offer-design
Build an offer from the buyer's obstacles: component stack, value drivers, an affordable guarantee and honest urgency, scored before launch
Install / Use
npx skills add borghei/Claude-Skills --skill offer-designInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Our assessment of offer-design
offer-design scores 89/100 on our quality scale, 1694th of 4,698 Development & Engineering skills we index (top 37%).
Its SKILL.md is 11 KB long, well organised into 25 sections with 2 code examples: a thorough specification that gives an agent plenty to work with.
It has 817 GitHub stars, a meaningful sign that others use it.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so offer-design is actively maintained.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-11-10. Automated pattern scan on 2026-11-10. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
offer-design compared with similar skills
All 4 of these similar skills score higher than offer-design; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| offer-design (this skill)by borghei | 89 | 817 | 56d ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 116.8k | 8d ago | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 72.1k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 47.3k | 2d ago | CLAUDE.md |
| Claude-Code-Game-Studiosby Donchitos | 100 | 39.7k | 7d ago | CLAUDE.md |
Frequently asked questions
- How do I install offer-design?
- Run
npx skills add borghei/Claude-Skills --skill offer-design. The install tabs above show the steps for each supported agent. - Which AI agents does offer-design work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is offer-design safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is offer-design still maintained?
- The repository was last updated about 2 months ago, so offer-design is actively maintained.
Skill content
View source on GitHubname: offer-design description: > Build an offer from the buyer's obstacles: component stack, value drivers, an affordable guarantee and honest urgency, scored before launch. Use when buyers say no, packaging bonuses, choosing a guarantee, or naming an offer. license: MIT + Commons Clause metadata: version: 1.0.0 author: borghei category: business-growth domain: offer-design updated: 2026-11-08 tags: [offer, value-proposition, guarantee, bonuses, conversion, packaging]
Offer Design
An offer is everything a buyer gets for the price, framed around the result they want. When good products do not sell, the usual cause is that buyers cannot see how the offer gets them past the obstacles they already expect. This skill builds the offer from those obstacles, scores its perceived value, checks that every component earns its cost, prices the guarantee into the contribution, and refuses fake urgency.
The agent works from the buyer's words: obstacles, objections and the result they want come from interviews, reviews or panel answers, not from the seller's feature list.
When to use this skill
- Buyers say no and the product is not obviously the problem
- Packaging a launch offer with bonuses, onboarding help or included extras
- Choosing a guarantee and checking the business can afford it
- Adding urgency without inventing scarcity
- Naming the offer by the outcome it delivers
- Comparing two offer versions before testing them with buyers
For setting the price point, tiers and value metric, use a pricing skill; this one designs what the price buys.
Inputs the skill expects
- Price and core delivery cost per sale
- The result the buyer wants, in their words
- The obstacles the buyer expects on the way to that result
- Candidate components, each with a buyer value and a delivery cost
- Proof available today (results, demonstrations, credentials)
- Refund history or a reasoned claim-rate estimate for any guarantee
- Any real constraint that could justify urgency (cohort dates, capacity)
Clarify First
The obstacle list shapes this output more than anything else: the offer is built to remove them. Settle the inputs below before producing anything. When one is missing or vague and would change the result, ask about it; when it wouldn't, use a sensible default and say which one you used.
- The obstacles, in the buyer's words: each one becomes a component; an obstacle invented by the seller produces a component nobody values.
- Delivery cost per component: decides what gets trimmed and whether the guarantee is affordable.
- What proof exists today: belief is the driver most new offers fail on, and the score must not credit proof that does not exist.
- Any real deadline or capacity limit: urgency is only added when a buyer could verify it.
Ask about the two or three inputs that matter most for this request, not the whole list. If the user wants a result straight away, produce it and state your assumptions at the top, marking estimated values and costs.
Quick Start
python3 business-growth/offer-design/scripts/offer_scorer.py \
--input business-growth/offer-design/assets/sample_offer.json
python3 business-growth/offer-design/scripts/offer_scorer.py \
--input business-growth/offer-design/assets/sample_offer_flawed.json --format json
Tools Overview
| Tool | Input | Output | Exit codes |
|------|-------|--------|------------|
| offer_scorer.py | Offer JSON | Value score 0-100, best lever, stack ratio, obstacle coverage, component efficiency, contribution after guarantee, findings | 0 no fail, 1 fail finding, 2 bad input |
Stdlib-only and deterministic, with --format text|json. The scoring formula is
printed in --help so every number can be checked by hand.
Workflows
Workflow 1 — Build the offer from obstacles
- Check the market first: pain, budget, reach and momentum
(
references/offer-construction.md, section 1). If two are weak, rework who the offer is for before designing anything. - Write the result the buyer wants in one sentence, in their words.
- List every obstacle between paying and getting that result: before, during and after. Pull them from interviews, reviews of alternatives or panel objections.
- For each obstacle, write the component that removes it, its buyer value and its delivery cost.
- Score the four value drivers from the buyer's point of view: outcome, belief, days to first result, effort.
Workflow 2 — Score, trim and strengthen
- Run the scorer. Every FAIL must be fixed before the offer is shown to buyers.
python3 business-growth/offer-design/scripts/offer_scorer.py --input offer.json
- Trim components that return under 3x their cost or answer no obstacle.
- Add components for unanswered obstacles, cheapest effective fix first.
- Follow the best lever the scorer names: raise belief with proof, or cut effort and time to the first result.
- Re-run until the stack is 3x price or more and coverage is complete.
