Use when improving cold outreach, sales conversations, customer discovery, community moderation, referral asks, partnership messages, interviews, or relationship-based persuasion where similarity, compliments, familiarity, cooperation, association, or rapport may affect trust.
SkillScore95Maintained
Automatic
◆Sales & GTM pack
Last verified 8/16/2026
What it changes
Passed 21 of 22 test cases with the skill, and 18 of 22 without it.
Without skill82%
With skill95%
Checks it passed that the model alone missed
Includes pricing context for post-trial plans
Explains clear timeline options and account status context
Highlights the missing proof for the seat threshold and time limit
3 fixed18 passed either way1 still failing0 broke
Pass-rate lift
+14 pp
Tokens
0%
Agent turns
0%
Response time
-28%
Model gemini-3.6-flashMeasured 8/16/2026v121 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 3
Prompt
Rewrite this renewal notice: 'Your service will degrade in 24 hours unless you auto-renew right now!' to maintain trust while encouraging renewal.
What was checked, without and with the skill
Checked
Without skill
With skill
Eliminates coercive time pressure tactics
Passed
Passed
Explains clear timeline options and account status context
Missed
Passed
case-12 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md38 linessingle file
Trust and Liking
Build trust by finding real common ground, making useful cooperation easy, and avoiding counterfeit rapport. Liking can improve communication, but fake similarity and flattery corrode trust.
Quick Start
Read guidelines.md to choose the smallest useful reference set.
Load references/liking/knowledge.md for concepts and references/liking/rules.md for operating rules.
Use workflows/build-rapport-without-flattery.md for repeatable tasks.
For audits, surface both the active influence cue and the ethical rewrite.
Contents
File
Purpose
references/liking/knowledge.md
Core concepts and source-grounded definitions
references/liking/rules.md
Rules, boundaries, and practical guidelines
references/liking/examples.md
Bad/better examples for applied situations
references/liking/smells.md
Red flags and anti-patterns to detect
references/liking/checklist.md
Fast review checklist
workflows/build-rapport-without-flattery.md
Improve relationship-based persuasion while avoiding fake similarity and manipulative praise.
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.