메뉴
Context-first investigation mode. Use for debugging, system understanding, and any task where conclusions should follow grounded internal and external analysis.
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 | analyze-mode |
| description | Context-first investigation mode. Use for debugging, system understanding, and any task where conclusions should follow grounded internal and external analysis. |
ACTIVATION: When loaded, gather comprehensive context before any deep analysis.
ANALYSIS MODE - Context First, Conclusions Second
Deploy parallel context gathering only where it will materially improve correctness:
// Internal context (1-2 agents)
task(agent="explore", prompt="Find all implementations of [topic]", background=true)
task(agent="explore", prompt="Find tests and usage patterns for [topic]", background=true)
// External context (if libraries involved)
task(agent="researcher", prompt="Find official docs for [library]", background=true)
task(agent="researcher", prompt="Find known issues and solutions", background=true)
While agents run, use direct tools to confirm scope, structure, symbols, diagnostics, and relevant history.
Escalate to Oracle when:
task(agent="oracle", prompt="Analyze [problem] given context...")
Synthesize analysis into a compact, evidence-rich answer:
## Analysis Summary
**Subject:** [What was analyzed]
**Context Gathered:**
- [Finding 1 from explore/researcher]
- [Finding 2]
**Key Observations:**
- [Observation 1]
- [Observation 2]
**Root Cause / Conclusion:**
[Clear statement]
**Recommended Action:**
[Specific next steps]
**Confidence Level:** [High/Medium/Low] - [Reasoning]