distill-classifier SKILL.md skillA
distill-classifier 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/distill-classifier@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/distill-classifier/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260719.1185398, committed Jul 19, 2026
- First version recorded
- Jun 9, 2026
- Size
- 6,339 bytes
- Repository stars
- 19
- License
- MIT
Use when a developer wants to replace an expensive frontier model on a classification workload (binary, multi-class, multi-label, or structured extraction) with a fine-tuned open-weight student — "distill this classifier", "can a small model do this tagging job", "the frontier labels these for $X, make it cheaper", "consensus-label my data". Multi-teacher majority-vote labeling, failure-directed SFT data, and a four-way promote/shadow/collect/stop verdict.
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
# Distill Classifier Most production LLM calls are not agents — they are classifiers: tag, route, score, extract. This worker replaces a frontier classifier with a fine-tuned open-weight student using **teacher-as-labeler hard-label distillation**: an ensemble of teachers votes labels onto unlabeled rows, the student trains on the consensus, and a gated verdict decides whether it ships. It does not cover reasoning or tool-calling workloads — for those use [`../compare-trajectories/SKILL.md`](../compare-trajectories/SKILL.md) and the training rungs it feeds. ## Decision Gate Right move when the task is **knowledge-bound classification** (domain label boundaries, not instruction-following), call volume justifies a ~$5–15 experiment, and either the teacher's logits are closed (hard labels are all you can get) or several teachers are available. Wrong move when prompt optimization hasn't been tried — run [`../optimize-workload/SKILL.md`](../optimize-workload/SKILL.md) (GEPA) first; it has moved classifiers +8pp accuracy with no weight update, and SFT is only warranted after it plateaus against a **measured baseline**. ## Safety Gates …
Read the whole file at its exact version.
How to install
mdr add understudylabs/orchestra-agent-tools/distill-classifier@sha256:bd7c8a472d436a0fThe 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_txcettgdyrvxaj6z)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Jun 9, 2026 and Jul 19, 2026, about one every 20 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260719.1185398 latest | 2026-07-19 | 1185398 | 6,339 B | A | view · diff |
| git:20260609.050d8ac | 2026-06-09 | 050d8ac | 6,225 B | A | view · diff |
| git:20260609.14cd52c | 2026-06-09 | 14cd52c | 6,229 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 (6339 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_txcettgdyrvxaj6z GET https://markdownregistry.com/api/v1/resolve?ref=understudylabs/orchestra-agent-tools/distill-classifier GET https://markdownregistry.com/api/v1/blob/bd7c8a472d436a0f24b9b82c0ba2cc984a835093dc8d0c44c8f74605c4e814a4
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.