quantization-agent SKILL.md skillA
quantization-agent from amd-agi/hyperloom is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add amd-agi/hyperloom/quantization-agent@git:20261029.20d8b20Pins git:20261029.20d8b20 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- amd-agi/hyperloom
- Path
src/hyperloom/agents/quantization/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261029.20d8b20, committed Oct 29, 2026
- First version recorded
- Jul 8, 2026
- Size
- 16,564 bytes
- Repository stars
- 262
- License
- a license file GitHub does not identify
Hyperloom sub-agent that drives the AMD Quark PTQ skill chain end-to-end from a natural-language prompt. Produces a HuggingFace-format quantized model directory plus a structured assessment of every artifact that the Quark workflow + validator + llm-eval skills emit. Single public entry: `quantize_via_prompt(prompt, *, workspace, options=QuantSkillRunOptions(), runner_fn=None, log=None)`.
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
# quantization-agent — runtime contract You are the Hyperloom quantization-agent. This file is your **operating manual** — `driver/runner.py` loads it into every attempt. Follow it literally. The Python orchestrator (`driver/retry.py`) drives the multi-attempt loop, counter file, and final assessment assembly. You drive the per-attempt work: intake → plan → manifest → execute → validate → eval, plus all in-session auto-recovery and the diagnose-fix-retry artifacts that bridge attempts. ## 1. Purpose & boundary Produce a quantized model from the user's natural-language prompt by chaining three Quark skills (intake/plan/execute via `quark-torch-ptq`, validation via `quark-torch-result-validator`, evaluation via `quark-torch-llm-eval`). Everything goes through Quark's skill registry — do not call `examples/torch/language_modeling/llm_ptq/quantize_quark.py` directly. **Read-only-Quark invariant**: NEVER write to any path under `quark_root`. That includes `quark/`, `examples/`, `tools/`, `docs/`, `tests/`, `pyproject.toml`, `requirements.txt`. If a fix would require editing quark_root, classify the outcome as `upstream_change_required` (writes …
Read the whole file at its exact version.
How to install
mdr add amd-agi/hyperloom/quantization-agent@sha256:7105f9e0ef632dcbThe line at the top of this page pins the label git:20261029.20d8b20, 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_hhm4ijd2fwon5prg)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 8, 2026 and Oct 29, 2026, about one every 28 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261029.20d8b20 latest | 2026-10-29 | 20d8b20 | 16,564 B | A | view · diff |
| git:20261026.290f68a | 2026-10-26 | 290f68a | 16,594 B | A | view · diff |
| git:20260904.a64d24c | 2026-09-04 | a64d24c | 16,661 B | A | view · diff |
| git:20260715.3c08dba | 2026-07-15 | 3c08dba | 14,874 B | A | view · diff |
| git:20260708.14bc9cd | 2026-07-08 | 14bc9cd | 14,872 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 (16564 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
amd-agi/hyperloom · 262 stars · license a license file GitHub does not identify · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hhm4ijd2fwon5prg GET https://markdownregistry.com/api/v1/resolve?ref=amd-agi/hyperloom/quantization-agent GET https://markdownregistry.com/api/v1/blob/7105f9e0ef632dcb2989f6c897a0a62de22f60c1c623f150d57610b2ee796b16
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.