Content
87%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The content is lean, fully actionable, and well-organized for a simple CLI skill, but it omits validation/verification steps for its destructive resize and repair operations, capping workflow clarity at 3.
Suggestions
Add a verification step after resize/repair, e.g. run 'cli-anything-3mf info -o output.3mf' to confirm the modified mesh is watertight and the bounding box is sane.
Note that the repair command should be run after resize to clean up any degenerate faces introduced by radial vertex scaling, making the safe sequence explicit.
Show an example of using '--json' output to programmatically verify hole diameter after a resize before proceeding.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence — no preamble explaining 3MF or mesh concepts, and every section (installation, commands, JSON output, key features) earns its tokens, matching the score-5 anchor. | 5 / 5 |
Actionability | Commands are fully executable and copy-paste ready with real flags and arguments (e.g. 'cli-anything-3mf resize <file.3mf> --hole 0 --hole 1 --diameter 4.2 -o output.3mf'), covering all common cases, matching the score-5 anchor. | 5 / 5 |
Workflow Clarity | Commands are clear and executable but the destructive resize/repair operations have no validation or verification step, and per the rubric cap a destructive skill without validation cannot score above 3 even though the single actions are unambiguous. | 3 / 5 |
Progressive Disclosure | The skill is under 50 lines with no bundle files and no need for external references, yet is well-organized into clear sections, qualifying for the score-5 simple-skill exception. | 5 / 5 |
Total | 18 / 20 Passed |