Agent skill

Optimize Skill

by ghbalf in ghbalf/freecad-ai

Automatically optimize a skill's SKILL.md by running test cases, scoring results, and iteratively improving instructions

LGPL-2.1Auto-check passedTesting & QA

Install Optimize Skill

skills CLI
$ npx skills add ghbalf/freecad-ai --skill optimize-skill -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ghbalf/freecad-ai optimize-skill --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ghbalf/freecad-ai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/optimize-skill .claude/skills/optimize-skill && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
optimize-skill
GitHub stars
550
Token cost
~216 tokens
SKILL.md length
98 words
Files
2
Skills in repo
9
Repo updated
First seen
Licence
LGPL-2.1

At a glance

Automatically optimize a skill's SKILL.md by running test cases, scoring results, and iteratively improving instructions

  • Works in 5 steps: Select a skill and define test cases → The optimizer runs each test case,… → The LLM analyzes failures and modifies… → …
  • Tasks that involve Test generation
  • SKILL.md covers Usage and How It Works
  • Runs Python scripts from its folder

What it does

Optimize Skill is an agent skill from ghbalf/freecad-ai. Automatically optimize a skill's SKILL.md by running test cases, scoring results, and iteratively improving instructions

Its SKILL.md is about 220 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `handler.py`).

It sits in Testing & QA, covering Test generation. The repository describes itself as: AI-powered assistant workbench for FreeCAD — generate 3D models from natural language.

When your agent uses it

  • Tasks that involve Test generation

Example prompts

  • “/optimize-skill”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  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

What it can do on your machine

Read from SKILL.md and the folder at commit 5ef1e2d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Optimize Skill loads about 216 tokens when it runs. Until then it costs about 34 tokens; SKILL.md has 98 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~34
When it runs · the whole SKILL.md, loaded when a task matches
~216

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ghbalf/freecad-ai at commit 5ef1e2d, republished under its LGPL-2.1 licence (© ghbalf). 98 words, ~216 tokens.

Download SKILL.mdSave it as .claude/skills/optimize-skill/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
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.

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

© ghbalf, LGPL-2.1. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/optimize-skill of ghbalf/freecad-ai.

  • SKILL.md
  • handler.py

Open the folder on GitHubat commit 5ef1e2d

Compare with similar skills

Optimize Skill next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Optimize Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Optimize Skill this skillghbalf/freecad-ai550—~216Automated safety check: PassLGPL-2.1
Emcaklofas/kicad-happy1.4k1 repos~2.8kAutomated safety check: PassMIT
Swig Testswig/swig6.3k—~2.3kAutomated safety check: PassCustom licence
Generate Test Cases342164796/generate-test-cases1191 repos~2.9kAutomated safety check: PassNone
Verify Cc Safety Netkenryu42/cc-safety-net1.6k—~2kAutomated safety check: PassMIT
Wioworkersio/skills190—~5.8kAutomated safety check: PassMIT

Similar skills

  • Emc

    aklofas/kicad-happy

    EMC pre-compliance risk analysis for KiCad PCB designs — 18 check categories, 44 rule IDs covering ground planes, decoupling, I/O filtering, switching harmonics, clock routing, differential pair…

    1.4k GitHub starsUsed in 1 repo~2.8k tokens
    Testing & QAAuto-check passed
  • Swig Test

    swig/swig

    Run SWIG test suite for specific languages. An agent skill from swig/swig.

    6.3k GitHub stars~2.3k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Generate Test Cases

    342164796/generate-test-cases

    自主学习型测试文档生成器。从需求文档(Markdown)生成测试用例 XMind 文件,支持持久化记忆和持续学习。当用户提到"生成测试用例"、"根据需求生成测试"时触发。

    119 GitHub starsUsed in 1 repo~2.9k tokens
    Testing & QAAuto-check passed
  • Verify Cc Safety Net

    kenryu42/cc-safety-net

    Launch and drive the real cc-safety-net CLI — the hook decision path, explain, status/doctor, logs, and the local policy GUI — against an isolated home, capturing evidence.

