curiosity-engine
por luofulily1-cmyk
Coding Agents & IDEsResumo
Curiosity-driven reasoning enhancement for OpenClaw agents.
Descrição
O que esta skill faz
Curiosity Engine reshapes how an agent reasons at inference time using a structured OODA-C loop: Observe, Orient, Doubt, Act, and Curiose. It injects self-questioning, assumption challenging, and information gap detection before the agent responds. No training required — it operates as a reasoning protocol during live sessions.
Unlike prompt-level instructions to 'think step by step', this skill provides a concrete, repeatable loop with defined protocols for doubt and gap detection, making deeper reasoning reproducible across sessions.
Quando usá-la
- Researching an unfamiliar technical topic before answering
- Investigating why a system behaves unexpectedly
- Digging deeper into a surprising data finding
- Fact-checking assumptions in a complex analysis
- Exploring open-ended questions where quick answers fall short
Exemplo de fluxo de trabalho
User asks: 'Why did our API latency spike last Tuesday?'
- 1
Observe available logs, metrics, and context provided
- 2
Form initial hypothesis about likely causes and rate confidence
- 3
Run Protocol A: generate 3 unexplored questions about the spike
- 4
Run Protocol C: map known facts vs assumed vs missing data
- 5
Use web_search or exec to fill highest-priority knowledge gaps
- 6
Reflect on findings, update confidence, log open threads
Structured response with findings, updated confidence rating, any surprises noted, and open threads for follow-up
Instalação
clawhub install luofulily1-cmyk/curiosity-engineExecute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.