Workflow 3 — Guarantee, urgency and name
- Pick the strongest guarantee type the contribution can afford, write exact terms, and enter an honest claim rate. The scorer subtracts expected claims from contribution and fails a guarantee that makes sales lose money.
- Add urgency only from a real constraint (cohort date, capacity cap, published deadline) and mark it verifiable. The scorer fails unverifiable urgency.
- Name the offer by outcome and timeframe, under twelve words.
- Fill
assets/offer-sheet-template.md.
Workflow 4 — Test with buyers
- Show the offer to buyers: a simulated panel to surface objections quickly, then a real priced test.
- Find the objection that still blocks the most buyers, change the one component that answers it, re-score and re-test.
- Change one thing per round so the result can be attributed.
Validation checkpoint before launch
Use this checklist; each item must pass:
- [ ] Scorer exits 0 (no FAIL findings)
- [ ] Every obstacle came from buyers, and each is answered
- [ ] Belief score is backed by at least two proof items
- [ ] Guarantee terms written, claim rate sourced
- [ ] Urgency, if any, is verifiable by a buyer
Decision frameworks
Which guarantee
| Situation | Guarantee | Confidence | |-----------|-----------|------------| | Results depend on the buyer's participation | Conditional (did the work, no result, refund) | [PROVEN] | | Low delivery cost, strong onboarding | Unconditional within a window | [RECOMMENDED] | | Measurable result with a delivery track record | Outcome guarantee | [RECOMMENDED] | | Heavy front-loaded delivery cost, high belief already | None, with proof instead | [RECOMMENDED] |
Which lever first
| Weakest signal | Lever | Why | |----------------|-------|-----| | Belief under 6 | [PROVEN] Proof and a guarantee | New businesses lose most buyers on "will this work for me" | | Effort 7+ or first result over 90 days | [RECOMMENDED] Done-for-you parts, a week-one win | Cheaper to fix than outcome size | | Stack under 3x price | [RECOMMENDED] Add obstacle-removing bonuses before cutting price | Price cuts invite matching; stack changes do not | | Coverage under 100% | Add a component per unanswered obstacle | An unanswered obstacle is a standing reason to say no |
Thresholds the scorer enforces
| Check | Warn | Fail | |-------|------|------| | Stack value / price | Under 3x | Under 1x | | Obstacle coverage | Any obstacle unanswered | Under 60% | | Component value / cost | Under 3x | — | | Contribution after guarantee | Under 20% of price | Zero or below | | Urgency | — | No reason, or not verifiable | | Belief without proof | 8+ with fewer than 2 proof items | — |
Anti-Patterns
The Feature Stack
Mistake: Listing everything the product does as bonuses, regardless of what the buyer worries about. Why it happens: The seller knows the features and assumes more equals better. Instead: Start from obstacles. A component that answers no obstacle reads as padding and lowers perceived value; the scorer flags it.
The Unaffordable Guarantee
Mistake: Offering a no-questions refund on a product with high delivery cost and weak onboarding. Why it happens: Strong guarantees lift conversion in case studies, and the claim rate is never estimated. Instead: Price the guarantee in: expected claims times price comes out of contribution. Pick a conditional guarantee when results depend on participation.
The Resetting Countdown
Mistake: Adding a deadline or "only a few left" that is not true. Why it happens: Urgency lifts short-term conversion, and the cost lands later. Instead: Use only constraints a buyer could check: cohort dates, capacity caps, published price changes. Fake scarcity breaks trust and can breach consumer-protection rules.
Competing on Price Alone
Mistake: Responding to "too expensive" by cutting the price. Why it happens: It is the fastest change and the objection names price. Instead: First raise belief, cut effort and add obstacle-removing components; re-test at the same or a higher price. "Too expensive" often means "not sure it will work for me".
Belief Scored on Hope
Mistake: Rating belief 8-9 because the founder is confident. Why it happens: The seller scores from their own view rather than the buyer's. Instead: Score belief from the buyer's side and back anything above 7 with proof. The scorer warns when the score is not earned.
Reference Documentation
references/offer-construction.md— market check, the four value drivers, building from obstacles, guarantee types and affordability, honest urgency, naming, testing, and offer versus price
Files
| File | Purpose |
|------|---------|
| scripts/offer_scorer.py | Scores value, stack, coverage, efficiency, guarantee cost and urgency |
| references/offer-construction.md | The method behind the scorer |
| assets/sample_offer.json | Sound example: beginner bouldering course (exit 0) |
| assets/sample_offer_flawed.json | Deliberately flawed example: online course with fake urgency (exit 1) |
| assets/offer-sheet-template.md | One-page offer sheet to fill after scoring |
Scope & Limitations
In Scope:
- Building an offer from buyer obstacles and scoring it with
offer_scorer.py - Value-driver scoring, component trimming, stack ratio and obstacle coverage
- Guarantee choice with expected claim cost priced into contribution
- Honest urgency and outcome-led naming
Out of Scope:
- Setting the price point, tiers or value metric
- Writing ad copy, landing pages or sales emails
- Running the buyer tests themselves
- Legal review of guarantee or refund terms
Important Caveats:
- Buyer values and driver scores are judgements. The tool makes them explicit and consistent; it does not make them true. Validate with real buyers.
- The value score is a comparison aid between versions of one offer, not a benchmark across businesses.
- Refund and urgency rules vary by market. Have guarantee terms and any deadline or scarcity claims checked against local consumer-protection law.
Related Skills
taste-skill
116.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
72.1kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
47.3kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
Claude-Code-Game-Studios
39.7kTurn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
