Content
63%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 is highly actionable and clearly sequenced — command syntax, path conventions, tier logic, and the deliverable template are all concrete. Its main weakness is structure: the body is a monolith dominated by an inlined proposal template containing marketing boilerplate and time-sensitive claims, with no reference files to split it out and no final placeholder-validation step.
Suggestions
Move the ~240-line proposal template to a references/ file (e.g. references/proposal-template.md) and keep only the placeholder-filling rules and tier logic in SKILL.md, which would improve both conciseness and progressive_disclosure.
Add an explicit validation step to the workflow: after generating the document, verify no '[PLACEHOLDER]' strings remain before saving and reporting the proposal as client-ready.
Either add concrete PDF generation instructions (the description promises PDF output) or remove the PDF claim from the description and rely solely on the '/geo report-pdf' handoff.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The command, workflow, and output sections are lean, but ~240 of ~330 lines are an inlined sales template whose generic marketing prose ('First-mover advantage is real') and time-sensitive claims ('+527% YoY', '25-40% of organic discovery by end of 2026') read as padding Claude could draft unaided. Mostly efficient but with unnecessary sections that could be tightened — anchor 3, not 2 because the pricing, package inclusions, and score-tier mappings are genuine data Claude does not know. | 3 / 5 |
Actionability | Concrete throughout: exact command syntax with three worked examples, file paths for audit input and proposal output, a deterministic score-to-tier mapping, a fill-in template, and the exact confirmation output. Not 5 because the frontmatter promises PDF output while the body contains no PDF generation steps (only a pointer to '/geo report-pdf'), and 'update prospect record' lacks field-level specifics. | 4 / 5 |
Workflow Clarity | Steps 1-3 are clearly sequenced and include an error-recovery path (missing audit → suggest '/geo quick' first). Not 5 because there is no validation checkpoint that all [PLACEHOLDERS] were actually replaced before declaring the document client-ready, leaving a silent placeholder-leakage risk in the final deliverable. | 4 / 5 |
Progressive Disclosure | Sections are well-organized and navigable (Command, Workflow, Template, Output), but the ~240-line proposal template is precisely the content that belongs in a one-level-deep reference file, and no bundle files or references exist at all. Some structure with content that should be separate inlined — anchor 3 rather than 2 because the section organization itself is clear. | 3 / 5 |
Total | 14 / 20 Passed |