Content
60%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, actionable workflow and well-structured one-level-deep references, but a large fraction of the body is generic boilerplate (templated 'When to Use', 'Key Features', 'Implementation Details', a leaked example path) that pads the token budget without adding skill-specific value.
Suggestions
Remove or radically trim the boilerplate 'When to Use', 'Key Features', and 'Implementation Details' sections that restate the description and generic process language; keep only skill-specific guidance.
Fix the broken 'When to Use' bullet ('you need assists researchers in generating prospero registration content...') and drop the generic bullets about date_utils.py being 'the most direct path'.
Replace the leaked dated path in 'Example Usage' ('20260316/scientific-skills/Protocol Design/...') with a clean, current invocation example.
Embed an explicit input-validation checkpoint at the start of the Workflow (validate title/protocol present and in scope before proceeding) rather than relegating it to a separate section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Several sections are padded boilerplate that add little: 'When to Use' restates the description (one bullet even contains a grammar error, 'you need assists'), 'Key Features' and 'Implementation Details' restate generic process language, and 'Example Usage' leaks a dated path ('20260316/scientific-skills/...'). This matches anchor 2 (noticeably verbose; several unnecessary padded sections) rather than 3 because the filler is substantial relative to the genuinely useful Workflow/Quality Rules content. | 2 / 5 |
Actionability | Concrete executable commands are present ('python scripts/date_utils.py', 'python -m py_compile scripts/date_utils.py') and the workflow points to specific named prompt templates in references/prompt_templates.md (Steps 3.1/3.2/3.3). It is below 5 because the core generation work is delegated to the reference rather than given inline. | 4 / 5 |
Workflow Clarity | The Workflow is a clear numbered sequence (Analyze Input -> Calculate Timeline -> Generate Content with sub-steps 3.1-3.3) and an Input Validation scope-gate is documented. It is not 5 because validation is a separate section rather than an explicit validate-then-proceed checkpoint embedded in the workflow, and not 3 because the sequence and scope gate are clearly present. | 4 / 5 |
Progressive Disclosure | The body acts as an overview and correctly delegates the bulk of detail one level deep to references/prompt_templates.md and scripts/date_utils.py, both real files that are clearly signaled. It is below 5 because the body itself is cluttered with boilerplate sections that slightly obscure navigation. | 4 / 5 |
Total | 14 / 20 Passed |