Content
86%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.
An efficient, specialist recipe that gives concrete Terraform-framework guidance with a verification section and clear sectioning. The only meaningful gap is the absence of a copy-paste code example showing the modifier in a schema definition.
Suggestions
Add a short Go code block showing UseNonNullStateForUnknown() applied to a nested Optional+Computed id attribute so the fix is copy-paste ready, lifting actionability toward 5.
Make the workflow an explicit numbered sequence (detect → grep all levels → swap modifier → add the unit test with non-null State) so the validation loop reads as a checklist.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and assumes framework competence — it never explains what Optional+Computed or UseStateForUnknown mean, and every section (Trigger, Fix, Do not, Unit-testing, Why) earns its tokens with non-obvious edge-case knowledge. | 5 / 5 |
Actionability | Concrete, executable guidance is given via exact API calls (UseNonNullStateForUnknown(), UseStateForUnknown()), a grep recipe, and a specific test setup (tfsdk.State with non-null Raw); it stops short of 5 only because there is no copy-paste code block showing the modifier wired into a schema. | 4 / 5 |
Workflow Clarity | A clear sequence is present (identify the null→known failure, swap the modifier at every list level, grep for sibling cases, fix together) with a verification checkpoint in the Unit-testing section; it is not a numbered validate→fix→retry loop, which keeps it just below 5. | 4 / 5 |
Progressive Disclosure | Under 50 lines with no need for external references (no bundle files exist and none are referenced), and it is organized into well-labeled sections, meeting the simple-skill exception for a top score. | 5 / 5 |
Total | 18 / 20 Passed |