skill-optimizer skillA
skill-optimizer is agent-read markdown (skill) from rohitg00/pro-workflow: SkillOpt-flavored offline training loop for any SKILL.md. Treats accumulated learn-rule corrections as training trajectories, proposes bounded patches via an optimizer LLM, gates each candidate against a held-out validation set built from the user's own past corrections, and ships only candidates that demonstrably improve the score. Inspired by Microsoft SkillOpt's ReflACT pipeline (rollout → reflect → aggregate → select → update → evaluate) adapted to pro-workflow's SQLite store. Use when a ski.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified before it reaches your agent: the main file against the SHA-256 recorded here, the others against the git hashes of its source commit. The deterministic audit below grades the latest version, and the same checks always give the same file the same grade.
What the file says
# Skill Optimizer Train an existing SKILL.md the way a deep-learning optimizer trains weights: via rollouts, gradient-like reflections, validation-gated acceptance. No model retraining; only the skill markdown changes. ## When to use Use this skill when: - A pro-workflow skill has accumulated 8+ learn-rule rows for it - The user reports the skill is "getting bloated" or "rules keep being repeated" - The user wants offline, budget-capped improvement over multiple sessions Do not use when: - Skill has fewer than 8 trajectories (nothing to learn from) - The user wants real-time edits (this is offline, single-shot) - No `ANTHROPIC_API_KEY` (or equivalent provider key) is available ## Architecture (mirrors SkillOpt's six-stage loop) ```text rollout pull recent learnings from SQLite (existing learn-rule rows) reflect optimizer LLM analyzes a minibatch, proposes add/delete/replace patches aggregate vote-merge patches across minibatches select clip by LR budget (default: 3 adds, 2 deletes, 3 replaces per step) update apply selected patches to a candidate skill content evaluate evaluator LLM scores candidate against held-out validation items …
Read the whole file at its exact version.
How to install
mdr add rohitg00/pro-workflow/skill-optimizer@git:20260926.d6ee15fmdr add rohitg00/pro-workflow/skill-optimizer@sha256:75c2d01cdfd00622Pin to a label to follow the author's releases, or to a sha256 for exact bytes. Either way the resolved hash is written to mdr.lock, and mdr install fetches those bytes again and checks them, so it installs them exactly or fails.
[](https://markdownregistry.com/a/art_xov3hvdqmjx23huo)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260926.d6ee15f latest | 2026-09-26 | d6ee15f | 4,737 B | A | view · diff |
| git:20260718.7f7209d | 2026-07-18 | 7f7209d | 4,748 B | A | view · diff |
| git:20260603.5c313e2 | 2026-06-03 | 5c313e2 | 4,727 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 (4737 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
rohitg00/pro-workflow · 2,885 stars · license none · pushed 2026-09-26 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xov3hvdqmjx23huo GET https://markdownregistry.com/api/v1/resolve?ref=rohitg00/pro-workflow/skill-optimizer GET https://markdownregistry.com/api/v1/blob/75c2d01cdfd006227dc7fca8a094c453e04d01450df0e891d65dcd756b331744
Your agent 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.
More from rohitg00/pro-workflow
Every file in rohitg00/pro-workflow