Content
31%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 clear two-step workflow skeleton with concrete quality rules, but it is unrunnable as packaged because the referenced prompt templates are missing, and roughly half of the body is generic template boilerplate that adds no value. It needs the actual reference files shipped and the filler sections removed.
Suggestions
Ship the referenced references/prompt_templates.md file (or inline the actual subtitle and outline prompts) — the workflow is unexecutable without it.
Delete the generic filler sections (When to Use, Key Features, Example Usage, Implementation Details, Quick Validation) that restate the description or state that nothing is required; keep only the workflow, quality rules, output format, and failure guidance.
Consolidate the overlapping boilerplate sections (Required Inputs, Input Validation, Validation and Safety Rules, Output Contract) into one concise input/validation block to cut token cost.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Several sections are generic padded boilerplate: 'When to Use' ('Use this skill when the request matches its documented task boundary'), 'Key Features' repeating the frontmatter description verbatim, an 'Example Usage' block that is just a directory listing, 'Implementation Details' opening with 'See ## Workflow above', and a 'Quick Validation' section stating 'No local script validation step is required.' This matches anchor 2 ('Noticeably verbose; several unnecessary explanations or padded sections') — far more than the 'some unnecessary explanation' of anchor 3. | 2 / 5 |
Actionability | The workflow steps ('Use the Subtitle Generation Prompt (see references/prompt_templates.md)') point to the actual executable prompts, but that file — and the entire references/ directory — does not exist, so the concrete instructions are missing. The Quality Rules are specific ('exactly 6 subtitles', 'screening -> verification -> mechanism -> in vivo'), but the core executable guidance lives in a missing file, matching anchor 2 ('Minimal concrete guidance; high-level hints but missing the specific steps to execute') rather than anchor 3, which requires some concrete guidance that is present but incomplete. | 2 / 5 |
Workflow Clarity | The two-step sequence (generate 6 subtitles, then generate the outline from subject + subtitles) is clearly ordered with explicit inputs, and Quality Rules serve as checkpoints. However, the workflow's central dependency is a missing prompt-templates file, and the validation sections are filler ('No local script validation step is required'), so anchor 3 ('Steps listed but validation gaps') fits better than anchor 4's 'most checkpoints present'. | 3 / 5 |
Progressive Disclosure | The body's only reference, 'references/prompt_templates.md', points to a nonexistent file — no references/, scripts/, or assets/ directories exist in the bundle, so the skill is unrunnable as packaged. Combined with inlined generic boilerplate that should be trimmed rather than kept in SKILL.md, this matches anchor 2 ('Minimal structure; ... references are buried' / broken) rather than anchor 3, which requires a present, if imperfectly signaled, reference structure. | 2 / 5 |
Total | 9 / 20 Passed |