메뉴
Apply structured reasoning models to analyze a decision or problem. Activate when user mentions "reason", "pre-mortem", "5 whys", "pareto", "think through", "analyze decision", "inversion", "first principles", "second order".
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
Generate professional Product Requirement Documents (PRD) from multiple sources — Figma designs, briefs, user research, existing code. Includes risk analysis, RICE prioritization, Gherkin stories and launch plan. Activate when user mentions "PRD", "product requirements", "requirement document", "product spec", "figma to PRD", "generate PRD".
Record and query the decision log for a project. Activate when user mentions "audit", "trail", "log decisions", "decision history", "why was this decided", "ADR", "architecture decision".
Audit and document what personal or sensitive data the project collects, processes, and stores. Activate when user mentions "privacy", "data policy", "what data", "GDPR", "personal data", "data retention", "PII".
Detect and reconcile divergence between specs and implementation. Activate when user mentions "drift", "sync", "spec divergence", "out of sync", "spec doesn't match", "implementation differs".
Estimate effort, duration and cost using 4 complementary models (Function Points, Planning Poker AI, COCOMO, Historical). Activate when user mentions "estimate", "estimation", "effort", "how long", "cost", "story points", "sizing".
Evaluate the quality of a spec and return a structured score with improvement recommendations. Activate when user mentions "spec quality", "score spec", "how good is my spec", "spec review", "validate spec quality".
| name | doncheli-reasoning |
| description | Apply structured reasoning models to analyze a decision or problem. Activate when user mentions "reason", "pre-mortem", "5 whys", "pareto", "think through", "analyze decision", "inversion", "first principles", "second order". |
| ID | Best For |
|---|---|
| pre-mortem | Imagining failure before it happens; surfacing hidden risks |
| 5-whys | Root cause analysis of a known problem |
| pareto | Identifying the 20% of causes driving 80% of impact |
| inversion | Asking "what would guarantee failure?" to find blockers |
| second-order | Mapping downstream consequences of a decision |
| first-principles | Decomposing assumptions down to fundamental truths |
| minimize-regret | Choosing the option you will regret least in 10 years |
| opportunity-cost | Evaluating what you give up by choosing this option |
| circle-of-competence | Assessing whether you have the knowledge to decide well |
| map-territory | Separating your mental model from reality |
| probabilistic | Assigning probabilities to outcomes; expected-value calc |
| reversibility | Classifying decisions as one-way vs. two-way doors |
| rlm-chain-of-thought | Step-by-step explicit reasoning (RLM: PrimeIntellect style) |
| rlm-decomposition | Breaking a complex problem into atomic sub-problems (RLM) |
| rlm-verification | Self-checking the reasoning chain for contradictions (RLM) |
## Reasoning: <problem>
**Model applied:** <id> — <why this model fits>
### Analysis
<step-by-step application of the model>
### Insight / Recommendation
…
### Caveats
…