About social-proof-evidence
social-proof-evidence is a marketing skill for selecting and presenting social proof. It requires evidence to be genuine and relevant, and provides a process for identifying staged cues, assessing risks, and making ethical rewrites.
Key features
- 01Select genuine, relevant social proof
- 02Check whether evidence supports a claim
- 03Spot manipulative cues and anti-patterns
- 04Follow a process for ethical rewrites
Use cases
- 01Audit customer testimonials in marketing
- 02Choose relevant evidence for product messaging
- 03Rewrite fabricated or staged social proof
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/social-proof-evidencein Claude Code to confirm it loaded.
Bundled files
References and scripts installed along with SKILL.md.
guidelines.mdagents/openai.yamlevals/evals.jsonreferences/social-proof/checklist.mdexamples.mdknowledge.mdrules.mdsmells.mdworkflows/choose-social-proof.mdDetails
From the project READMESocial Proof Evidence
Use social proof as evidence, not theater. The principle works because people infer appropriate action from others, especially under uncertainty, but the evidence must be real and relevant.
Quick Start
- Read
guidelines.mdto choose the smallest useful reference set. - Load
references/social-proof/knowledge.mdfor concepts andreferences/social-proof/rules.mdfor operating rules. - Use
workflows/choose-social-proof.mdfor repeatable tasks. - For audits, surface both the active influence cue and the ethical rewrite.
Contents
| File | Purpose |
|---|---|
| references/social-proof/knowledge.md | Core concepts and source-grounded definitions |
| references/social-proof/rules.md | Rules, boundaries, and practical guidelines |
| references/social-proof/examples.md | Bad/better examples for applied situations |
| references/social-proof/smells.md | Red flags and anti-patterns to detect |
| references/social-proof/checklist.md | Fast review checklist |
| workflows/choose-social-proof.md | Select and present proof that is truthful, relevant, and not staged. |
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
- 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.
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.