local-distillation-lab SKILL.md skillA
local-distillation-lab from understudylabs/orchestra-agent-tools is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add understudylabs/orchestra-agent-tools/local-distillation-lab@git:20260719.1185398Pins git:20260719.1185398 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- understudylabs/orchestra-agent-tools
- Path
skills/local-distillation-lab/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260719.1185398, committed Jul 19, 2026
- First version recorded
- Jun 7, 2026
- Size
- 7,460 bytes
- Repository stars
- 19
- License
- MIT
Use when a developer wants to fine-tune or distill a local open model on their Mac and see which training method actually moves a captured workload — "fine-tune a local model", "distill the frontier into a small model", "would training close the gap". Compares baseline, rejection-sampled fine-tuning, distillation, and surprisal-gated pedagogical arms; includes learning from privileged answers/feedback.
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
# Local Distillation Lab Train a local student model and measure which **post-training method** actually moves a captured workload — without spending on hosted training. The student samples/learns on your Mac; the only optional spend is a frontier teacher you can almost always avoid. This is the missing **weight-update rung**: `optimize-workload` (GEPA) explicitly does not train; `prepare-verifier-handoff` jumps to hosted RL. This skill is what sits between them. ## When To Use - The developer has a captured workload with a verifiable reward (final-state validator, recall/precision-vs-gold, etc.) and frozen train/dev/holdout splits. - Prompt optimization has plateaued and the question is now "can a weight update close the gap." - They want a **method comparison** (SFT-RS vs off-policy distill vs pedagogical/OPSD), not a single blind training run. If the workload only needs prompt/route changes, use [`../optimize-workload/SKILL.md`](../optimize-workload/SKILL.md). If it genuinely needs hosted multi-step RL, use [`../prepare-verifier-handoff/SKILL.md`](../prepare-verifier-handoff/SKILL.md). ## Safety Gates …
Read the whole file at its exact version.
How to install
mdr add understudylabs/orchestra-agent-tools/local-distillation-lab@sha256:f2d12a4639793f47The line at the top of this page pins the label git:20260719.1185398, 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_ckgucyxqkizpmsl5)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Jun 7, 2026 and Jul 19, 2026, about one every 14 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260719.1185398 latest | 2026-07-19 | 1185398 | 7,460 B | A | view · diff |
| git:20260609.050d8ac | 2026-06-09 | 050d8ac | 7,429 B | A | view · diff |
| git:20260607.5275481 | 2026-06-07 | 5275481 | 6,707 B | A | view · diff |
| git:20260607.3babe7d | 2026-06-07 | 3babe7d | 7,151 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 (7460 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
understudylabs/orchestra-agent-tools · 19 stars · license MIT · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ckgucyxqkizpmsl5 GET https://markdownregistry.com/api/v1/resolve?ref=understudylabs/orchestra-agent-tools/local-distillation-lab GET https://markdownregistry.com/api/v1/blob/f2d12a4639793f4703da74d576d5cf8f483202ce2958eca81efd57b61f7c3349
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.