Content
65%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A highly actionable, well-structured ClickUp automation skill with concrete tool sequences and parameter detail, held back by duplicated pitfalls, missing feedback loops for batch/destructive ops, and a monolithic structure with no progressive file disclosure.
Suggestions
De-duplicate pitfalls: keep each gotcha in one place (either the per-workflow 'Pitfalls' block or 'Known Pitfalls', not both) and cross-reference instead.
Add an explicit validation/feedback loop for batch and destructive operations, e.g. 'After bulk CREATE_TASK, verify via CLICKUP_GET_TASKS that the count matches and no duplicates appeared; retry only missing items' and 'Confirm task_id with CLICKUP_GET_TASK before CLICKUP_DELETE_TASK.'
Split detailed parameter reference into a referenced file (e.g. REFERENCE.md) so SKILL.md stays a concise overview pointing one level deep, improving progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient and free of basic-concept padding, but pitfalls are duplicated across per-workflow 'Pitfalls' blocks and the 'Known Pitfalls' section (e.g. case-sensitive status, ms timestamps, team_id meaning Workspace ID), so it could be tightened; not the score-3 'every token earns its place'. | 2 / 3 |
Actionability | It provides concrete tool slugs, exact typed parameters ('due_date: Unix timestamp in milliseconds', 'priority: 1 (Urgent), 2 (High)...'), and actionable quirks (URL-encoding spaces), matching the score-3 'fully executable ... copy-paste ready' anchor. | 3 / 3 |
Workflow Clarity | Tool sequences are clearly numbered with [Prerequisite]/[Required]/[Optional] tags and the setup has an explicit ACTIVE-status validation checkpoint, but batch (bulk task creation) and destructive (DELETE_TASK) operations lack an explicit validate→fix→retry feedback loop, which per the rubric caps workflow_clarity at 2. | 2 / 3 |
Progressive Disclosure | Sections are well-organized and the Quick Reference table aids navigation, but this is a ~230-line monolithic file with no bundle files and substantial inline reference content (parameter lists, pitfalls) that could be split out, matching the score-2 'content that should be separate is inline' rather than the score-3 overview-with-one-level-references. | 2 / 3 |
Total | 9 / 12 Passed |