Content
53%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 skill has a solid Quick Start with executable pytest patterns and a well-formatted resource index, but four filler/boilerplate sections pad the token budget, the testing workflow is never explicitly sequenced, and all progressive-disclosure references point to files that do not exist in the bundle, leaving mocking and replay guidance unavailable. Tightening the body and shipping (or inlining) the referenced resources would address the main weaknesses.
Suggestions
Create the four referenced resource files (resources/unit-testing.md, resources/integration-testing.md, resources/replay-testing.md, resources/local-setup.md) or inline their key content — currently every progressive-disclosure reference is dangling, so the promised mocking strategies, replay patterns, and setup guidance are unreachable.
Add an explicitly ordered testing workflow with validation checkpoints (e.g., 1. write test with time-skipping fixture → 2. run and assert → 3. mock activities for integration cases → 4. replay production histories before deploy) instead of distributing the approach across Philosophy, Quick Start, and Coverage sections.
Trim the tautological 'Do not use this skill when' bullets and the generic 'Instructions' boilerplate, and state the ≥80% coverage target and time-skipping benefit once instead of repeating them across three sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient (Testing Philosophy, Quick Start, resource listings are tight), but it includes unnecessary padding: the tautological 'Do not use this skill when' bullets ('The task is unrelated to temporal python testing strategies'), generic boilerplate Instructions ('Clarify goals, constraints, and required inputs'), and repetition of the ≥80% coverage target across three sections and the time-skipping benefit across two. | 3 / 5 |
Actionability | The Quick Start provides structurally complete, executable pytest code (WorkflowEnvironment.start_time_skipping fixture, Worker context, execute_workflow with assert; ActivityEnvironment example), which meets 'mostly executable guidance with minor gaps'. It falls short of 5 because of placeholders (YourWorkflow, args, expected), no pytest-asyncio configuration shown, and mocking/error-injection guidance being entirely deferred to resource files. | 4 / 5 |
Workflow Clarity | A rough approach is implied (Testing Philosophy list plus Quick Start code) but the testing workflow (write test → run with time-skipping → mock activities → replay before deploy) is distributed across sections rather than explicitly sequenced, and validation checkpoints are implicit in asserts only. Not 2 because structure and a rough sequence are present; not 4 because no explicit checkpoints or ordered steps are given. | 3 / 5 |
Progressive Disclosure | The body references 'resources/unit-testing.md', 'resources/integration-testing.md', 'resources/replay-testing.md', and 'resources/local-setup.md', but none of these files exist in the bundle (no resources/ directory), so every reference is dangling and the promised detail is unreachable. The per-resource signaling format (File/When to load/Contains) is good, but scored against the actual bundle structure the navigation is broken, which fits 'minimal structure / references buried' better than the clearly-signaled anchors at 4-5. | 2 / 5 |
Total | 12 / 20 Passed |