Content
75%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 copy-paste CLI commands and an explicit connection-readiness feedback loop, and is well-structured into navigable sections. Its main weaknesses are moderate verbosity and redundancy (overlapping action-list sections, repeated best-practice guidance) and slightly inconsistent step numbering that keeps workflow clarity just below the top anchor.
Suggestions
Collapse the redundant "Searching for actions" and "Popular actions" sections into a single action-discovery section to remove duplicated `action list` examples.
Fix the step numbering: add a clear "1a" / "Step 1" label and define the "Step 2" the text references, so the sequence reads as an explicit ordered workflow.
Trim explanatory prose (e.g. "so you can focus on the integration logic rather than auth plumbing", "This is the fastest way to get a connection") that does not change what Claude executes.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient with useful code blocks, but includes padded prose ("so you can focus on the integration logic rather than auth plumbing", "This is the fastest way to get a connection...") and redundant sections ("Searching for actions" and "Popular actions" both demonstrate `action list`; Best practices repeats discover-before-build), matching the anchor for mostly efficient content that could be tightened. It is not a 4 because the redundancy and explanatory padding are more than minor, and not a 2 because the core is still command-focused and largely useful. | 3 / 5 |
Actionability | The body provides copy-paste ready, fully executable commands for every stage (install, login, connection ensure/get, action list, action run, request) plus a flags table and JSON-input examples, covering the common cases. It is not a 4 because the examples are concrete and complete rather than having meaningful gaps. | 5 / 5 |
Workflow Clarity | The install → authenticate → connect → poll-for-ready → search → run sequence is clear, with an explicit feedback loop (poll again after CLIENT_ACTION_REQUIRED until READY) and state-based branches. It is not a 5 because step numbering is inconsistent (a "1b" header with no "1a", and a dangling "skip to Step 2" reference with no clearly labeled Step 2 header), and not a 3 because validation checkpoints (state polling, error-field guidance) are largely present. | 4 / 5 |
Progressive Disclosure | No bundle files exist, and the single SKILL.md is organized into clearly headed sections (Overview, Working with Cludo, Authentication, Connecting, Searching, Running actions, Proxy, Best practices) with one-level structure. It is not a 5 because there is no external reference split for the larger detail blocks (state-machine breakdown, flags table) and the "Searching for actions"/"Popular actions" sections overlap, and not a 3 because the structure is genuinely navigable rather than merely present. | 4 / 5 |
Total | 16 / 20 Passed |