mechanism-ideation
Skill32 starsChanged 8 months agoMITView on GitHub
Ideate novel mechanism angles for a product claim or result — the "M" in RMBC. Use when you need unique, specific explanations of WHY a product delivers its promised outcome. Branches for supplements, e-commerce, and info products.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- Zenobia0000/dtc-copywriting-skillsedited, first seen Mar 20, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- Zenobia0000/dtc-copywriting-skills★ 453% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository41 other files it gives its agents.
- ab-test-planSkill
- ad-angle-generatorSkill
- ad-creative-auditSkill
- advertorial-writerSkill
- bonus-stackSkill
- broadcast-emailSkill
- cart-abandonment-flowSkill
- checkout-abandonmentSkill
- competitor-offer-analysisSkill
- copy-rewriteSkill
- creative-briefSkill
- email-promoSkill
- email-retention-sequencesSkill
- fb-ad-copySkill
- free-offer-briefSkill
- funnel-architectureSkill
- funnel-auditSkill
- guarantee-writerSkill
- hook-batterySkill
- ingredient-researchSkill
- lander-copySkill
- lead-writerSkill
- media-buying-briefSkill
- offer-stackSkill
- order-form-croSkill
- pdp-ecomm-templateSkill
- post-purchase-sequenceSkill
- pricing-strategySkill
- reengagement-sequenceSkill
- rmbc-contextSkill
- rmbc-copy-auditSkill
- scarcity-urgencySkill
- soap-opera-sequenceSkill
- thank-you-pageSkill
- ugc-briefSkill
- unified-research-synthesizerSkill
- upsell-scriptSkill
- upsell-sequence-writerSkill
- vsl-scriptSkill
- webinar-registration-copySkill
- welcome-sequenceSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 33
Read rmbc-context/SKILL.md for framework overview and quality dimensions.
- Distinctive: line 125
Every mechanism must name something specific — no "powerful formula" or "unique blend"
- Distinctive: line 131
Specificity gate: Every mechanism angle must include a number, name, or timeframe — no "unique approach" or "effective process"
- Distinctive: line 132
Mechanism quantification: When referencing the mechanism, include at least one specific data point (number, timeframe, study reference)
- Distinctive: line 134
Proof diversity: Use at least 2 different proof types (testimonial, statistical, authority, case study) — do not rely on a single proof mode
- Very specific: line 139
If research is thin, run /ingredient-research or /unified-research-synthesizer first
- Very specific: line 140
After mechanism selected, use in /hook-battery for mechanism-driven hooks
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
mechanism-ideation
Purpose
Generate 5-7 novel mechanism angles for a product's core claim. A mechanism is the unique, specific explanation of WHY a product delivers its result — not "it works" but "because of [specific thing no competitor can claim]." This is Stefan Georgi's "Copy Thinking" — strategic ideation before a single word of copy is written. The mechanism is what separates winning copy from generic copy.
A strong mechanism is:
- Novel — the reader thinks "I've never heard of that before"
- Specific — names a compound, process, framework, or system
- Believable — grounded in real product attributes or research
- Ownable — passes the "only we" test (no competitor can claim it)
Inputs
| Input | Required | Description |
product_description | Yes | What the product is, what it does, key ingredients/features/components |
product_category | Yes | One of: supplement, ecommerce, info_product |
target_claim | No | The specific result or transformation the mechanism must explain |
research_context | No | Prior research output (ingredient data, competitor analysis, ICP insights) |
Execution Protocol
Step 1 — Load Framework Context
Read rmbc-context/SKILL.md for framework overview and quality dimensions. The mechanism phase requires a novel explanation that passes the "only we" test.
Step 2 — Extract Raw Material
From product_description and research_context, identify:
- Differentiators — What does this product have that competitors don't?
- Process uniqueness — How is it made, formulated, delivered, or structured differently?
- Proof anchors — What clinical data, patents, case studies, or results exist?
- Naming opportunities — What can be branded, coined, or reframed?
