atai-task-verification-agent SKILL.md skillA
atai-task-verification-agent from archetypeai/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add archetypeai/agent-skills/atai-task-verification-agent@git:20261030.0e5182aPins 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-task-verification-agent/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261030.0e5182a, committed Oct 30, 2026
- First version recorded
- Oct 1, 2026
- Size
- 38,041 bytes
- Repository stars
- 7
- License
- Apache-2.0
Run Archetype AI's managed Task Verification (TVA) agent over the Agents API — upload a recording AND a reference procedure (an SOP), create a bundle from the `tva` blueprint, run it, poll, download a per-step PASSED / FAILED / MISSING verdict per step. Use when the user has a recording of work that should have followed a known procedure and wants to know whether each step was performed — assembly QA, maintenance sign-off, training assessment, SOP compliance. Covers the runtime SOP input…
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
# TVA Agent — Managed Task Verification via the Agents API
The TVA agent checks a recording against a procedure you supply. You hand the platform an `.mp4` **and** an SOP as a `.txt`; it samples frames, transcribes the audio, fuses both with your procedure in one pass, and returns one verdict per SOP step:
```
video ──► sample frames ──► preprocess ─┐
├─► newton-fusion f1-0 ─► parse ─► per-step verdicts
SOP (.txt) ──► PrepareSOPNode ──────────┤
whisper ASR ───────────────────┘
```
TVA V1 is **zero-shot**. The `tva` blueprint pins its own models (`newton-fusion-1-0` and `whisper-base` since the 2026-10-15 blueprint; `newton-fusion:1.0` and `whisper:large-v3` before it), so like `mga` — and unlike `osm`/`red` — there is **no classifier to fit and no `artifacts` map to pass**.
## When to Apply
**Use when** the procedure is already known and the question is whether it was followed: did the operator install the o-ring, torque the fitting, apply the tape? Each verdict carries a status, a time range and a reason.
…Read the whole file at its exact version.
How to install
mdr add archetypeai/agent-skills/atai-task-verification-agent@sha256:e1d69096dcb46524The 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.
[](https://markdownregistry.com/a/art_q6vfc4uzmcfcoou4)
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.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261030.0e5182a latest | 2026-10-30 | 0e5182a | 38,041 B | A | view · diff |
| git:20261027.4139bd5 | 2026-10-27 | 4139bd5 | 37,753 B | A | view · diff |
| git:20261027.86b5644 | 2026-10-27 | 86b5644 | 37,962 B | A | view · diff |
| git:20261019.d648daa | 2026-10-19 | d648daa | 33,882 B | A | view · diff |
| git:20261001.ee14152 | 2026-10-01 | ee14152 | 33,872 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (38041 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
archetypeai/agent-skills · 7 stars · license Apache-2.0 · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_q6vfc4uzmcfcoou4 GET https://markdownregistry.com/api/v1/resolve?ref=archetypeai/agent-skills/atai-task-verification-agent GET https://markdownregistry.com/api/v1/blob/e1d69096dcb46524b3065b909f020f87e03284ff2049cabe64a2732ccd888405
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.