    1.6k GitHub stars~2k tokensUpdated today
    Testing & QAAuto-check passed
  • Wio

    workersio/skills

    Testing workflow skill for finding high-value test candidates, writing focused tests, generating realistic workloads, reviewing test value, and diagnosing test-suite health.

    190 GitHub stars~5.8k tokensUpdated 2 mo ago
    Testing & QAAuto-check passed
  • File Server

    microsoft/WindowsProtocolTestSuites

    Official

    ALWAYS LOAD THIS SKILL when working with FileServer, SMB, SMB2, SMB3, CIFS, file sharing, MS-SMB2, MS-FSCC, MS-FSA, MS-DFSC, MS-FSRVP, MS-RSVD, MS-SQOS, or any file server protocol test…

    567 GitHub stars~4.1k tokensUpdated 23 days ago
    Testing & QAAuto-check passed

More from ghbalf/freecad-ai

All 9 skills in this repo
  • Skill Creator

    ghbalf/freecad-ai

    Create new FreeCAD AI skills, modify existing skills, and iteratively improve them.

    550 GitHub stars~2.7k tokensUpdated 4 days ago
    Auto-check passed
  • Create Validation

    ghbalf/freecad-ai

    Generate a draft VALIDATION.md for a skill by analyzing its SKILL.md construction steps

    550 GitHub stars~1.2k tokensUpdated 4 days ago
    Auto-check passed
  • Enclosure

    ghbalf/freecad-ai

    Generate a parametric electronics enclosure with a base and lid.

    550 GitHub stars~1.5k tokensUpdated 4 days ago
    Auto-check passed
  • Fastener Hole

    ghbalf/freecad-ai

    Create standard fastener holes: clearance, counterbore, or countersink.

    550 GitHub stars~487 tokensUpdated 4 days ago
    Auto-check passed
  • Gear

    ghbalf/freecad-ai

    Create an involute spur gear using FreeCAD's Part module. An agent skill from ghbalf/freecad-ai.

    550 GitHub stars~1.2k tokensUpdated 4 days ago
    Auto-check passed
  • Lattice

    ghbalf/freecad-ai

    Generate a 3D lattice or infill pattern inside a bounding region.

    550 GitHub stars~483 tokensUpdated 4 days ago
    Auto-check passed

Categories

Questions about Optimize Skill

What does Optimize Skill do?

Automatically optimize a skill's SKILL.md by running test cases, scoring results, and iteratively improving instructions. Optimize Skill is an agent skill from ghbalf/freecad-ai.

When should I use Optimize Skill?

Optimize Skill fits situations like: tasks that involve Test generation.

How do I install Optimize Skill in Claude Code?

Run `npx skills add ghbalf/freecad-ai --skill optimize-skill -a claude-code`. Or copy the skill folder (skills/optimize-skill in ghbalf/freecad-ai) into .claude/skills/optimize-skill in your project. Claude Code loads it when a task matches its description.

How do I install Optimize Skill in Codex?

Run `npx skills add ghbalf/freecad-ai --skill optimize-skill -a codex`. Or copy the skill folder (skills/optimize-skill in ghbalf/freecad-ai) into .agents/skills/optimize-skill in your project. Codex loads it when a task matches its description.

Can I use Optimize Skill in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ghbalf/freecad-ai --skill optimize-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/optimize-skill, .gemini/skills/optimize-skill, .github/skills/optimize-skill and .opencode/skills/optimize-skill in your project.

What does Optimize Skill need to run?

Going by SKILL.md and its folder, Optimize Skill needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Optimize Skill access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Optimize Skill safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Optimize Skill use?

Optimize Skill is published under the LGPL-2.1 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Optimize Skill use?

About 216 tokens (SKILL.md is roughly 864 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Optimize Skill?

Skills that share tags, products or a category with Optimize Skill: Emc (aklofas/kicad-happy, 1.4k stars), Swig Test (swig/swig, 6.3k stars), Generate Test Cases (342164796/generate-test-cases, 119 stars) and Verify Cc Safety Net (kenryu42/cc-safety-net, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Optimize Skill?

ghbalf (a GitHub user) maintains it in ghbalf/freecad-ai, which has 550 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 3, 2026.

Source: ghbalf/freecad-ai on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.