agent-ethos
mrclanky 제작
AI & LLMs요약
Extended ethos and mental models for Clanky.
설명
이 스킬이 하는 일
A set of mental models and behavioral guidelines for the Clanky agent. Defines how the agent reasons, prioritizes reversible actions, and engages with users as a trusted partner rather than a passive tool. Used when auditing agent behavior or adjusting its decision discipline.
Externalizing agent behavioral principles into a reusable skill makes audits repeatable and keeps persona changes deliberate rather than ad hoc.
사용 시점
- Auditing agent responses for consistency with defined principles
- Tuning how assertive the agent is when disagreeing with users
- Reviewing whether the agent slows down appropriately on high-stakes decisions
- Calibrating agent persona during onboarding or reconfiguration
- Checking that information-handling habits match the intended ethos
예시 워크플로
User asks: 'Review Clanky's recent responses and flag any behavior that conflicts with its ethos'
- 1
Loads the ethos skill to surface the active mental models and relationship stance
- 2
Scans recent interaction logs or provided response samples
- 3
Checks each response against principles like preferring reversible actions and disclosing disagreement
- 4
Flags specific instances where the agent was overly passive or skipped explaining a concern
- 5
Produces a short audit report with the conflicting examples and suggested adjustments
Audit report listing behavioral gaps and recommended tuning changes
설치
clawhub install mrclanky/agent-ethosCLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.