Content
57%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.
A well-structured, highly actionable MCP tool reference with exact tool slugs, parameter schemas, and per-workflow pitfalls. It is held back by significant internal duplication, no post-action validation for destructive/batch operations, and a monolithic single-file layout with no progressive disclosure layering.
Suggestions
Add validation/feedback steps to destructive and batch workflows: verify a created item with WEBFLOW_GET_COLLECTION_ITEM, confirm publish outcome, and give error-recovery guidance (e.g. retry after the 1-publish-per-minute rate limit, handle 403 by checking OAuth scopes).
Deduplicate: the "Known Pitfalls" section and Quick Reference table largely repeat the per-workflow Pitfalls and tool sequences — keep one authoritative copy and remove the filler "When to Use" section.
Move the per-tool parameter details and Quick Reference table into a references/ file (e.g. TOOLS.md) linked from a concise overview to add progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense reference material with little concept explanation Claude already knows, but it is noticeably duplicated: the "Known Pitfalls" section restates pitfalls already given per-workflow (field slugs vs display names, publish-all-staged-changes, rate limit appear twice), the Quick Reference table repeats the tool sequences, and the closing "When to Use" section ("This skill is applicable to execute the workflow or actions described in the overview.") is pure filler. Not a 4 because this repetition is substantial rather than minor; not a 2 because there is no padded beginner-level explanation. | 3 / 5 |
Actionability | Concrete, executable guidance throughout: exact tool slugs (e.g. "WEBFLOW_CREATE_COLLECTION_ITEM"), exact parameter shapes ("field_data: Object with field slug keys (NOT display names); must include name and slug"), ID formats with regex ("^[0-9a-fA-F]{24}$"), field value types, and md5 computation rules. Not a 5 because there are no example tool invocations/payloads for the common cases (e.g. a sample create-item call), which would make it copy-paste ready. | 4 / 5 |
Workflow Clarity | The five workflows have clearly numbered tool sequences with prerequisites marked and a validated setup flow (confirm connection ACTIVE before proceeding), but destructive and batch operations (DELETE_COLLECTION_ITEM, PUBLISH_SITE deploying ALL staged changes, paginated iteration) lack post-action verification and error-recovery feedback loops — the only checkpoint is "always confirm with the user". Per the rubric guideline, missing validation/verification steps for destructive/batch operations caps workflow clarity at 3. | 3 / 5 |
Progressive Disclosure | The skill is a single ~230-line file with no references/ bundle; the structure is well-sectioned, but bulk per-tool parameter reference and the Quick Reference table are inlined in SKILL.md where a one-level-deep reference file would keep the overview lean — matching the anchor of inline content that could be separate. Not a 4 because there is no reference layering at all; not a 2 because sections, headers, and the table make it navigable rather than a wall of text. | 3 / 5 |
Total | 13 / 20 Passed |