AD setup-unit-test
One-click initialization of an AI-driven unit testing environment for frontend projects (supports React/Vue/pure TypeScript/Next.js). Automatically detects project framework, installs Vitest + Testing Library + MSW, generates config files, and injects Claude Code custom commands for cross-project reuse. Trigger scenarios: (1) Need to initialize unit testing in a new or existing project. (2) User says "initialize unit tests", "configure test environment", or "setup unit test". (3) Need to enable /gen-unit-test and other AI test generation commands in the project. (4) Need a single command to set up test configurations across multiple tech stacks (React/Vue/Next.js/TS).
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 43/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 25 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1199 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 676: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.