Content
71%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 with concrete, copy-paste-ready CLI commands and a clear connection workflow with state-checkpoint feedback loops. Its main weaknesses are some unnecessary background explanation up front and a monolithic structure with no progressive disclosure into separate reference files.
Suggestions
Trim the opening paragraph that explains what Clockify is; Claude already knows the product, so lead directly with the integration workflow.
Move the 20-row Popular actions table and the detailed connection state-machine handling into a separate reference file (e.g. ACTIONS.md) and link to it from SKILL.md so the main file stays an overview.
Add a short verification/error-handling note after the `membrane action run` example (e.g. check the `output` field and handle non-READY connection states) to close the workflow-clarity validation gap.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient with concrete commands, but the opening paragraph explaining what Clockify is ("Clockify is a time tracking tool used by teams and individuals...") and mildly promotional Membrane phrasing ("so you can focus on the integration logic rather than auth plumbing") are unnecessary explanations Claude does not need, fitting the mostly-efficient-but-could-be-tightened anchor. | 3 / 5 |
Actionability | It provides copy-paste-ready executable commands for every phase (install, login, connection ensure, action list, action run, request) plus a 20-row table mapping action names to keys and a full table of proxy flags, fully covering the common cases per the top anchor. | 5 / 5 |
Workflow Clarity | The connect-and-poll workflow is clearly sequenced with explicit state checkpoints and a feedback loop (poll state, handle CLIENT_ACTION_REQUIRED, re-poll), but the action-running phase lacks a verification or error-handling step after execution, leaving a minor validation gap below the 5 anchor. | 4 / 5 |
Progressive Disclosure | The file is well-organized with clear section headers, but it is a monolithic ~165-line SKILL.md with no external reference files; detailed reference material such as the 20-row actions table and the connection state machine is inlined rather than split into one-level-deep referenced files, matching the anchor where content that should be separate is inline. | 3 / 5 |
Total | 15 / 20 Passed |