Content
65%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 dense, highly actionable reference whose tool sequences and parameter quirks are excellent, but it is hampered by cross-section redundancy, a missing pre-deletion validation step for destructive/batch operations, and an all-inline structure with no reference files. Tightening the duplicate pitfalls, adding a verify-before-delete checkpoint, and splitting the quick-reference table into a references file would raise most dimensions.
Suggestions
Add an explicit validation checkpoint before CLICKUP_DELETE_TASK and before bulk/batch operations (e.g., GET_TASK to confirm the target task, confirm with the user, and re-check created-task IDs on retry) to satisfy the destructive/batch feedback-loop requirement.
Deduplicate the pitfalls: the Known Pitfalls section restates case-sensitive status, millisecond dates, notify_all, and folderless lists already covered per-workflow — keep each pitfall in one place and reference it.
Move the 20-row Quick Reference table and per-tool parameter details into a references/ file (e.g. references/tool-reference.md) linked one level deep from SKILL.md, and replace the circular "When to Use" section with real trigger guidance or delete it.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body mostly assumes Claude's competence (no concept explanations, dense parameter tables), but it has noticeable redundancy: pitfalls repeated across sections (case-sensitive status stated three times, millisecond timestamps three times, notify_all and folderless-lists rules twice), overlapping Prerequisites/Setup sections, and a pure-filler "When to Use" section ("applicable to execute the workflow or actions described in the overview"). That is more than minor trimmable padding, so it sits at 3 rather than 4. | 3 / 5 |
Actionability | This is an instruction-only MCP-orchestration skill and the guidance is fully executable: exact tool slugs, ordered sequences tagged [Prerequisite]/[Required]/[Optional], parameter names with types and enums (priority 1-4, page starting at 0, 25/100 page sizes), and precise quirks like URL-encoding statuses ("to%20do") and passing " " to clear a description. The five workflows cover the common cases with specific, directly usable guidance. | 5 / 5 |
Workflow Clarity | Each workflow has a clear numbered tool sequence with role tags and some checkpoints (verify task via GET_TASK before commenting, confirm connection ACTIVE before running), but the skill includes destructive and batch operations — CLICKUP_DELETE_TASK and bulk creation with 429/retry-duplicate risks — without any validation step before deletion (e.g., GET_TASK to confirm the right task or user confirmation). Per the rubric guideline this caps workflow clarity at 3. | 3 / 5 |
Progressive Disclosure | There are no bundle files (no references/, scripts/, or assets/), so all ~230 lines live inline in SKILL.md with good section headers, but content that would benefit from being split out — the 20-row quick-reference table, the per-tool parameter lists, and the known-pitfalls catalog — is inlined rather than placed in one-level-deep reference files. That matches anchor 3 (structure present, content that should be separate is inline), not the well-split anchor 4. | 3 / 5 |
Total | 14 / 20 Passed |