verify-before-done
Require fresh verification evidence before claiming work is complete. Use ALWAYS before any completion claim, commit, push, PR, or status report. Prevents false completion claims.
Install
mkdir -p .claude/skills/verify-before-done && curl -L -o skill.zip "https://mcp.directory/api/skills/download/7149" && unzip -o skill.zip -d .claude/skills/verify-before-done && rm skill.zipInstalls to .claude/skills/verify-before-done
About this skill
Verify Before Done
철칙
검증 증거 없이 완료 주장 절대 금지
게이트 함수
모든 완료/성공 주장 전에:
- 식별: 이 주장을 증명하는 명령은?
- 실행: 해당 명령을 지금 실행 (이전 결과 불가)
- 읽기: 전체 출력, exit code, 실패 수 확인
- 검증: 출력이 주장을 확인하는가?
- No → 실제 상태를 증거와 함께 보고
- Yes → 증거와 함께 완료 주장
- 그 후에만 주장 가능
주장별 필요 증거
| 주장 | 필요한 증거 | 불충분한 증거 |
|---|---|---|
| "테스트 통과" | 테스트 명령 출력: 0 failures | 이전 실행, "통과할 것" |
| "린터 깨끗" | 린터 출력: 0 errors | 부분 체크, 추정 |
| "빌드 성공" | 빌드 명령: exit 0 | 린터 통과, 로그가 괜찮아 보임 |
| "버그 수정됨" | 원래 증상 테스트: 통과 | 코드 변경함, 수정 추정 |
| "요구사항 충족" | 항목별 체크리스트 | 테스트 통과 |
🚨 위험 단어 (사용 시 즉시 멈춤)
이 단어들이 입에서 나오려 하면 STOP:
- "~될 거야" / "~할 것 같아"
- "아마" / "대체로"
- "좋아!" / "완벽!" / "끝!" (검증 전)
- "~한 것 같은데"
- "수동으로 확인했으니"
- "에이전트가 성공이라고 했으니"
위임 작업도 예외 없음
서브에이전트가 "성공" 보고 → 독립 검증 필수
- VCS diff 확인 → 변경 사항 실제로 있는지?
- 테스트 직접 실행 → 정말 통과하는지?
- 에이전트 보고를 맹신하지 말 것
합리화 방지
| 핑계 | 현실 |
|---|---|
| "지금 잘 작동할 거야" | 검증 실행하세요 |
| "확신해" | 확신 ≠ 증거 |
| "이번 한 번만" | 예외 없음 |
| "린터 통과했으니" | 린터 ≠ 컴파일러 ≠ 런타임 |
| "피곤해" | 피곤함 ≠ 면제 |
| "부분 확인이면 충분" | 부분 확인은 아무것도 증명 못함 |
왜 중요한가
검증 없는 완료 주장은:
- 신뢰를 깨뜨림
- undefined 함수가 배포됨
- 요구사항 누락이 발견 안 됨
- 거짓 완료 → 재작업 → 시간 낭비
검증은 선택이 아니라 필수.
More by openclaw
View all skills by openclaw →You might also like
ui-ux-pro-max
nextlevelbuilder
"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."
pdf-to-markdown
aliceisjustplaying
Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.
flutter-development
aj-geddes
Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.
drawio-diagrams-enhanced
jgtolentino
Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.
godot
bfollington
This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.
nano-banana-pro
garg-aayush
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
Related MCP Servers
Browse all servers
Context7Boost your AI code assistant with Context7: inject real-time API documentation from OpenAPI specification sources into your coding workflow.
Task MasterBoost productivity with Task Master: an AI-powered tool for project management and agile development workflows, integrated with popular editors.
Spec Workflow MCPStructured spec-driven development workflow for AI-assisted software development.
PerplexityEmpower your workflows with Perplexity Ask MCP Server—seamless integration of AI research tools for real-time, accurate answers.
Spec-Driven DevelopmentGuide your software projects with structured prompts from requirements to code using the waterfall development model and software design specifications.
HuggingFace Spaces ConnectorSeamlessly connect Hugging Face Spaces with your AI assistants for instant access to powerful AI models—no manual setup required.