Make every
AI prompt
an expert move.
51 frameworks from bestselling business & engineering books — StoryBrand, JTBD, $100M Offers, Clean Code, and 47 more — packaged as skills for Claude, Claude Code, Claude Cowork, Codex, Cursor, OpenClaw, and Hermes Agent. Plus 14 guided journeys that run them end to end. Free and open-source.
1,956 stars on GitHubFor developers and founders who want proven business thinking baked into every AI prompt.
You ship fast.
But you ship without frameworks.
The knowledge gap
You know StoryBrand, JTBD, and Blue Ocean exist. But who has time to reread 51 books before every product sprint?
The nagging doubt
That feeling when your positioning is "good enough" — and you know good enough means forgettable.
Locked-up expertise
The best business thinking in the world is trapped in books. It should be available at the point of decision.
“Winging it” is the most expensive strategy in business.
Same prompt. Different universe.
You: “Help me position our product”
AI: Here are some tips for product positioning:
1. Identify your target audience
2. Research your competitors
3. Define your unique value proposition
4. Create a positioning statement
5. Test with customers
Remember to focus on what makes you unique...
You: “Help me position our product. Use obviously-awesome skill.”
AI: Applying April Dunford's positioning framework.
Step 1 — Competitive Alternatives
What would customers do if you didn't exist?
→ Spreadsheets + manual processes
→ [Competitor] + custom workarounds
Step 2 — Unique Attributes
What can you deliver that alternatives can't?
→ Real-time collaboration on frameworks
→ AI-powered analysis from 51 methodologies
Step 3 — Value for Customers
→ “Ship positioning decisions in hours, not weeks”
Step 4 — Target Segment
→ B2B SaaS teams, Series A-B, 10-50 people
who lack a dedicated strategist...
That's one skill. You get all 51.
Real prompts. Copy-pasteable.
Help me uncover the real Job to Be Done for our product. Who are the hiring managers and what competing "hires" should I worry about?
Use jobs-to-be-done skill. Design a Grand Slam Offer with bonuses, a risk-reversing guarantee, and ethical urgency for our SaaS.
Use hundred-million-offers skill. Score our pitch on the SUCCESs checklist. Rewrite it so the core message passes the Commander's Intent test.
Use made-to-stick skill. Build a Strategy Canvas of our top 6 competitors, then apply the Four Actions Framework to find a blue ocean move.
Use blue-ocean-strategy skill. Run a full CRO audit: top 5 visitor objections, missing persuasion assets, and which of Cialdini's 7 principles are absent.
Use cro-methodology and influence-psychology skills. Walk me through the full StoryBrand brand script: hero, problem, guide, plan, CTA, success vs. failure.
Use storybrand-messaging skill. Design a complete scorecard funnel: quiz title, 12 questions, scoring logic, and 3 result tiers with tailored CTAs.
Use scorecard-marketing skill. Apply Nielsen's 10 heuristics and Norman's framework to audit our dashboard. Rate each violation 0-4 severity.
Use ux-heuristics and design-everyday-things skills. Diagnose onboarding drop-off using B=MAP. Then map each step to the Hook Model cycle.
Use improve-retention and hooked-ux skills. Create a Vision/Traction Organizer with our 10-year target, 3-year picture, and 1-year plan. Then audit our incentive structure for Autonomy-Mastery-Purpose.
Use traction-eos and drive-motivation skills. Write responses to our top 3 objections using tactical empathy: labels, calibrated questions, and "That's right" moments.
Use negotiation and influence-psychology skills. Design a Cold Calling 2.0 outbound process: ideal customer profile, 3-email sequence, lead qualification, and pipeline math.
Use predictable-revenue skill. Design a launch strategy with a STEPPS-based referral mechanic and a 1-page marketing plan for $0 budget.
Use contagious and one-page-marketing skills. Build a Build-Measure-Learn experiment card and a 5-day sprint plan to go from sketches to testable prototype.
Use lean-startup and design-sprint skills. Audit our typography for readability. Then apply Refactoring UI hierarchy principles and deliver updated CSS.
Use web-typography and refactoring-ui skills. Design a homepage that would score on Awwwards: type system, hero composition, scroll reveals, and micro-interactions.
Use top-design skill. Check our iOS app against HIG: navigation patterns, 44pt touch targets, Dynamic Island, and safe areas.
Use ios-hig-design skill. Are we ready for pragmatist buyers? Map our product against the whole product model and identify a beachhead segment.
Use crossing-the-chasm skill. Pick one. Pick all. They're free.
Every framework installs as a standalone skill. Mix and match for your workflow.
Design & UX 9 All Design & UX →
Marketing & Messaging 6 All Marketing & Messaging →
Sales & Persuasion 6 All Sales & Persuasion →
Product & Innovation 10 All Product & Innovation →
Strategy & Growth 4 All Strategy & Growth →
Team & Operations 4 All Team & Operations →
Code Quality 6 All Code Quality →
Architecture & Systems 6 All Architecture & Systems →
No skills match “”. Try a skill name, book title, or author.
Install in 30 seconds. Use forever.
Install the full library
One command. 51 frameworks. No configuration needed.
npx skills add wondelai/skills --all --global Or pick just what you need
Only want positioning? Just JTBD? Install individual skills.
npx skills add wondelai/skills/obviously-awesome --global Prompt like you read the book
Your agent picks up a skill on its own when a task matches it. To call one explicitly, add "Use [skill-name] skill." to the prompt.
