tap-model-training SKILL.md skillA
tap-model-training from muvon/octomind-tap is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add muvon/octomind-tap/tap-model-training@git:20261108.a3ce67aPins git:20261108.a3ce67a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- muvon/octomind-tap
- Path
skills/tap-model-training/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261108.a3ce67a, committed Nov 8, 2026
- First version recorded
- May 21, 2026
- Size
- 8,917 bytes
- Repository stars
- 6
- License
- Apache-2.0
Train, evaluate and publish the octomind-embed model behind capability auto-activation. Use when capability triggers or skill semantic() phrases change.
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
## Overview `muvon/octomind-embed` is the bi-encoder octomind uses to score a user message against capability triggers and skill `semantic()` phrases. Since 2026-09 it is `ibm-granite/granite-embedding-30m-english` (6 layers, 384-dim, CLS-pooled) given a short contrastive fine-tune and blended back into the base as a WiSE-FT soup; the runtime loads its int8 ONNX graph. Whenever triggers or semantic phrases change, the model is stale. This skill walks through retraining, calibration, publishing, and recovery. The cross-encoder reranker is intentionally not trained or shipped: at the current capability count it does not improve routing over a well-calibrated bi-encoder. ## Mental model The runtime decision is: intent → one installed capability, or abstain. It scores each capability as the mean of its top-3 trigger cosines and accepts the winner only if it clears an absolute threshold and beats the runner-up by a margin. The model, the trigger corpus, and those two constants are one system: retraining moves the cosine scale, so the constants must be recalibrated on the int8 graph and shipped together with the weights. …
Read the whole file at its exact version.
How to install
mdr add muvon/octomind-tap/tap-model-training@sha256:a96b314cab6b5a05The line at the top of this page pins the label git:20261108.a3ce67a, 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_w6jy5jn7yzwd7457)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between May 21, 2026 and Nov 8, 2026, about one every 57 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261108.a3ce67a latest | 2026-11-08 | a3ce67a | 8,917 B | A | view · diff |
| git:20261013.a69e0bb | 2026-10-13 | a69e0bb | 9,562 B | A | view · diff |
| git:20260918.40e721d | 2026-09-18 | 40e721d | 10,896 B | A | view · diff |
| git:20260521.1caaaf0 | 2026-05-21 | 1caaaf0 | 10,898 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 (8917 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
muvon/octomind-tap · 6 stars · license Apache-2.0 · pushed 2026-11-08 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_w6jy5jn7yzwd7457 GET https://markdownregistry.com/api/v1/resolve?ref=muvon/octomind-tap/tap-model-training GET https://markdownregistry.com/api/v1/blob/a96b314cab6b5a058d9c39e90b953f2780ad9bfffcaca23cd0929ed233b0be1b
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.