AD flutter-master
Comprehensive Flutter & Dart mobile development skill — use for ANY Flutter task, not just when explicitly asked for "best practices" or an "audit". Trigger whenever the user mentions Flutter, Dart, pubspec.yaml, widgets, BLoC/Riverpod/Provider/GetX, .dart files, or mobile app architecture, or asks to build, review, refactor, debug, optimize, or ship a Flutter app. Especially trigger for auditing an existing project (code quality, architecture, performance, security, dependency health), setting up a new project correctly, choosing/reviewing state management, performance or build-size problems, pre-release checks (obfuscation, signing, store readiness), and testing strategy (unit/widget/integration/golden). Covers Material 3, null safety, effective Dart, clean architecture, and current Flutter ecosystem conventions. Use proactively even for small requests — a "quick fix" is still a chance to catch anti-patterns.
Comprehensive Flutter & Dart mobile development skill — use for ANY Flutter task, not just when explicitly asked for "best practices" or an "audit".
As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
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: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 48, 84): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 49/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 85Steps. 17 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2216 tokens
- 100Progress reporting. Reports progress
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 924: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Structure: 12 headings
- +3Step-by-step instructions: 17 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (9 of 9)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.