Menü
Break down complex problems before implementation using multi-model reasoning and prompt techniques
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Use when the user wants a security review of code or a diff — OWASP/CWE findings with severity, taint/data-flow analysis, and concrete fixes via security_review
Use when the user wants tests generated for code or a diff — enumerates edge cases and failure modes first, then emits runnable test code via testgen
Use when a task would benefit from a structured thinking technique but you're not sure which — recommends the right prompt technique for the intent (debug, spec, refactor, decision, design) and applies it
Use for decisions or judgments worth multiple independent perspectives — multi-model council with parallel analysis, search grounding, and synthesis (30-60s); for a quick single-call verdict use the jury tool directly
Use when the user shares or finishes a plan and wants it stress-tested before execution — adversarial multi-model pre-mortem with ranked risks, mitigations, and concrete plan edits
Use when code changes are ready for review — a diff exists, the user says "review my changes/PR", or a commit is about to happen. Multi-model diff review (Kimi, DeepSeek, GPT-5.5 panel + Gemini judge) with a MERGEABLE verdict
| name | breakdown |
| description | Break down complex problems before implementation using multi-model reasoning and prompt techniques |
| user-invocable | true |
Decompose complex tasks using first principles, pattern analysis, and multi-model reasoning before implementation. Adapts to your available API keys.
/breakdown [problem or task description]
When user invokes /breakdown [problem]:
The pipeline adapts to available tools. Each step lists a priority chain - use the FIRST available tool.
Use the FIRST available:
mcp__tachibot-mcp__execute_prompt_technique({ technique: "first_principles", tool: "grok_reason", query: "[problem]" })mcp__tachibot-mcp__execute_prompt_technique({ technique: "first_principles", tool: "openai_reason", query: "[problem]" })mcp__tachibot-mcp__execute_prompt_technique({ technique: "first_principles", tool: "gemini_analyze_text", query: "[problem]" })If execute_prompt_technique is unavailable, call the reasoning tool directly with the prompt: "Apply first principles thinking to: [problem]. Strip to fundamental truths, challenge assumptions, identify atomic units."
Extract: Core truths, assumptions to challenge, atomic units.
Use the FIRST available:
mcp__tachibot-mcp__execute_prompt_technique({ technique: "least_to_most", tool: "kimi_thinking", query: "..." })mcp__tachibot-mcp__execute_prompt_technique({ technique: "least_to_most", tool: "kimi_decompose", query: "..." })mcp__tachibot-mcp__execute_prompt_technique({ technique: "decompose", tool: "gemini_analyze_text", query: "..." })mcp__tachibot-mcp__execute_prompt_technique({ technique: "decompose", tool: "openai_reason", query: "..." })Feed step 1 output into the query. Use least_to_most to order sub-tasks from simplest → hardest (atomic parts first, complex parts last — each builds on previous solutions).
Extract: Sub-tasks ordered simplest→hardest, dependency graph, execution order.
Use the FIRST available:
mcp__tachibot-mcp__execute_prompt_technique({ technique: "patterns", tool: "gemini_analyze_text", query: "..." })mcp__tachibot-mcp__execute_prompt_technique({ technique: "patterns", tool: "grok_reason", query: "..." })mcp__tachibot-mcp__execute_prompt_technique({ technique: "patterns", tool: "openai_reason", query: "..." })Feed step 2 output into the query.
Extract: Hidden connections, recurring themes, potential cycles/loops.
Use the FIRST available:
mcp__tachibot-mcp__execute_prompt_technique({ technique: "pre_mortem", tool: "grok_reason", query: "..." })mcp__tachibot-mcp__execute_prompt_technique({ technique: "pre_mortem", tool: "openai_reason", query: "..." })mcp__tachibot-mcp__execute_prompt_technique({ technique: "feasibility", tool: "gemini_analyze_text", query: "..." })Use pre_mortem when available: "Assume this failed 6 months from now — why?" This catches failure modes that forward analysis misses (Klein 2007). Fall back to feasibility if pre_mortem isn't available.
Extract: Failure causes ranked by likelihood, early warning signs, mitigations, go/no-go.
Present structured breakdown:
## Problem
[One sentence]
## First Principles
- [Truth 1]
- [Truth 2]
- Challenged assumption: [X]
## Sub-Tasks
1. **[Task A]** - [purpose]
- Depends on: none
- Risk: low
2. **[Task B]** - [purpose]
- Depends on: Task A
- Risk: medium
## Patterns Found
- Causality: [X causes Y]
- Cycle: [A -> B -> C -> A]
- Anomaly: [unexpected finding]
## Execution Order (simplest → hardest)
1. [Simplest] - no deps, builds foundation
2. [Next] - builds on 1
...
## Feasibility
| Aspect | Status | Notes |
|--------|--------|-------|
| Technical | OK | [details] |
| Time | Warning | [constraint] |
| Resources | OK | [details] |
## Risks & Mitigations
| Risk | Likelihood | Mitigation |
|------|------------|------------|
| [Risk 1] | Medium | [approach] |
## Verdict
[Go / No-go / Needs more info]
/breakdown implement OAuth authentication with refresh tokens/breakdown refactor monolith payment module to microservice/breakdown add real-time collaboration to document editor