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, information-dense reference with concrete tool sequences and genuinely useful pitfalls, weakened by internal duplication, no destructive-operation validation steps, and a monolithic single-file layout that inlines what should be split into reference files.
Suggestions
Add validation checkpoints for destructive and batch operations, e.g. fetch and display the task via CLICKUP_GET_TASK before CLICKUP_DELETE_TASK, and verify created task IDs after bulk creation.
Deduplicate the 'Known Pitfalls' section against per-workflow Pitfalls, keeping one canonical location and cross-referencing it.
Move the Quick Reference table and per-tool parameter details into a references/ file (e.g. reference/tools.md) and keep SKILL.md as an overview with one-level-deep links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and free of concept over-explanation, but pitfalls stated per workflow are repeated nearly verbatim in 'Known Pitfalls' (case-sensitive status, ms timestamps, team_id meaning), and the 20-row Quick Reference table re-lists parameters already tabulated — it could be tightened, matching anchor 3 rather than anchor 4's 'minor instances'. | 3 / 5 |
Actionability | Concrete tool slugs, typed parameter lists ('due_date: Unix timestamp in milliseconds', 'priority: 1 (Urgent)...4 (Low)') and specific quirks give mostly executable guidance, but no example tool-call payloads are shown, leaving minor gaps versus the copy-paste-ready anchor 5. | 4 / 5 |
Workflow Clarity | Sequences are clearly ordered with [Prerequisite]/[Required]/[Optional] markers and setup includes connection-status validation, but destructive and batch operations lack validation checkpoints — 'Permanently remove a task' (CLICKUP_DELETE_TASK) has no verify-before-delete step and bulk creation only mentions 'track created task IDs' — so the batch/destruction cap holds the score at 3. | 3 / 5 |
Progressive Disclosure | At ~230 lines with no bundle files, all per-tool API detail (full parameter tables and the Quick Reference) is inlined in SKILL.md; section structure is good, but content that belongs in separate reference files is inline, matching anchor 3. | 3 / 5 |
Total | 13 / 20 Passed |