Content
82%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.
A strong, dense reference skill: executable examples for every common pattern, sharp gotchas (silent no-route, two-pass loop, cache both-parts), and clear decision guidance. The main costs are the duplicated 'house rules' tail section, the absence of an explicit verify-locally-then-deploy workflow, and a monolithic structure that inlines reference-grade detail.
Suggestions
Remove or de-duplicate the trailing 'Netlify house rules' section — all five rules are already stated (mostly verbatim) in the main body, so the last ~30 lines are pure token cost.
Add an explicit deploy sequence with a checkpoint, e.g.: write function with scoped `path` → verify locally with `netlify dev` (and `--geo=mock` for geo logic) → confirm the route actually executes → deploy → check logs under Cloud compute > Edge functions.
Move the long-tail reference material (full `Context` object listing, Limits, Feature limitations, runtime API inventory) into a `references/` file (e.g. `references/context-and-limits.md`) and link to it from SKILL.md, keeping the body as a lean overview; also point 'check the framework adapter/reference first' at a concrete file or URL.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and imperative with no explanations of concepts Claude already knows, but the trailing 'Netlify house rules' section (~30 lines) restates five guardrails already covered earlier (path scoping, silent no-route, two-pass loop, edge-vs-serverless, cache 'both parts'). That is more than a trivial trim candidate but less than pervasive padding, so it sits between the 3 and 5 anchors — 'minor instances of over-explanation that could be trimmed' (4) is the closest fit. | 4 / 5 |
Actionability | Copy-paste-ready code for redirect, rewrite, middleware transform, request-body re-read, caching, and SSR (.tsx), plus concrete TOML config and CLI commands ('netlify dev', '--geo=mock', '--edge-inspect'). Specific examples cover the common cases, matching the 5 anchor. | 5 / 5 |
Workflow Clarity | Decision points are clear (edge vs serverless, onError modes, cache 'both parts or neither') with a troubleshooting feedback loop ('my edge function does nothing' → check the route first) and local dev/deploy/monitor commands. It falls short of 5 because there is no explicit end-to-end sequence with checkpoints (e.g., verify the function runs under 'netlify dev' before deploying); it exceeds 3 because sequence and checkpoints are mostly present. | 4 / 5 |
Progressive Disclosure | Well-organized single-file skill with clear section headers and no buried or nested references, but ~235 lines include API-reference-like material (full 'Context' listing, Limits, Feature limitations) inlined that could live in a reference file, and 'check the framework adapter/reference first' gestures at a reference that does not exist in the bundle. Good structure with minor organization gaps matches the 4 anchor; it is above 3 (nothing is buried or disorganized) and below 5 (content is not split despite size). | 4 / 5 |
Total | 17 / 20 Passed |