Automatically optimize a skill's SKILL.md by running test cases, scoring results, and iteratively improving instructions
Scanned 5/27/2026
Install via CLI
Skills Directoryopenskills install ghbalf/freecad-ai---
name: optimize-skill
description: Automatically optimize a skill's SKILL.md by running test cases, scoring results, and iteratively improving instructions
---
# Skill Optimizer
Optimizes a FreeCAD AI skill by iteratively running it against test cases,
evaluating the results, and using the LLM to improve the SKILL.md instructions.
Inspired by [autoresearch](https://github.com/karpathy/autoresearch).
## Usage
Type `/optimize-skill` to open the configuration dialog, or
`/optimize-skill skill-name` to pre-select a skill.
## How It Works
1. Select a skill and define test cases
2. The optimizer runs each test case, collects metrics (errors, completions, measurements)
3. The LLM analyzes failures and modifies the SKILL.md
4. Repeat until the score converges or iterations are exhausted
5. The best version is saved; the original is always backed up
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
