跳到主要内容
知仓学习社ZHICANG

authority-credibility

Use when presenting or auditing expertise, credentials, certifications, advisory boards, expert quotes, trust badges, medical claims, legal claims, …

不碰外部(只输出文字)无严重或高危命中hashgraph-online/awesome-codex-plugins

它会碰到什么

扫了多少10 个文本文件,16 KB
它会碰到什么不碰外部(只输出文字)
命中总数0 处
命中统计严重 0 · 高 0 · 中 0 · 低 0

这一栏是扫描器报的事实,不是结论。命中多不等于有毒(安全工具、规则库、示例脚本本来就会包含危险写法),命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系,需要你自己看。

技能内容

Authority Credibility

Use authority signals to clarify expertise and accountability, not to bypass scrutiny. Authority is useful when the credential is relevant, current, and accurately scoped.

Quick Start

  1. Read guidelines.md to choose the smallest useful reference set.
  2. Load references/authority/knowledge.md for concepts and references/authority/rules.md for operating rules.
  3. Use workflows/verify-credibility-signals.md for repeatable tasks.
  4. For audits, surface both the active influence cue and the ethical rewrite.

Contents

| File | Purpose |

| --- | --- |

| references/authority/knowledge.md | Core concepts and source-grounded definitions |

| references/authority/rules.md | Rules, boundaries, and practical guidelines |

| references/authority/examples.md | Bad/better examples for applied situations |

| references/authority/smells.md | Red flags and anti-patterns to detect |

| references/authority/checklist.md | Fast review checklist |

| workflows/verify-credibility-signals.md | Check authority claims for relevance, evidence, scope, and overstatement. |

Operating Principles

  • 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.

Output Pattern

  1. Diagnosis - name the influence principle or cue.
  2. Evidence Check - state what proof supports or is missing from the cue.
  3. Risk - explain manipulation, trust, or decision-quality risk.
  4. Rewrite or Recommendation - provide an ethical alternative.

Validation

Use the prompts in evals/evals.json as smoke tests. A good result identifies the relevant Influence principle, preserves user agency, and avoids fabricated evidence or coercive pressure.

想直接用这个技能?

本站把开放许可(MIT / Apache 等)的技能按仓库打包整理到网盘,点一下转存到你自己的网盘,不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接,不打包。