Content
42%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 skill has a genuinely executable core (a runnable script, concrete compile-check commands, parameter table, and output schema), but it is buried under generic template boilerplate and broken self-referential section pointers. The biggest concrete defect is an interface mismatch: the documented 'size'/'sections' parameters and the '--help' example do not match what scripts/main.py actually accepts.
Suggestions
Delete the three content-free cross-reference sections ('Key Features', 'Dependencies', 'Implementation Details' as written) — each is just a mislabeled 'See ## X above' pointer to a section that appears later in the file — and merge their one or two real facts into the sections they point to.
Make scripts/main.py accept the documented parameters (e.g., argparse with --size and --sections) so 'python scripts/main.py --help' works and the Input Parameters table matches reality; or change the docs to describe the demo-run behavior.
Trim the generic Risk Assessment, Security Checklist, Evaluation Criteria, and Lifecycle Status boilerplate (or move it to references/), and concretely define the 'fallback path' named in Workflow step 5 instead of leaving it abstract.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is noticeably padded: it repeats the already-weak description verbatim in 'When to Use', contains circular filler sections ('See `## Features` above', 'See `## Prerequisites` above', 'See `## Workflow` above' — each introducing a section with no content of its own), and carries generic template boilerplate (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria) that adds no poster-specific knowledge. Some sections (Input Parameters, Output Format, Quick Check) are lean, so it does not reach anchor 1's 'severely verbose' level. | 2 / 5 |
Actionability | There is real executable material — 'python -m py_compile scripts/main.py', 'python scripts/main.py --help', 'python scripts/main.py' (the script exists and runs) plus a concrete Input Parameters table and Output Format spec. But the guidance is incomplete: the documented interface (required 'size' and 'sections' parameters) does not match the script, which accepts no CLI arguments and runs a hard-coded demo; 'python scripts/main.py --help' will not print help since there is no argparse; and the run plan hedges with 'Edit the in-file CONFIG block or documented parameters if the script uses fixed settings'. This lands at anchor 3: some concrete guidance but with missing key details. | 3 / 5 |
Workflow Clarity | The 'Workflow' section gives a sequenced 5-step process with an early scope-validation checkpoint ('stop early if the task would require unsupported assumptions') and an Error Handling section, which is more than anchor 2's bare sequence. However, checkpoints remain largely implicit and step 5's 'switch to the fallback path' references a fallback that is never concretely defined anywhere in the skill — a real gap that keeps it below anchor 4. | 3 / 5 |
Progressive Disclosure | The bundle structure is real and one level deep: 'references/guidelines.md' and 'scripts/main.py' both exist and are pointed to from the body, avoiding nested-reference failure. But navigation is undermined by mislabeled forward pointers ('Key Features' says 'See `## Features` above' though Features appears later; same for Dependencies→Prerequisites and Implementation Details→Workflow), references/guidelines.md is a 5-line skeleton, and large swaths of template boilerplate sit inline in SKILL.md that belong in reference files or nowhere. | 3 / 5 |
Total | 11 / 20 Passed |