Content
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A well-structured, actionable research workflow with clear sequencing and concrete examples, weakened by redundancy with the frontmatter intent and by references to bundle files that do not exist. Tightening the prose and providing the referenced template/sample files would raise the score.
Suggestions
Remove the verbatim repeat of the frontmatter intent in the Purpose section, or replace it with skill-specific framing that adds new information.
Provide the referenced bundle files (template.md and examples/sample.md) and move the inline fill-in templates into template.md so the SKILL.md body stays a lean overview.
Collapse the Key Concepts "Core Components" list, which overlaps the Application steps, to reduce token cost without losing guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body restates the frontmatter intent verbatim in the Purpose section and carries lengthy placeholder template blocks plus overlapping Key Concepts/Application sections, so it is mostly efficient but could be tightened rather than fully lean. | 2 / 3 |
Actionability | The nine steps each pair a concrete fill-in template with worked Stripe examples, explicit "Sources to check" lists, and quality checks, giving actionable guidance appropriate to an instruction-only skill. | 3 / 3 |
Workflow Clarity | Steps 1–9 are clearly numbered and sequenced with quality checks (Recent/Substantive/Attributed) and a synthesis step that surfaces remaining questions, satisfying the clear-sequence-with-checkpoints anchor. | 3 / 3 |
Progressive Disclosure | No bundle directories exist, yet the body references template.md and examples/sample.md that are absent while the full template content stays inline, so structure is present but the overview/detail split is not cleanly realized. | 2 / 3 |
Total | 10 / 12 Passed |