메뉴
Forces agents to run verification commands and show evidence before claiming completion. Prevents "it should work" without proof.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Interview the user relentlessly about a plan or design until branch-level decisions are resolved for execution.
Access Figma designs, extract design systems, and retrieve component specifications. Use when implementing UI from Figma mockups, extracting design tokens, or analyzing design files.
Enforce cost-aware MCP usage. Use when a task might trigger heavy external tools, web search, or broad context expansion. Prevents token burn by ensuring MCPs are only used when local context is insufficient.
Navigate the Warmplane mcp0 facade efficiently. Use when the active config exposes provider capabilities through `mcp0_*` tools and you need to discover or call provider tools without brute-force describing large capability sets. Trigger on requests involving mcp0, Warmplane, or provider work through the facade such as Linear, Notion, Figma, New Relic, Context7, grep.app, or Storybook tools.
Use this when the user needs to control Chrome, navigate to a page, inspect a tab, click or fill elements, take screenshots, or automate a browser flow with aeroxy/chrome-devtools-cli.
Guidelines for creating and managing implementation plans with citations
| name | verification-before-completion |
| description | Forces agents to run verification commands and show evidence before claiming completion. Prevents "it should work" without proof. |
Load this skill when you need to ensure work is actually verified, not just claimed complete.
NOTHING is "done" without PROOF it works.
Claims without evidence are worthless. Every completion claim must be backed by diagnostics, command output, or a direct manual observation.
Before marking ANY task complete, verify the changed area with the smallest set of checks that can still prove correctness:
lsp_diagnostics on changed files when supported.| Violation | Why It Fails |
|---|---|
| "It should work now" | No evidence. Run it. |
| "I added the tests" | Did they pass? Show output. |
| "Fixed the bug" | How do you know? What did you test? |
| "Implementation complete" | Did you verify against success criteria? |
| Skipping test execution | Tests exist to be RUN |
| "The code looks correct" | Looking isn't testing. Execute it. |
When reporting completion, include:
## Verification Evidence
### Build
✅ `bun run build` - Exit code 0
Output: [paste relevant output]
### Tests
✅ `bun test` - 42 tests passed
Output: [relevant summary only]
### Type Check
✅ `lsp_diagnostics` - No errors in changed files
### Manual Check
✅ Verified [specific behavior] works as expected
| Phase | Command | Evidence Needed |
|---|---|---|
| Build | bun run build | Exit code 0 |
| Test | bun test | All pass |
| Types | lsp_diagnostics | No errors |
| Lint | bun run lint | No warnings |
CLAIM NOTHING WITHOUT PROOF. EXECUTE. VERIFY. SHOW EVIDENCE.