Content
67%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 content is a solid, command-rich integration guide with a clear connection workflow including polling and error-state handling, and well-organized sections. Its main weaknesses are mild prose padding in the intro/auth narrative and slightly loose step numbering rather than a fully numbered, validated sequence.
Suggestions
Trim explanatory prose such as the opening 'GTmetrix is a website performance analysis tool...' paragraph and 'so you can focus on the integration logic rather than auth plumbing' to improve token efficiency.
Fix the step numbering: label a 'Step 1' before '1b. Wait for the connection' and resolve the 'skip to Step 2' reference so the sequence is unambiguous.
Show a concrete GTmetrix-specific proxy or action example with a real endpoint/actionId instead of only generic placeholders.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient and command-heavy, but includes unnecessary prose such as the opening 'GTmetrix is a website performance analysis tool. It's used by web developers...' and padding like 'so you can focus on the integration logic rather than auth plumbing'. It is not 4 because several explanatory sentences could be trimmed without losing clarity, and not 2 because the bulk is concrete commands and a useful action table rather than extensively padded. | 3 / 5 |
Actionability | It provides numerous copy-paste-ready commands (npm install, membrane login, connection ensure, action list/run, request) with --json examples and a concrete popular-actions table with keys. It is not 5 because some examples use unexplained placeholders (CONNECTION_ID, actionId) and the proxy section is generic rather than showing a GTmetrix-specific endpoint call. | 4 / 5 |
Workflow Clarity | The connection setup is clearly sequenced with a polling feedback loop (ensure -> check state -> --wait poll -> handle CLIENT_ACTION_REQUIRED -> READY -> search/run actions) and error states (CONFIGURATION_ERROR, SETUP_FAILED). It is not 5 because step numbering is loose ('skip to Step 2' with no labeled Step 1, and a '1b' without a '1a'), and not 3 because explicit state-checking checkpoints are present. | 4 / 5 |
Progressive Disclosure | The single SKILL.md is well-organized with clearly labeled sections (Overview, Working with GTmetrix, Install, Authentication, Connecting, Searching, Popular actions, Running actions, Proxy, Best practices) and no nested references. It is not 5 because the body exceeds 50 lines and the large popular-actions table could arguably live in a separate reference file, and not 3 because structure and navigation are clearly signaled. | 4 / 5 |
Total | 15 / 20 Passed |