Content
28%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 body reads as a marketplace landing page rather than operational skill instructions: it is padded with marketing prose, an FAQ, and promo links, and provides no executable commands or sequenced workflow — especially damning since the tooling it describes is explicitly not included in the folder. Structure exists (headers, an example, limitations), which keeps it from the bottom of the scale.
Suggestions
Replace the 'Why use this?', 'Questions' FAQ, and promotional footer sections with concise operational guidance, and move the 'When to use' list out of the body since it duplicates the frontmatter description verbatim.
Add executable guidance — the actual command(s) to run validation, versioning, and packaging — or, since the scripts are not bundled, state plainly what Claude can do with only the files present and remove the simulated CLI transcript.
Present the publish workflow as an explicit numbered sequence (validate -> dry-run -> review proposed changes -> apply -> verify dist/ output) with the dry-run output framed as a validation checkpoint before any files are written or versions bumped.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Noticeably verbose for what it conveys: marketing prose ('transforms your raw AI skill folders into production-ready marketplace packages'), a 'Why use this?' section, a five-question FAQ that restates earlier content, and promotional footers ('More skills and info at nex-ai.be and slopsome.com', paid-catalog link). Not 1 because it does not lecture on concepts Claude already knows. | 2 / 5 |
Actionability | Minimal concrete guidance: no commands or code appear anywhere, only a simulated dry-run transcript and a passing 'Ready to apply? Use --apply.' — and the body states 'Scripts, extension source, and templates from the original package are not in this folder', so nothing shown is actually executable from this skill. Not 1 because the example transcript is a concrete high-level hint of intended usage. | 2 / 5 |
Workflow Clarity | The validate -> dry-run -> approve -> apply -> dist/ sequence is only implied via the 'Dry-run first' philosophy paragraph and the example; no steps are listed and no validation checkpoints are articulated for operations that write files and bump versions. Not 3 because steps are not actually enumerated, only hinted at. | 2 / 5 |
Progressive Disclosure | The body has section headers but references no bundle files (references/, scripts/, assets/ do not exist in this folder), and FAQ/marketing content that does not belong in a SKILL.md is inlined across ~80 lines. Not 4 because at this length with off-topic material and zero reference signaling, organization is only partial. | 3 / 5 |
Total | 9 / 20 Passed |