Use when creating, auditing, optimizing, or rewriting marketing copy - posts, ads, landing pages, emails, webinars, push notifications, product launches. Applies 20 cognitive biases from behavioral economics and evolutionary psychology to engineer high-converting persuasion. Self-contained skill with inline bias router, 14 power combos, 13 anti-patterns with detection rules (including statistical-only fallacy), 7 tone styles with narrative minimums and keyword density caps, cultural adaptation across 12 regions, post-generation verification (6 checks including humanity), Named Person Story Arc requirement with fallback patterns for human-quality output, and Rewrite Without Metrics variant for qualitative transformation of existing copy (7 rewrite intents). Use ONLY for marketing content creation, audit, optimization, or rewrite tasks. DO NOT use for general writing, technical documentation, or non-marketing tasks.
$npx -y skills add madeval/mindfluence --skill mindfluenceInstalls into the current project.
Run `npx skills use "https://github.com/madeval/mindfluence" --skill "madeval/mindfluence"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/madeval/mindfluence" that are relevant to the current task. Run `npx skills add "https://github.com/madeval/mindfluence"` and select the relevant skills, then follow their instructions.
| 1 | # MindFluence |
| 2 | |
| 3 | []() |
| 4 | [](LICENSE) |
| 5 | []() |
| 6 | |
| 7 | [ **English** | [Русский](README.ru.md) ] |
| 8 | |
| 9 | > **Persuasion engineered through psychology, not manipulation.** |
| 10 | |
| 11 | An AI prompt-skill that turns 20 cognitive biases into high-converting marketing copy - for any language, any platform, any audience. **v2.2: self-contained single-file with narrative depth.** All tables, 13 anti-patterns with detection rules, cultural data, and few-shot examples are inlined into SKILL.md. Named Person Story Arc (NPSA) requirement ensures human-quality output alongside mechanical verification. No external file reads required for core operation. |
| 12 | |
| 13 | --- |
| 14 | |
| 15 | ## What is this? |
| 16 | |
| 17 | **MindFluence** is a system prompt (skill) for LLMs - GPT, Claude, Gemini, DeepSeek or any capable model. It transforms the AI into a marketing strategist who understands *why* humans click, read, and buy - not just *what* to write. |
| 18 | |
| 19 | It's built on decades of research in behavioral economics and evolutionary psychology: Kahneman's two systems, Cialdini's principles, Munger's psychological misjudgments, Festinger's cognitive dissonance - distilled into actionable copywriting instructions. |
| 20 | |
| 21 | ## How it works |
| 22 | |
| 23 | 1. **Load `SKILL.md`** as a system prompt into any LLM. That's it - the file is fully self-contained. |
| 24 | 2. **Give a task:** "Write a LinkedIn post about..." / "Create a landing page for..." / "Audit this ad for cognitive biases." |
| 25 | 3. **Get output** with every bias labeled, every decision explained, every word psychologically justified. |
| 26 | |
| 27 | **The LLM uses a single-table Bias Selection Router** (audience × product × platform → instant bias stack) instead of a 10-step procedure. After generating, it runs a **mechanical Post-Generation Verification** - 6 checks (numbers, names, exit, explain, blame-system, human narrative) - and a mandatory **Named Person Story Arc** requirement before delivering. |
| 28 | |
| 29 | **Four modes:** |
| 30 | - **Quick Mode** (default) - 3-step internal procedure: lookup router → scenario override → verify. Fast for user, fast for LLM. |
| 31 | - **Deep Mode** - the AI asks 5 clarifying questions at once, then routes through the same lookup. |
| 32 | - **Audit Mode** - analyzes existing copy for biases and anti-patterns using mechanical detection rules (13 anti-patterns including Statistical-Only Fallacy). |
| 33 | - **Optimize Mode** - iterates on underperforming copy using funnel-to-bias mapping. Generates A/B variants with statistical confidence thresholds. Also handles qualitative rewrites without metrics: tone shifts, bias injection/removal, anti-pattern fixes, audience/platform adaptation (7 rewrite intents). |
| 34 | |
| 35 | ## The 20 Cognitive Biases |
| 36 | |
| 37 | | # | Bias | Category | Marketing Use | |
| 38 | |---|------|----------|---------------| |
| 39 | | 1 | **Social Proof / Bandwagon** | Social | Used by teams at Google, Airbnb, and 10,000+ startups | |
| 40 | | 2 | **Anchoring** | Optimizer | Enterprise: $499/mo → Pro: $99/mo | |
| 41 | | 3 | **Framing** | Filter | "90% success rate" vs "Only 10% fail" | |
| 42 | | 4 | **Appeal to Authority** | Social | The same method taught at Harvard Business School | |
| 43 | | 5 | **Fear / Loss Aversion** | Filter + Social | Every day without X costs you $200 in missed revenue | |
| 44 | | 6 | **Availability Heuristic** | Optimizer | "Sarah tripled her revenue in 3 months. Here's the exact playbook." | |
| 45 | | 7 | **Confirmation Bias** | Filter | "You already know newsletters are broken. Here's the data that proves your instinct right." | |
| 46 | | 8 | **Cognitive Dissonance** | Filter + Optimizer | "You care about health but skip breakfast. Our 2-minute shake fixes the gap." | |
| 47 | | 9 | **Survivorship Bias** | Optimizer | "The 23% who succeeded all followed this pattern. The 77% did not." | |
| 48 | | 10 | |