddings_1_4`) over the prod…
git:20261019.153f693 · audit B · 7 stars
atai-newton-omega-nvidia-nemotron SKILL.md skill
archetypeai/agent-skills · skills/atai-newton-omega-nvidia-nemotron/SKILL.md · Pair Archetype AI's Omega encoder (`OmegaEncoder::omega_embeddings_1_4` over `/query`) with NVIDIA Nemotron on NVIDIA's…
git:20261007.0bba2d3 · audit A · 7 stars
atai-operational-state-monitoring-agent-data-prep SKILL.md skill
archetypeai/agent-skills · skills/atai-operational-state-monitoring-agent-data-prep/SKILL.md · Prepare labelled sensor recordings for Archetype AI's Operational State Monitoring (OSM) agent, locally and with no API…
git:20261101.af1fb27 · audit A · 7 stars
atai-operational-state-monitoring-agent SKILL.md skill
archetypeai/agent-skills · skills/atai-operational-state-monitoring-agent/SKILL.md · Run Archetype AI's Operational State Monitoring (OSM) agent over the Agents API, on two paths. Path 1 — run a…
git:20261101.2ce5ab3 · audit B · 7 stars
atai-rare-event-detection-agent-data-prep SKILL.md skill
archetypeai/agent-skills · skills/atai-rare-event-detection-agent-data-prep/SKILL.md · Prepare a labelled sensor recording for Archetype AI's Rare Event Detection (RED) agent, locally and with no API key…
git:20261101.3272771 · audit A · 7 stars
atai-rare-event-detection-agent SKILL.md skill
archetypeai/agent-skills · skills/atai-rare-event-detection-agent/SKILL.md · Run Archetype AI's Rare Event Detection (RED) agent over the Agents API, on two paths. Path 1 — run the maintained "RED…
git:20261102.d2f5914 · audit B · 7 stars
atai-task-verification-agent SKILL.md skill
archetypeai/agent-skills · skills/atai-task-verification-agent/SKILL.md · Run Archetype AI's managed Task Verification (TVA) agent over the Agents API — upload a recording AND a reference…
git:20261030.0e5182a · audit A · 7 stars

Every file in archetypeai/agent-skills

Browse by kind, by grade A, or by owner.