Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Optimize Skill

skill · ghbalf/freecad-aiLGPL-2.1 licenceAudited 19 Oct 2026 · source 24034f36bad7

★ 577pushed 2 days ago
✓SAFEGrade B · 89/100 · 19 Oct 2026 · 24034f3
577repo stars · whole ghbalf/freecad-ai
InstallView source on GitHub ↗

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 24034f36bad7 and observed filesystem access and no hard-coded secrets. What it does: Automatically optimize a skill's SKILL.md by running test cases, scoring results, and iteratively improving instructions

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
CoCopilotAIGoogle AI Mode
Cite

Cite this page

ModelsAtlas. “Optimize Skill (ghbalf/freecad-ai)”. Retrieved 19 Oct 2026. https://modelsatlas.com/skills/ghbalf/optimize-skill

Trust audit

Audit 0.4.1 · source read 19 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high1 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemUndeclared1 observation, not in its own description
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeWARN1
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (1)

MEDIUMFilesystem / pathfs.destructive · handler.py:79
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
os.remove(history_path)
Why
No further detail recorded for this rule.
Fix
—

Audit 0.4.1 · source sha 24034f36bad7 · 19 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherghbalf GitHub userOwner of the repository this skill is read from
  • Source folderghbalf/freecad-ai/skills/optimize-skillThe exact folder we audited
  • LicenceLGPL-2.1As the repository states it
  • Commit pinned for this verdict24034f36bad7A new audit runs when the source changes
  • Repository statusNot archivedLast push 2 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

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

---
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

Excerpt, first 862 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 24034f3

Download folder ↗
git clone https://github.com/ghbalf/freecad-ai
git -C freecad-ai checkout 24034f36bad7

The author documents no install command, so this uses the repository directly. Our verdict covers commit 24034f36bad7 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 24034f36bad7

Similar skills

Create Validation✓SAFE

ghbalf/freecad-ai

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

★ 577Grade B
Enclosure✓SAFE

ghbalf/freecad-ai

Generate a parametric electronics enclosure with a base and lid.

★ 577Grade B
Fastener Hole✓SAFE

ghbalf/freecad-ai

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

★ 577Grade B
Gear✓SAFE

ghbalf/freecad-ai

Create an involute spur gear using FreeCAD's Part module.

★ 577Grade B
Lattice✓SAFE

ghbalf/freecad-ai

Generate a 3D lattice or infill pattern inside a bounding region. Useful for lightweight structural parts.

★ 577Grade B
Sketch From Image✓SAFE

ghbalf/freecad-ai

Extract 2D geometry from an attached image and create a FreeCAD sketch from it.

★ 577Grade B

Questions about Optimize Skill

What does the Optimize Skill skill do?
AI-powered assistant workbench for FreeCAD — generate 3D models from natural language
Is Optimize Skill safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Optimize Skill access on my machine?
The audit observed that it reads or writes files. At least one of those is not mentioned in its own description, which is itself a finding. Secrets in the source: none found.
How current is this page?
The grade is for one exact copy of the source (24034f36bad7), read on 2026-10-19. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.