Step 3 — Branch by Category
Supplements
Focus on ingredient-based mechanisms:
- Unique compounds or proprietary blends
- Delivery systems (liposomal, time-release, nano-emulsion)
- Synergistic combinations ("X amplifies Y by Z%")
- Bioavailability advantages (absorption rates, clinical comparisons)
- Dosage differentiation (therapeutic dose vs competitor underdosing)
- Origin/sourcing story (high-altitude, wild-harvested, patented extraction)
E-commerce
Focus on product design and manufacturing mechanisms:
- Material innovation (proprietary fabric, alloy, compound)
- Manufacturing process (hand-finished, 47-step quality check, zero-waste)
- Structural engineering (patented hinge, load distribution, airflow system)
- Sourcing story (single-origin, direct-from-artisan, traceable supply chain)
- Design methodology (tested with 500 users, 3 years R&D, biomechanics lab)
- Performance metric (lasts 3x longer, 40% lighter, withstands 10,000 cycles)
Info Products
Focus on methodology and framework mechanisms:
- Proprietary framework (named system, unique sequencing, contrarian model)
- Elimination angle ("removes the one thing that blocks X")
- Speed/compression mechanism ("condenses 10 years into 90 days because...")
- Counter-intuitive principle ("works by doing the opposite of conventional advice")
- Stacking/layering system ("3 phases that compound — each unlocks the next")
- Credential transfer ("developed from [specific experience] that no course covers")
Step 4 — Generate Mechanism Ideas
For each of the 5-7 mechanisms, develop:
- Mechanism name — A coined or branded term (e.g., "Tri-Phase Absorption Complex," "The Reverse Funnel Method")
- One-line explanation — What it is in plain language
- Why it works — The causal logic (2-3 sentences)
- Proof anchor — What evidence supports this mechanism
- Novelty score — 1-5 (1 = commonly claimed, 5 = never seen before)
- Specificity rating — 1-5 (1 = vague, 5 = precise and concrete)
- Believability check — HIGH / MEDIUM / LOW with one-line rationale
Step 5 — Rank and Recommend
Rank mechanisms by combined score (novelty + specificity). Flag any with LOW believability — these need additional research before use. Recommend the top 2-3 for copy development.
Output Format
## Mechanism Ideation: [Product Name]
**Category:** [supplement | ecommerce | info_product]
**Target claim:** [what the mechanism must explain]
---
### 1. [Mechanism Name]
**What it is:** [one-line explanation]
**Why it works:** [2-3 sentence causal logic]
**Proof anchor:** [supporting evidence]
| Novelty | Specificity | Believability |
|---------|-------------|---------------|
| X/5 | X/5 | HIGH/MED/LOW |
[Repeat for each mechanism]
---
## Recommendation
**Top picks:** [ranked top 2-3 with brief rationale]
**Research gaps:** [any mechanisms that need deeper research before use]
**Next steps:** [which downstream skills to run]Quality Criteria
- Every mechanism must name something specific — no "powerful formula" or "unique blend"
- At least 3 of 7 mechanisms should score 4+ on novelty
- Any mechanism scoring LOW on believability must include a research gap callout
- Mechanisms must be grounded in actual product attributes, not fabricated claims
- Output should give a copywriter enough material to write a mechanism reveal section
- Specificity gate: Every mechanism angle must include a number, name, or timeframe — no "unique approach" or "effective process"
- Mechanism quantification: When referencing the mechanism, include at least one specific data point (number, timeframe, study reference)
- Audience journey: Each mechanism must reference where the reader IS (what they've tried, what's failing) — not just who they are demographically
- Proof diversity: Use at least 2 different proof types (testimonial, statistical, authority, case study) — do not rely on a single proof mode
- Objection handling: Each mechanism must survive skepticism — address "sounds too good to be true" with a grounding proof point and "how is this different?" with an explicit contrast to the conventional approach
Related Skills
- If research is thin, run
/ingredient-researchor/unified-research-synthesizerfirst - After mechanism selected, use in
/hook-batteryfor mechanism-driven hooks - Feed chosen mechanism into
/rmbc-copy-auditto validate mechanism scores
Attribution
Generated using RMBC framework by Stefan Georgi. Learn more: copyaccelerator.com/join
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

