aide-training-phase-b3-eval-export SKILL.md skillC
aide-training-phase-b3-eval-export from anonymousnomad/aide-sovereign-workbench is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add anonymousnomad/aide-sovereign-workbench/aide-training-phase-b3-eval-export@git:20260823.df7cbdePins git:20260823.df7cbde in mdr.lock. Pin the fingerprint instead.
- Audit grade
- C, 14 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- anonymousnomad/aide-sovereign-workbench
- Path
skills/packs/aide-training-phase-b3-eval-export/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260823.df7cbde, committed Aug 23, 2026
- Size
- 3,196 bytes
- Repository stars
- 53
- License
- Apache-2.0
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 Phase B3 — Eval Gates + GGUF Export Loop ## What Close the training loop with fail-closed evaluation: validation-perplexity curve from the run, a task-eval harness (held-out prompts scored by exact-match/rubric) comparing tuned vs base, a general-capability forgetting probe, then merged-GGUF export at Q4_K_M → existing ingest → instantly chat-testable. Registration into the model manifest is BLOCKED unless the tuned model beats its baseline by the recorded threshold. ## Why "If you don't measure, you don't know" — every 2026 guide makes eval-before-deploy non-negotiable: perplexity alone is not task performance; evaluate AT deployment quantization (Q4_K_M), and probe for catastrophic forgetting when training on narrow data (mix 5–20% general data / lower lr / fewer epochs are the documented mitigations). Our own Phase-9 doctrine adds the local law: no-vacuous-pass — gates without gold or with degenerate outputs are FAILs. ## Code Plan - `node/src/services/training-eval.ts`: given job dir + locked B1 split → 1. **Perplexity**: read trainer eval_loss history from run log (already streamed in B2); report best step vs final. …
Read the whole file at its exact version.
How to install
mdr add anonymousnomad/aide-sovereign-workbench/aide-training-phase-b3-eval-export@sha256:592c7a4c8def9173The line at the top of this page pins the label git:20260823.df7cbde, 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_s6afjbcx6volkhg7)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 23, 2026.
Audit of the latest version
- fail: Frontmatter block present
- fail: Frontmatter declares a name
- fail: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3196 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
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
anonymousnomad/aide-sovereign-workbench · 53 stars · license Apache-2.0 · pushed 2026-10-26 · branch covert-production
API
GET https://markdownregistry.com/api/v1/artifacts/art_s6afjbcx6volkhg7 GET https://markdownregistry.com/api/v1/resolve?ref=anonymousnomad/aide-sovereign-workbench/aide-training-phase-b3-eval-export GET https://markdownregistry.com/api/v1/blob/592c7a4c8def9173263d905e81ce1fbb30175c57aa1d9f4e5718b5904ba3346e
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.