commitment-ladder-design
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseCommitment Ladder Design
承诺阶梯设计
Design commitments that help users act on real intent, not commitments that trap them into defending a decision. The consistency drive is useful when it supports identity-aligned action and risky when it hides changing terms.
设计有助于用户基于真实意愿行动的承诺机制,而非将用户困在为决策辩护的陷阱中。一致性驱动力在支持符合用户身份的行动时是有益的,但在隐藏条款变更时则存在风险。
Quick Start
快速开始
- Read to choose the smallest useful reference set.
guidelines.md - Load for concepts and
references/commitment/knowledge.mdfor operating rules.references/commitment/rules.md - Use for repeatable tasks.
workflows/build-commitment-ladder.md - For audits, surface both the active influence cue and the ethical rewrite.
- 阅读以选择最实用的参考资料集。
guidelines.md - 加载获取相关概念,加载
references/commitment/knowledge.md获取操作规则。references/commitment/rules.md - 使用完成可重复任务。
workflows/build-commitment-ladder.md - 进行审核时,同时明确当前的影响提示语以及符合伦理的改写版本。
Contents
目录
| File | Purpose |
|---|---|
| references/commitment/knowledge.md | Core concepts and source-grounded definitions |
| references/commitment/rules.md | Rules, boundaries, and practical guidelines |
| references/commitment/examples.md | Bad/better examples for applied situations |
| references/commitment/smells.md | Red flags and anti-patterns to detect |
| references/commitment/checklist.md | Fast review checklist |
| workflows/build-commitment-ladder.md | Create a sequence of small, authentic commitments that lead toward a meaningful user goal. |
| 文件 | 用途 |
|---|---|
| references/commitment/knowledge.md | 核心概念及基于来源的定义 |
| references/commitment/rules.md | 规则、边界及实用指南 |
| references/commitment/examples.md | 应用场景下的反面/优化示例 |
| references/commitment/smells.md | 需要识别的危险信号及反模式 |
| references/commitment/checklist.md | 快速审核清单 |
| workflows/build-commitment-ladder.md | 创建一系列小型、真实的承诺,逐步引导用户达成有意义的目标。 |
Operating Principles
操作原则
- Use only honest evidence. Do not invent popularity, scarcity, credentials, endorsements, or social connection.
- Separate helping a good decision from pushing a shortcut response. If the cue is counterfeit, treat it as a red flag.
- When rewriting, preserve user agency: add context, alternatives, and enough time to decide when stakes are meaningful.
- 仅使用真实证据。不得虚构受欢迎程度、稀缺性、资质、背书或社交关联。
- 将助力合理决策与诱导快速响应区分开。若提示语存在虚假成分,需将其视为危险信号。
- 改写时需保留用户自主权:当决策涉及重大利益时,补充背景信息、替代选项,并给予充足的决策时间。
Output Pattern
输出模式
- Diagnosis - name the influence principle or cue.
- Evidence Check - state what proof supports or is missing from the cue.
- Risk - explain manipulation, trust, or decision-quality risk.
- Rewrite or Recommendation - provide an ethical alternative.
- 诊断 - 明确所采用的影响原则或提示语。
- 证据核查 - 说明支持或缺失该提示语的证据。
- 风险 - 解释操纵、信任或决策质量方面的风险。
- 改写或建议 - 提供符合伦理的替代方案。
Validation
验证
Use the prompts in as smoke tests. A good result identifies the relevant Influence principle, preserves user agency, and avoids fabricated evidence or coercive pressure.
evals/evals.json使用中的提示作为冒烟测试。优质结果应能识别相关的影响原则、保留用户自主权,且避免伪造证据或施加强制压力。
evals/evals.json