跳到正文
TakoAPI
返回技能列表

babel-epistemic

由 mdiskint 提供

Coding Agents & IDEs
421下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Prevents metacognitive poisoning in multi-agent handoffs.

描述

该技能的功能

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.

何时使用

  • 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

示例工作流

输入

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

智能体
  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

输出

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

安装

clawhub install mdiskint/babel-epistemic

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接