"Redesign our pricing page. Use hundred-million-offers skill." These skills are compatible with Claude, Claude Code, Claude Cowork, Codex, Cursor, OpenClaw, Hermes Agent, and other agentskills.io-compatible agents.
Install nothing.
Ask the library instead.
One URL turns all 65 skills into something your agent can query mid‑task. Describe the job in plain words; get back which frameworks to load, which to skip, and the skill’s own reason for each. Read‑only, no account, no auth.
claude mcp add --transport http wondel-skills https://skills.wondel.ai/mcp recommend_skills
task: “our landing page gets traffic but nobody signs up”
routed against 65 skills
- load cro-methodology Traffic is healthy, the funnel leaks, and nobody can say at which step or for what reason.
- load influence-psychology Your homepage shows testimonials and a logo bar but nothing that tells a stranger why credible people trust you.
- skip one-page-marketing not for: One square is the entire problem — go straight to the specialist, like Scorecard Marketing for lead capture.
A real response shape. The reasons are each skill’s own words — the part keyword search cannot reproduce.
5 tools, every one read‑only and annotated as such — so a client can call them without stopping to ask you first.
- 01
search_skills(query, kind?, category?, limit?) Search skills - 02
recommend_skills(task, stack?, phase?, max?) Recommend skills for a task start here - 03
get_skill(slug, sections?) Get skill metadata - 04
load_skill(slug, part?) Load skill instructions - 05
get_journey(slug? | goal?) Get a guided journey
Skills are free.
Mastery is the multiplier.
The Developer Toolkit shows you how to get more out of every skill — from choosing the right one for each task to writing custom skills your whole team can share.
Learn the skills ecosystem
Structured tutorials on Cursor, Claude Code & Codex. Understand how skills work under the hood — from installation to context injection.
Recipes for real projects
80+ ready-to-use workflows for real projects. Know exactly which skill to reach for — and how to chain them for complex tasks.
Create your own skills
Build custom skills for your team’s domain expertise. Ship institutional knowledge as markdown files your AI agents load every session.
From $19.99/mo · Updated weekly · By the creators of Wondel.ai Skills
What is an AI agent skill?
An AI agent skill is a folder of instructions — a SKILL.md plus any scripts it needs — that your coding agent loads on demand, the moment a task calls for it. Wondel.ai Skills packages 51 frameworks from bestselling business and engineering books this way, so your agent applies a proven method instead of improvising.
Each one distils a bestselling book into a method your agent can follow — 51 skills across strategy, marketing, product, design, code and architecture, plus 14 guided journeys that run whole projects phase by phase. Browse the full library.
How do I install Wondel.ai Skills?
Run `npx skills add wondelai/skills --all --global` to install all 51 skills, or `npx skills add wondelai/skills/<slug> --global` for a single one — for example `npx skills add wondelai/skills/clean-code --global`. Installation takes about 30 seconds and needs no account.
Which AI agents do these skills work with?
They are built on the open agentskills.io standard, so they work in Claude, Claude Code, Claude Cowork, Codex, Cursor, OpenClaw and Hermes Agent — and in any other agent that reads the same format. Nothing here is locked to one vendor.
Are the skills free?
Yes. All 51 skills and 14 guided journeys are free and MIT-licensed, published at https://github.com/wondelai/skills. You can read, fork, and adapt every one of them.
What is a guided journey, and how is it different from a skill?
A skill applies one framework. A guided journey — a metaskill — sequences eight to eleven of them into a whole job, asking one decision question per phase and writing the answer to a file you keep. There are 14 journeys, covering creating, improving, and growing a business, website, or app, plus three engineering tracks.
Who builds and maintains these skills?
Wondel.ai — a small team led by Michał Jaskólski, who previously built and sold two companies and shipped consumer products to over four million monthly users. The library covers 8 domains and is developed in the open at https://github.com/wondelai/skills.
Don’t just install skills.
Ship outcomes.
Long-form playbooks on a simple grid — create, improve, or grow a business, website, or app — each stacking the exact skills for the job, with copy-paste prompts.
You could keep prompting from scratch every time.
Or let 50 authors
do the thinking.
npx skills add wondelai/skills --all --global MIT Licensed · Works with Claude, Claude Code, Claude Cowork, Codex, Cursor, OpenClaw, Hermes Agent & other agentskills.io agents · No account needed
Don’t guess your AI engineering level.
Measure it.
AI Developer Scorecard
How production-grade is your AI engineering?
Twenty-five questions across the practices that separate vibe-coding from production-grade engineering. Instant score, per-section breakdown, and a 30/60/90-day playbook.
Score 0–75 · 30/60/90-day playbook Score yourself For CTOs & foundersCTO Scorecard
Is your engineering team ready for AI at scale?
Twenty-five questions on how your org adopts AI — adoption, governance, automation, and ROI. See where you sit on the path from Reactive to Strategic Leader.
Score 0–75 · Reactive → Strategic Leader Score your orgWe build the skills you already use. Now we’ll build yours.
Fixed-price engagements, quoted after a 15-minute call. Shipped to production, or you don't pay the final milestone.
Frameworks from the authors who wrote the rules.
Every skill is distilled from actual book methodologies — not summaries, not vibes. Structured frameworks your AI can follow step by step — and 14 guided journeys that run them in the right order.