Content
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is a tight, actionable guide with executable code throughout and well-signaled external references. Its main weakness is workflow clarity — sequences lack explicit validation checkpoints and feedback loops for the local-HTTP and CI/deploy flows.
Suggestions
Add an explicit validation step to the serverless-offline flow (e.g. poll http://localhost:3000/hello for a 200 before running HTTP tests) so the local-HTTP sequence has a checkpoint.
Add a verify gate to the CI/deploy section — run npx jest and assert it passes before 'serverless deploy --stage staging', with a retry-on-failure note for the staging smoke tests.
Insert a short 'Choosing an approach' decision note (direct handler test vs serverless-offline vs invoke local) to make the multi-path workflow sequencing explicit rather than implied by section order.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and code-forward — install commands, YAML config, TypeScript test snippets, and a dense anti-patterns table — with only minimal prose that serves tool selection/scoping rather than explaining concepts Claude already knows. It does not reach the verbosity needed to drop to 2. | 3 / 3 |
Actionability | It provides fully executable, copy-paste-ready bash (npm install, serverless invoke local, serverless offline), YAML configs, and complete TypeScript test examples, matching the 'fully executable code/commands; copy-paste ready' anchor. | 3 / 3 |
Workflow Clarity | Sections are sequenced (Install → serverless.yml → invoke local → offline → jest-plugin → direct handler → Running → CI), but there are no explicit validation checkpoints or verify-fix-retry feedback loops — e.g. confirming serverless offline is live before curling, or asserting CI test results before deploy — which caps this at 2. | 2 / 3 |
Progressive Disclosure | No bundle files exist, but the single SKILL.md is well-organized with a clear overview, a dedicated References section with clearly signaled one-level-deep links (npmjs/github/serverless docs) and named sibling skills, and easy header-based navigation; nothing requires splitting. | 3 / 3 |
Total | 11 / 12 Passed |