Continuous Discovery
Habits for continuous product discovery
Build continuous discovery habits into your product team using Teresa Torres's structured approach. This skill equips your AI agent with opportunity solution trees, interview techniques, and assumption testing methods that keep product decisions grounded in customer evidence.
Continuous Discovery Habits
npx skills add wondelai/skills/continuous-discovery --global This skill is compatible with Claude, Claude Code, Claude Cowork, Codex, Cursor, OpenClaw, Hermes Agent, and other agentskills.io-compatible agents.
What is the Continuous Discovery skill?
Continuous Discovery installs Teresa Torres’s Continuous Discovery Habits as a practice your agent can actually run — an opportunity solution tree from outcome down through opportunities, solutions and assumption tests, a weekly interview cadence instead of research campaigns, and experiments sized to the risk rather than to the calendar.
Key concepts from Continuous Discovery Habits your agent applies
Opportunity Solution Trees
Map the path from desired outcome to opportunities to solutions to experiments — visualize your entire discovery process.
Weekly Customer Interviews
Talk to customers every week, not just during research sprints. Build continuous feedback into your team's rhythm.
Assumption Mapping
Identify desirability, viability, feasibility, and usability assumptions. Test the riskiest ones first.
Compare & Contrast
Always generate at least three solutions before picking one — comparison leads to better decisions than evaluation.
Small Experiments
Test assumptions with the smallest possible experiment — prototype tests, one-door/two-door decisions, and concierge tests.
When to use Continuous Discovery — and when not to
Reach for it when
- Your team researches in bursts before big launches and then flies blind for the six months in between.
- The roadmap is a list of solutions with no visible link to the outcome anyone is actually accountable for.
- Someone senior floats a feature and it gets built, because there is no structure for comparing it against alternatives.
- You do interview customers, but the notes live in a document nobody opens on the day the decision gets made.
Reach for something else when
- One high-stakes question needs answering this week with everyone in a room — Design Sprint is the right container.
- The unresolved question is which outcome to chase at all — Good Strategy Bad Strategy forces the diagnosis first.
- Your interviews still come back full of compliments — fix the technique with The Mom Test before scaling the cadence.
- The company treats the team as a feature factory and no cadence survives that — Inspired takes on the structural problem.
Example prompts for the Continuous Discovery skill
Build an opportunity solution tree for our user onboarding outcome using continuous-discovery skill
Product discoveryCreate an interview guide for understanding our users' biggest pain points using continuous-discovery skill
Customer researchMap and prioritize assumptions for this new feature idea using continuous-discovery skill
Assumption testingDesign three different solutions for this opportunity and help me compare them using continuous-discovery skill
Solution designContinuous Discovery vs the other Product & Innovation skills
All 10 Product & Innovation skills are free and install the same way — the only question is which framework fits the job in front of you.
| Skill | Based on | Best for |
|---|---|---|
| Jobs to Be Done | Competing Against Luck — Clayton Christensen | JTBD framework for product innovation |
| Hooked UX | Hooked — Nir Eyal | Habit-forming product design |
| Improve Retention | Tiny Habits — BJ Fogg | Behavior design for user retention using B=MAP |
| Lean Startup | The Lean Startup — Eric Ries | Build-Measure-Learn methodology |
| Design Sprint | Sprint — Jake Knapp | 5-day process for validating ideas through prototyping |
| Continuous Discovery | Continuous Discovery Habits — Teresa Torres | Habits for continuous product discovery |
| Inspired | Inspired — Marty Cagan | Building products customers love |
| The Mom Test | The Mom Test — Rob Fitzpatrick | Customer conversations that reveal the truth |
| The 37signals Way | Shape Up — Jason Fried & DHH | Lean, opinionated product development from Getting Real to Shape Up |
| Lean Analytics | Lean Analytics — Alistair Croll & Benjamin Yoskovitz | Startup metrics and the One Metric That Matters |
Frequently asked questions
How do I install the Continuous Discovery skill?
Run npx skills add wondelai/skills/continuous-discovery --global. It takes about 30 seconds and needs no account. The Continuous Discovery skill then works in Claude, Claude Code, Claude Cowork, Codex, Cursor, OpenClaw and Hermes Agent — anything that reads the open agentskills.io format — and your agent loads it on its own when a task calls for it. It is free and MIT-licensed, and the source is at https://github.com/wondelai/skills.
Which book is the Continuous Discovery skill based on?
It packages Continuous Discovery Habits by Teresa Torres — product discovery coach, creator of the Opportunity Solution Tree. The skill distils the book's method into instructions your agent follows while it works, covering opportunity solution trees, weekly customer interviews and assumption mapping. It sits in the Product & Innovation part of the library.
How is this different from the Jobs to Be Done skill?
JTBD is a theory about why people buy; Continuous Discovery is an operating rhythm for a team. Torres’s contribution is structural — the opportunity solution tree, weekly touchpoints, the product trio of manager, designer and engineer doing discovery together — and it is deliberately agnostic about which theory of customer need you populate it with. You can hang JTBD-shaped opportunities on a Torres tree quite happily. What she adds is the discipline that keeps discovery alive through a quarter when everyone is busy.
What is an opportunity solution tree, exactly?
Four levels. At the top, one desired outcome the team is accountable for. Beneath it, opportunities — unmet needs, pain points and desires in the customer’s own words, never solutions in disguise. Beneath each of those, at least three candidate solutions. Beneath those, the assumption tests that would tell you whether a solution works. Its real job is to make reasoning visible: anyone can trace which opportunity a feature serves and which outcome that opportunity moves, so requests that map nowhere can be declined for a reason rather than by seniority.
Why insist on three solutions before choosing one?
Because evaluating a single idea turns into arguing for or against it, and the person who brought it defends it. Put three on the table and the question changes from whether to which, which is a conversation about trade-offs rather than egos. Torres calls this compare and contrast, and it is the cheapest quality improvement in the book — it costs an hour and routinely surfaces an option better than the one everybody arrived with.
What if I cannot get an interview every week?
The habit degrades gracefully, but not infinitely. Fortnightly still works; quarterly is research, not discovery, and the tree goes stale between rounds. If access is the real blocker — enterprise gatekeeping, a slow recruiting pipeline — say so in the prompt and the skill will lean harder on evidence you can gather without a live customer: unmoderated tests, support-ticket mining, one-question in-product surveys, sales-call recordings. It will not pretend those are equivalent to talking to someone.
Guides that use this skill
Install Continuous Discovery
Free, open-source, and ready in 30 seconds.
npx skills add wondelai/skills/continuous-discovery --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.
Sprints from $3K · shipped to production, or you don’t pay the final milestone.