Content
87%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is concise, highly actionable, and well-structured with executable commands and well-sourced common-mistake guidance. Its one gap is workflow clarity: the dev-watch/apply loop describes preconditions but lacks explicit validation checkpoints and a retry loop.
Suggestions
Add an explicit validate→fix→retry loop for the sync/apply workflow, e.g. after 'add-on dev' or 'add', check the target app picked up changes and re-run compile if metadata errors appear.
Insert a numbered sequence for the full authoring loop (init → compile → dev → edit → re-compile → apply) with an explicit checkpoint between compile and apply, rather than listing patterns as isolated commands.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean — tight code blocks, one-line explanations, and source references — and avoids explaining concepts Claude already knows; every section earns its tokens. | 3 / 3 |
Actionability | Provides fully executable commands with flags and copy-paste-ready Wrong/Correct pairs (e.g. 'npx @tanstack/cli create my-sandbox --dev-watch ../path/to/framework-dir'), matching the 'fully executable, specific examples' anchor. | 3 / 3 |
Workflow Clarity | Steps and preconditions are present (setup, dev loop, re-run compile before apply), but the sync/apply workflow lacks explicit validation checkpoints or a validate→fix→retry feedback loop; validation is framed implicitly as 'fails before...' preconditions. | 2 / 3 |
Progressive Disclosure | Content is well-organized under clear sections (Setup, Core Patterns, Common Mistakes) with a single clearly-signaled one-level cross-reference ('See also: add-addons-existing-app/SKILL.md § Common Mistakes'); no bundle files exist to require deeper splitting. | 3 / 3 |
Total | 11 / 12 Passed |