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.
The body is highly actionable — exact tool slugs, typed params, and a lookup table make the MCP workflows concrete — and well sequenced. Weaknesses are duplicated pitfall content, missing validation checkpoints around destructive/batch operations, and a monolithic single-file structure with no external references.
Suggestions
Add explicit validation/feedback checkpoints for destructive and batch operations, e.g. verify the task via `CLICKUP_GET_TASK` and confirm with the user before `CLICKUP_DELETE_TASK`, and confirm the target count/list before bulk task creation.
De-duplicate the pitfalls: keep either the per-workflow "Pitfalls" blocks or the consolidated "Known Pitfalls" section, not both, to remove the repeated ms-timestamp / case-sensitive-status / hierarchy content.
Move the detailed per-tool parameter reference and the Quick Reference table into a separate reference file (e.g. `references/tools.md`) and link to it from SKILL.md so the main file stays an overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is mostly efficient and reference-style (no over-explaining of what ClickUp is), but pitfalls are stated twice — once in each workflow's "Pitfalls" block and again verbatim in the consolidated "Known Pitfalls" section (ms-timestamp dates, case-sensitive status, hierarchy rules). That duplicated material is more than minor trimming, fitting anchor 3 rather than 4. | 3 / 5 |
Actionability | Provides numbered tool sequences with exact slugs (e.g. `CLICKUP_CREATE_TASK`), typed required/optional parameters, enum values (priority 1-4), and a Quick Reference table mapping tasks to tool slugs and key params — concrete, executable MCP guidance with only minor gaps (no example call payload). It sits at anchor 4, short of 5's fully copy-paste-ready examples covering common cases. | 4 / 5 |
Workflow Clarity | Workflows are clearly sequenced with [Prerequisite]/[Required]/[Optional] tags and the Setup section validates connection status (ACTIVE), but destructive operations (`CLICKUP_DELETE_TASK`) and batch operations (bulk task creation, 429 handling) lack explicit validation/feedback-loop checkpoints. The rubric caps workflow_clarity at 3 for destructive/batch skills missing validation, which overrides the otherwise strong sequencing. | 3 / 5 |
Progressive Disclosure | Headers and the Quick Reference table give decent navigation, but ~230 lines of detailed workflows plus a consolidated pitfall reference plus a lookup table are all inlined into the single SKILL.md with zero references out (no bundle files exist). Reference material that belongs in a separate file is inlined, matching anchor 3 rather than 4's "most content appropriately placed". | 3 / 5 |
Total | 13 / 20 Passed |