Content
52%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's actual instructions and reference structure are sound and actionable, but the body is buried under a large volume of generic templated boilerplate that adds little skill-specific value and inflates the token budget. Trimming the boilerplate and adding a concrete Mermaid output example would meaningfully improve it.
Suggestions
Remove the generic boilerplate sections (When to Use, Key Features, Dependencies, Example Usage, Implementation Details, Required Inputs, Recommended Workflow, Output Contract, Failure Handling, Quick Validation) or collapse them into a few lines; 'Key Features' currently restates the description verbatim.
Add a short concrete example showing the expected Mermaid `flowchart TD` output for a small sample input so the deliverable shape is unambiguous.
Tighten the Validation step with a specific renderability check (e.g., confirm each node id is defined and no unsupported syntax is used) instead of the soft 'ensure it is renderable' guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is padded with roughly ten generic boilerplate sections (When to Use, Key Features, Dependencies, Example Usage, Implementation Details, Required Inputs, Recommended Workflow, Output Contract, Validation and Safety Rules, Failure Handling, Quick Validation), and 'Key Features' repeats the description verbatim, fitting the 'noticeably verbose; several unnecessary padded sections' anchor rather than the mostly-efficient anchor 3. | 2 / 5 |
Actionability | The Instructions section gives concrete guidance (identify Background/Scientific Question/Objectives/Research Content/Methodology; build a `flowchart TD`; output only the code block), but the detailed extraction rules are deferred to the reference and no example Mermaid output is shown, leaving it at 'some concrete guidance but incomplete' rather than mostly-executable anchor 4. | 3 / 5 |
Workflow Clarity | A clear three-step sequence (Analyze Input → Generate Mermaid Code → Validation) is present with an explicit validation checkpoint ('Ensure the code is syntactically correct and renderable'), and since this is not a destructive or batch operation no cap applies; the validation check is somewhat soft, keeping it below the explicit-feedback-loop anchor 5. | 4 / 5 |
Progressive Disclosure | Detailed extraction rules are appropriately split into a single one-level-deep reference clearly signaled via '## References' -> references/prompt_guidelines.md, but SKILL.md itself is a padded overview rather than a lean one, so it sits at 'good structure; minor organization gaps' rather than the lean-overview anchor 5. | 4 / 5 |
Total | 13 / 20 Passed |