- name
SKILL.md
Le fichier du skill reste dans le dépôt de l'éditeur.
Collez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add wondelai/skills --skill continuous-discovery -a cursor -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add wondelai/skills --skill continuous-discovery -a claude-code -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add wondelai/skills --skill continuous-discovery -a codex -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add wondelai/skills --skill continuous-discovery -a grok -yEnvoyez le message copié dans un chat Grok Bot. Le Bot récupère ce SKILL.md sur GitHub et l'ajoute aux skills que partagent tous vos Bots.
Install this skill: https://github.com/wondelai/skills/tree/HEAD/continuous-discoveryDe l'éditeur
Framework for building a sustainable weekly practice of customer discovery that keeps product teams progressing toward desired outcomes. Discovery is not a phase before development — it is embedded in the ongoing rhythm of product work so every decision is informed by fresh evidence.
Good product discovery requires a continuous cadence, not a one-time event. Teams that talk to customers every week, map opportunities visually, and test assumptions before building consistently outperform teams that rely on intuition, stakeholder opinions, or quarterly research cycles. The benchmark: at least one customer touchpoint per week, every week, by the product trio (product manager, designer, engineer).
Goal: 10/10. Score a discovery practice by the seven Quick Diagnostic rows below — start at 3, add 1 point per row answered "yes" (max 10). Bands: 9-10 = weekly cadence, a living Opportunity Solution Tree, systematic assumption testing, and every shipped feature traceable to a customer opportunity; 5-6 = some discovery happening but ad hoc, PM-only, or disconnected from delivery; ≤3 = intuition- and stakeholder-driven with no regular customer contact. Report the current score, the failing rows, and the specific fix for each.
Core concept: An Opportunity Solution Tree (OST) visually connects a desired outcome (top) to customer opportunities (middle) to potential solutions and experiments (bottom), making implicit product thinking explicit and shared.
Why it works: Most teams jump from business outcome straight to solutions, skipping the customer need entirely; the OST forces understanding of the opportunity space first, preventing features nobody wants.
Key insights:
Product applications:
Ethical boundary: Never cherry-pick opportunities to justify a predetermined solution — the tree must reflect needs discovered through research.
See references/opportunity-trees.md when building or auditing a tree — adds the 4-layer diagram, good-vs-poor outcome tables, solution-generation techniques, a weekly update rhythm, healthy/dying-tree signals, two worked examples, and four anti-patterns.
Core concept: Current-state experience maps capture how customers accomplish a goal today, step by step, revealing pain points that become opportunities on the tree.
Why it works: Teams assume they understand the customer's current experience; mapping it from interview data exposes gaps, workarounds, and emotions invisible from inside the building.
Key insights:
Product applications:
See references/experience-mapping.md when mapping a new problem space or churn flow — adds the current-state map template, the experience-vs-journey-map distinction, and the collaborative mapping exercise.
Core concept: Story-based interviews capture specific past experiences (not opinions or predictions), and each interview is synthesized into a one-page snapshot the whole team can absorb and reference.
Why it works: Customers are poor predictors of their own future behavior; grounding insights in real past events reveals what they actually did and felt, and snapshots turn each interview into a growing library of evidence.
Key insights:
Product applications:
Ethical boundary: Never lead participants toward conclusions — ask open-ended questions about past behavior and let the story reveal what matters.
See references/interview-snapshots.md when running interviews or setting up recruitment — adds story-based interview structure, the one-page snapshot format, synthesis across snapshots, and how to automate weekly recruitment.
Core concept: Before building, identify the assumptions a solution depends on, map them by importance and evidence, then run small fast tests on the riskiest ones first.
Why it works: Every solution sits on a stack of desirability, viability, feasibility, and usability assumptions; most teams test none — or only the easy ones — and invest months in solutions built on false premises.
Key insights:
Product applications:
Ethical boundary: Never deceive participants — painted-door tests should say the feature is coming soon, not fake functionality without disclosure.
See references/assumption-mapping.md when designing a test for a risky assumption — adds the four assumption types in depth, the importance-vs-evidence 2x2, the test-design menu, and how to set success criteria for leap-of-faith assumptions.
Core concept: Compare opportunities against each other — not in isolation — using opportunity size, market, company, and customer factors to find the highest-leverage bets.
Why it works: Teams default to the loudest stakeholder, recency bias, or gut feel; structured head-to-head comparison forces explicit tradeoff discussions and surfaces disagreements before implementation.
Key insights:
Product applications:
See references/prioritization-methods.md when ranking your top opportunities — adds the opportunity-sizing method, the compare-and-contrast technique, how to weigh data, and how to avoid analysis paralysis.
Core concept: Continuous discovery only works as a sustainable weekly habit for the trio — automate recruitment, create lightweight rituals, and embed discovery into the existing workflow rather than treating it as extra work.
Why it works: Discovery that depends on "finding time" loses to delivery pressure every week; structural support (automated recruitment, standing slots, shared artifacts) removes the per-week decision so the habit survives and compounds.
Key insights:
Product applications:
Ethical boundary: Respect participant time — keep interviews to 30 minutes, compensate fairly, and never disguise a sales pitch as discovery.
See references/case-studies.md when adapting the habit to your context — worked walkthroughs of continuous discovery in B2B SaaS, consumer mobile, platform, and growth teams.
Based on the continuous discovery framework developed by Teresa Torres:
Teresa Torres is an author, speaker, and coach who has helped hundreds of product teams — from startups to Capital One and Calendly — adopt continuous discovery. She created the Opportunity Solution Tree, writes the widely read Product Talk blog, and distilled her coaching practice into Continuous Discovery Habits.
Build a weekly cadence of customer touchpoints using Opportunity Solution Trees, assumption mapping, and interview snapshots. Use when the user mentions "continuous discovery", "opportunity solution t
---name: continuous-discoverydescription: Build a weekly cadence of customer touchpoints using Opportunity Solution Trees, assumption mapping, and…---# continuous-discovery/SKILL.mdVue d'ensemble
Build a weekly cadence of customer touchpoints using Opportunity Solution Trees, assumption mapping, and interview snapshots. Use when the user mentions "continuous discovery", "opportunity solution tree", "weekly interviews", "assumption testing", "discovery habits", "product trio", "outcome-based roadmap", "how do I talk to customers regularly", "we keep building things nobody uses", or "connect research to the roadmap". Also trigger when setting up regular customer feedback loops, prioritizing which experiments to run, or tying discovery insights to delivery work. Covers experience mapping, co-creation, and prioritizing opportunities. For interview technique, see mom-test. For team structure, see inspired-product.
FAQ
Téléchargez continuous-discovery/SKILL.md auprès de l'éditeur, ou copiez le chemin et ouvrez le dépôt. PlugMCP répertorie le skill et n'héberge pas le fichier.
L'éditeur le maintient sur https://github.com/wondelai/skills.
Claude, Cursor, Codex et Grok Build peuvent lire un SKILL.md que vous ajoutez depuis le dépôt de l'éditeur. Grok Bot l'installe lorsque vous envoyez dans un chat le lien du dossier GitHub du skill.