본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

babel-epistemic

mdiskint 제작

Coding Agents & IDEs
421clawskills.sh가 보고한 다운로드 수
0조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

Prevents metacognitive poisoning in multi-agent handoffs.

설명

이 스킬이 하는 일

Babel Epistemic Convention tracks confidence levels across multi-agent handoffs. Without it, inferences made by one agent silently become verified facts by the time they reach a third agent. The skill provides a tagging vocabulary for confidence, intent, register, affect, grounds, and trajectory that travels with the work.

Confidence calibration propagates through the forwarding block without any shared infrastructure, so the receiving agent does not need the skill installed.

사용 시점

  • Tagging a news-sourced inference as REPORTED before passing it to a downstream summarizer
  • Preventing a derived metric from being treated as confirmed data in a financial pipeline
  • Flagging regulatory constraints that must remain non-overridable across agent delegations
  • Marking a four-month declining trend as ESCALATE rather than a neutral INFORM update
  • Auditing a three-agent research chain for confidence laundering after incorrect outputs

예시 워크플로

입력

User asks: Research Acme Corp's potential Vanta partnership and hand off to the drafting agent.

에이전트
  1. 1

    Search for partnership mentions and find a single unverified news item

  2. 2

    Label the claim REPORTED at 0.25 confidence, not VERIFIED_DATA

  3. 3

    Set intent to INFORM and consider switching to FLAG_RISK given low confidence

  4. 4

    Append the Babel forwarding block to the handoff output

  5. 5

    Drafting agent inherits the label as REPORTED and does not promote it to verified in the draft

출력

Handoff payload with per-assertion confidence tags intact; drafting agent qualifies the claim as unconfirmed in the output.

설치

clawhub install mdiskint/babel-epistemic

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크