BB Flutter
Builds, debugs, and ships Flutter apps: widgets, layout constraints, state management, navigation, performance, and store releases. Use when writing Dart widgets or screens; when a RenderFlex overflows, a viewport is given unbounded height, or a RenderBox was not laid out; when setState is called during build or after dispose, or BuildContext is used across an async gap; when the UI janks, scrolling stutters, or images exhaust memory; when hot reload stops applying changes; when Provider, Riverpod, or Bloc rebuild too much or too little; when routing with Navigator or go_router, deep links, or back-button handling; when the keyboard covers a form field or validation misfires; when a platform channel throws MissingPluginException; when localizing strings or mirroring a layout for right-to-left; when widget, golden, or integration tests hang or fail in CI; or when a build works in debug but the release APK, IPA, or web bundle breaks. Not for React Native or native-only Swift and Kotlin work.
As a process B 69/100 · Nearly there — weak spots: inputs and preconditions, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 24. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 6291 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 69/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 12 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 65Failures and branches. 3 branches
- 70Execution cost. Instruction body is 6291 tokens
- 100Tools and files. No external tools needed
- 100Steps. 51 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
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
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 1004: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 51 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.