Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/influence-audit
Use when auditing landing pages, emails, sales scripts, pricing flows, fundraising asks, product UX, or negotiations for persuasion mechanisms, pressure tactics, manipulation risk, fake urgency, fake social proof, authority misuse, or ethical rewrites.
Passed 21 of 23 test cases with the skill, and 21 of 23 without it.
1 fixed20 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
An automated pre-recorded webinar platform shows 'Only 3 seats remaining for this live broadcast session!' every time someone loads the page at any hour of the day. Audit this registration form.
| Checked | Without skill | With skill |
|---|---|---|
| Identifies the seat limit claims as false urgency. | Passed | Passed |
| Points out that pre-recorded automated streams lack physical seat limits. | Missed | Passed |
| Recommends labeling the content as on-demand. | Passed | Passed |
The instructions your model reads when the skill loads.
Audit persuasion by identifying which shortcut cues are present, whether those cues are truthful, and what a less manipulative version would look like. The central distinction is honest decision support versus counterfeit evidence.
guidelines.md to choose the smallest useful reference set.references/audit/knowledge.md for concepts and references/audit/rules.md for operating rules.workflows/audit-influence-risk.md for repeatable tasks.| File | Purpose |
|---|---|
| references/audit/knowledge.md | Core concepts and source-grounded definitions |
| references/audit/rules.md | Rules, boundaries, and practical guidelines |
| references/audit/examples.md | Bad/better examples for applied situations |
| references/audit/smells.md | Red flags and anti-patterns to detect |
| references/audit/checklist.md | Fast review checklist |
| workflows/audit-influence-risk.md | Review a persuasion surface for mechanisms, evidence quality, user autonomy, and safer rewrites. |
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.
test cases passed, vs 21 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.