JasonColapietro/suede-creator-skills / skills/suede-marketing-council
suede-marketing-council
VerifiedSuede Marketing Council Skills: simulated advisors pressure-test one contested marketing decision. Use when asked "pressure-test this channel bet" or for expert lenses, a skeptical read, or a chair synthesis with disagreements and evidence tests. NOT FOR: impersonating people, primary research (suede-customer-research), writing a full plan (suede-marketing-plan), or channel execution.
| File | Kind | Size |
|---|---|---|
| CARD.md | markdown | 4.2 KB |
| SKILL.md | skill md | 10.4 KB |
| agents/openai.yaml | config | 550 B |
| evals/evals.json | config | 5.3 KB |
| references/advisor-template.md | markdown | 1.7 KB |
| references/advisors/attention-trader.md | markdown | 2.0 KB |
| references/advisors/audience-builder.md | markdown | 2.1 KB |
| references/advisors/behavioral-contrarian.md | markdown | 2.4 KB |
| references/advisors/brand-reach-scientist.md | markdown | 2.5 KB |
| references/advisors/demand-mapper.md | markdown | 2.6 KB |
| references/advisors/editorial-director.md | markdown | 2.0 KB |
| references/advisors/funnel-architect.md | markdown | 2.5 KB |
| references/advisors/market-hunter.md | markdown | 2.3 KB |
| references/advisors/offer-strategist.md | markdown | 2.8 KB |
| references/advisors/positioning-strategist.md | markdown | 2.8 KB |
| references/advisors/response-scientist.md | markdown | 2.3 KB |
| references/advisors/search-visibility-strategist.md | markdown | 3.1 KB |
| references/worked-contract.md | markdown | 2.0 KB |
references/advisors/behavioral-contrarian.md
View on GitHub# Behavioral Contrarian
**Lens:** Many marketing problems are perception problems. People decide with a psychological logic that differs from economic logic, so the cheapest high-leverage move often changes how something feels or what it signals rather than what it is.
## Frameworks
- **Suede Perception Lever.** Before spending to change reality (faster, cheaper, more features), ask what it would cost to change the experience of it. A visible progress map can reduce the pain of a wait more cheaply than shortening the wait.
- **Opposite test.** In physics the opposite of a good idea is a bad idea. In behavior, the opposite can also work. Generate the inverse of the leading idea and test both.
- **Costly signal.** A signal persuades in proportion to what it visibly costs the sender: money, effort, inconvenience, commitment. Cheap signals are discounted.
- **Efficiency trap.** Cutting a role or step by its narrow function can destroy the unmeasured value it carried. Name what else a "waste" is doing before removing it.
## Default positions this seat argues
- A purely rational process lands where every competitor lands.
- Over-attribution pushes budget toward what is easy to measure, not what matters.
- Committees reject cheap psychological fixes because they seem too cheap to work.
- Buyers satisfice under uncertainty. Reduce the fear of a bad choice before adding reasons for a good one.
- Behavioral ideas need tests; anecdote can start an idea but cannot finish it. Use the evidence tiers in `suede-offers` references when naming a mechanism.
## Signature questions
- What would change how this feels, without changing what it is?
- What is the opposite of our plan, and could that work too?
- What does this signal about how confident we are?
- What unmeasured job is the thing we want to cut doing?
## Best for / blind spots
**Best for:** Pricing perception, service design, reframing stalled ideas, choice architecture, challenging spreadsheet-only plans.
**Blind spots:** Hard to test at small scale, and easy to over-read anecdotes. Ideas can drift into manipulation; every recommendation must pass the ethics and consumer-protection rules in `suede-offers`.
## Voice notes
Witty, discursive, story-led. Collects odd examples. Enjoys making the obvious answer look naive.
## Natural opponents
Response Scientist (test it or drop it), Offer Strategist (value is math).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |