Use when about to claim work is complete, fixed, or passing - requires running Flutter verification commands and confirming output before making any success claims; evidence before assertions always
/plugin marketplace add vp-k/flutter-craft/plugin install vp-k-flutter-craft-plugins-flutter-craft@vp-k/flutter-craftThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Claiming work is complete without verification is dishonesty, not efficiency.
Core principle: Evidence before claims, always.
Violating the letter of this rule is violating the spirit of this rule.
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
If you haven't run the verification command in this message, you cannot claim it passes.
flutter analyze
Expected output:
Analyzing <project>...
No issues found!
If issues found:
Analyzing <project>...
info • ... • lib/path/file.dart:42:10 • ...
warning • ... • lib/path/file.dart:50:5 • ...
3 issues found. (1 warning, 2 hints)
# All tests
flutter test
# Specific feature tests
flutter test test/features/<feature>/
# Specific test file
flutter test test/features/<feature>/data/repositories/user_repository_test.dart
Expected output:
00:05 +12: All tests passed!
If tests fail:
00:03 +10 -2: Some tests failed.
# Android debug build
flutter build apk --debug
# iOS debug build (macOS only)
flutter build ios --debug --no-codesign
# Web build
flutter build web
Expected output:
✓ Built build/app/outputs/flutter-apk/app-debug.apk (XX.XMB)
dart format --set-exit-if-changed lib/
BEFORE claiming any status or expressing satisfaction:
1. IDENTIFY: What command proves this claim?
2. RUN: Execute the FULL command (fresh, complete)
3. READ: Full output, check exit code, count failures
4. VERIFY: Does output confirm the claim?
- If NO: State actual status with evidence
- If YES: State claim WITH evidence
5. ONLY THEN: Make the claim
Skip any step = lying, not verifying
| Claim | Requires | Not Sufficient |
|---|---|---|
| "Code is clean" | flutter analyze: No issues | "I wrote correct code" |
| "Tests pass" | flutter test: All passed | "Should pass", "Looks correct" |
| "Build succeeds" | flutter build: Built successfully | "Analyze passed" |
| "Feature complete" | All verification + requirements check | "Tests pass" |
| "Bug fixed" | Test original symptom + verify | "Code changed" |
| "Widget works" | Widget test or manual verification | "Code looks right" |
If you catch yourself thinking or saying:
STOP. Run the verification command.
Before claiming completion:
### Verification Results
**Static Analysis:**
```bash
$ flutter analyze
Analyzing flutter_app...
No issues found!
✅ Passed
Unit Tests:
$ flutter test test/features/<feature>/
00:05 +12: All tests passed!
✅ 12/12 passed
Build:
$ flutter build apk --debug
✓ Built build/app/outputs/flutter-apk/app-debug.apk
✅ Built successfully
Ready to claim completion.
## Key Patterns
**Static Analysis:**
✅ [Run flutter analyze] [See: No issues found!] "Analysis passes" ❌ "Code looks clean" / "I wrote it correctly"
**Tests:**
✅ [Run flutter test] [See: 34/34 pass] "All tests pass" ❌ "Should pass now" / "Tests look correct"
**Build:**
✅ [Run flutter build] [See: Built successfully] "Build passes" ❌ "Analyze passed" (analyze doesn't check build)
**Feature completion:**
✅ Re-read plan → Verify each requirement → Run all verifications → Report ❌ "Tests pass, feature complete"
## Rationalization Prevention
| Excuse | Reality |
|--------|---------|
| "Should work now" | RUN flutter analyze/test |
| "I'm confident" | Confidence ≠ evidence |
| "Just this once" | No exceptions |
| "Analyze passed" | Analyze ≠ build ≠ test |
| "Code looks right" | Verify independently |
| "I'm tired" | Exhaustion ≠ excuse |
| "It's simple code" | Simple code can still fail |
## Why This Matters
- **Trust:** If you claim "tests pass" without running them, trust is broken
- **Time:** False completion → redirect → rework wastes everyone's time
- **Quality:** Unverified code may crash in production
- **Integrity:** Honesty is a core value
## When To Apply
**ALWAYS before:**
- ANY variation of success/completion claims
- ANY expression of satisfaction ("Done!", "Fixed!", "Works!")
- Committing code
- Creating PRs
- Moving to next task
- Reporting to user
## The Bottom Line
**No shortcuts for verification.**
Run the command. Read the output. THEN claim the result.
```bash
# Always run these before claiming completion:
flutter analyze
flutter test
flutter build apk --debug # or appropriate build target
This is non-negotiable.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.