AB expo-mobile-dev
Opinionated, step-by-step workflow for starting a new React Native + Expo mobile app — gathers the app's name, purpose, and target region (China mainland vs international), scaffolds with `pnpm create expo-app --template default@sdk-55`, installs a hand-picked stack (better-auth, sonner-native, TanStack Query, TanStack Form, Zustand), and installs the official Expo + TanStack AI development skills so future work has expert guidance loaded. Use whenever the user mentions building, scaffolding, starting, or bootstrapping a React Native, Expo, iOS, Android, or "mobile app" — even casually ("我想做一个 app", "make me an app", "start a mobile project"). Also use when the user references files like `app.json`, `app.config.ts`, `eas.json`, the `app/` router directory, or Expo-specific imports. Default to this skill for mobile work unless the user explicitly asks for native Swift, Kotlin, or Flutter.
As a process B 67/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
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: 9. 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 67/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 40 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4704 tokens
- 85Steps. 42 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 7 branches, has a failure section
- 100Consistency. Name and required fields are in place
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)
- +3Description length 900: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 21 headings
- +3Step-by-step instructions: 42 items
- +4Has examples (13 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.