Home / rohitg00 / pro-workflow · skills/skill-optimizer/SKILL.md · GitHub

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

Latest version
mdr add rohitg00/pro-workflow/skill-optimizer@git:20260926.d6ee15f
Exact content
mdr add rohitg00/pro-workflow/skill-optimizer@sha256:75c2d01cdfd00622

Pin 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_xov3hvdqmjx23huo.svg)](https://markdownregistry.com/a/art_xov3hvdqmjx23huo)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260926.d6ee15f latest2026-09-26 d6ee15f 4,737 BA view · diff
git:20260718.7f7209d2026-07-18 7f7209d 4,748 BA view · diff
git:20260603.5c313e22026-06-03 5c313e2 4,727 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • 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

GitHub

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

agent-teams skill
rohitg00/pro-workflow · skills/agent-teams/SKILL.md · Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and…
git:20260718.7f7209d · audit A · 2,885 stars
auto-setup skill
rohitg00/pro-workflow · skills/auto-setup/SKILL.md · Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate…
git:20260718.7f7209d · audit A · 2,885 stars
batch-orchestration skill
rohitg00/pro-workflow · skills/batch-orchestration/SKILL.md · Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for…
git:20260718.7f7209d · audit A · 2,885 stars
bug-capture skill
rohitg00/pro-workflow · skills/bug-capture/SKILL.md · Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the…
git:20260417.f9e421e · audit A · 2,885 stars
compact-guard skill
rohitg00/pro-workflow · skills/compact-guard/SKILL.md · Smart context compaction with state preservation. Saves critical files, task progress, and working state before…
git:20260718.7f7209d · audit A · 2,885 stars
context-engineering skill
rohitg00/pro-workflow · skills/context-engineering/SKILL.md · Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction…
git:20260926.d6ee15f · audit A · 2,885 stars
context-optimizer skill
rohitg00/pro-workflow · skills/context-optimizer/SKILL.md · Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of…
git:20260718.7f7209d · audit A · 2,885 stars
cost-tracker skill
rohitg00/pro-workflow · skills/cost-tracker/SKILL.md · Track session costs, set budget alerts, and optimize token spend. Use to check costs mid-session or set spending limits.
git:20260718.7f7209d · audit A · 2,885 stars
design-engineering skill
rohitg00/pro-workflow · skills/design-engineering/SKILL.md · Apply interface craft when building or reviewing UI - motion, easing, timing, springs, component feel, and visual…
git:20260718.7f7209d · audit A · 2,885 stars
deslop skill
rohitg00/pro-workflow · skills/deslop/SKILL.md · Remove AI-generated code slop, unnecessary comments, and over-engineering from the current branch diff. Cleans up…
git:20260718.7f7209d · audit A · 2,885 stars
domain-modeling skill
rohitg00/pro-workflow · skills/domain-modeling/SKILL.md · Build the project's shared language and bounded contexts before writing code, so names stay consistent and the agent…
git:20260718.7f7209d · audit A · 2,885 stars
file-watcher skill
rohitg00/pro-workflow · skills/file-watcher/SKILL.md · Configure file watching hooks to auto-react to config changes, env file updates, and dependency modifications. Use to…
git:20260718.7f7209d · audit A · 2,885 stars

Every file in rohitg00/pro-workflow

Other files named skill-optimizer

skill-optimizer skill
tdimino/claude-code-minoan · skills/core-development/skill-optimizer/SKILL.md · Guide creating and reviewing skills that extend Claude with specialized knowledge, workflows, or tool integrations…
git:20260416.4e43d41 · audit A · 41 stars
skill-optimizer skill
s977043/river-review · .claude/skills/skill-optimizer/SKILL.md · Evaluate and improve an existing Claude Code skill using explicit success criteria and small controlled changes. Use…
git:20260321.857d5ca · audit A · 3 stars

Browse by kind, by grade A, or by owner.