training-audit SKILL.md skillA
training-audit from uchicago-dsi/ai-sci-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add uchicago-dsi/ai-sci-skills/training-audit@git:20261028.67cee2dPins git:20261028.67cee2d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- uchicago-dsi/ai-sci-skills
- Path
skills/training-audit/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261028.67cee2d, committed Oct 28, 2026
- First version recorded
- Oct 19, 2026
- Size
- 5,391 bytes
- Repository stars
- 20
- License
- MIT
Diagnose training instability, early validation decline, or uncertain convergence from saved run evidence, and choose a controlled optimization check before rejecting a method.
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
# Training audit Turn a training symptom into an evidence-backed diagnosis and the smallest next check that could change it. Use existing trainers, evaluators and run artifacts; this skill does not introduce another training or tuning loop. Invoke with `$training-audit` and a run directory, plus the symptom or comparison to investigate. Return the evidence-backed diagnosis, unresolved explanations and one discriminating next check. If the run artifacts are incomplete, identify the missing evidence before recommending a sweep. ## Establish what actually ran Read the run's saved effective config, producing commit, checkpoint metadata and measurement registration. A similarly named config in today's checkout is not historical evidence. Reconcile encoder/head/projector parameter ownership, actual LRs, optimizer, schedule, initialization, precision, batch construction, inputs and exposure. Distinguish intended configuration from executed/logged behavior. Name missing evidence rather than reconstructing it from a convenient default. For a historical audit, make one compact row per materially different recipe: …
Read the whole file at its exact version.
How to install
mdr add uchicago-dsi/ai-sci-skills/training-audit@sha256:eb78931314ab97b1The line at the top of this page pins the label git:20261028.67cee2d, 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_rupsu3pyk6qlxkb7)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Oct 19, 2026 and Oct 28, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261028.67cee2d latest | 2026-10-28 | 67cee2d | 5,391 B | A | view · diff |
| git:20261019.181bcba | 2026-10-19 | 181bcba | 5,099 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 (5391 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
uchicago-dsi/ai-sci-skills · 20 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_rupsu3pyk6qlxkb7 GET https://markdownregistry.com/api/v1/resolve?ref=uchicago-dsi/ai-sci-skills/training-audit GET https://markdownregistry.com/api/v1/blob/eb78931314ab97b1bc8ca2fcfd62d4354df87ae860c4f8444b096289f37ae796
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.