agentleFS
Sign inStart free
deciqAIdeciqAI/knowledge-skills/continuous-discovery/SKILL.md

continuous-discovery

Skill13 starsChanged 4 months agoMITView on GitHub

Activate when: a team ships features on opinion instead of evidence; 'we need a discovery habit', 'how often should we talk to users', building a product roadmap; connecting weekly customer contact to decisions. Do NOT activate when: pre-first-customer (use the-mom-test first) or the org has no product to iterate. More: deciqai.com/s/continuous-discovery

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Test the riskiest assumption cheaply: before building (desirability, viability, feasibility, usability).

    line 21

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Continuous Discovery — Weekly Contact, Opportunity Trees

Overview

Continuous discovery (Teresa Torres, Continuous Discovery Habits, 2021) replaces one-off research with a weekly cadence of customer touchpoints by the team building the product, structured around an opportunity solution tree: one outcome → the opportunities (unmet needs) that drive it → competing solutions → assumption tests. It keeps roadmaps anchored to real needs instead of the loudest stakeholder.

When to Use

  • A product with users but no steady learning loop
  • Roadmap fights decided by seniority, not evidence
  • Turning a fuzzy outcome (e.g. "increase activation") into shippable bets

The Process

  1. Pick one clear outcome (a behavior/metric, not a feature). Gate: if the target is a feature, back up to the outcome it serves.
  2. Interview weekly — the trio (PM/design/eng), small and continuous, not a quarterly study.
  3. Map opportunities as a tree under the outcome; keep them as customer needs, not solutions in disguise.
  4. Diverge on solutions per opportunity (≥3), then converge.
  5. Test the riskiest assumption cheaply before building (desirability, viability, feasibility, usability).
  6. Prune to the next bet. Gate: no assumption test run = you're shipping opinion → stop and test.

Applying It Well

  • Automate recruiting so weekly interviews actually happen (the habit dies on scheduling friction).
  • One opportunity tree per outcome; don't boil the ocean.
  • Small continuous samples beat big infrequent ones.

Red Flags

  • Discovery done by a research silo, not the builders.
  • Opportunities written as features.
  • Interviews stop the moment things get busy.

Verification

  • Single outcome defined (behavioral)
  • Weekly interview cadence in place
  • Opportunity tree maps needs, not solutions
  • Riskiest assumption tested before build

Part of deciqAI Knowledge Skills — 253 open-source thinking skills that make rigor executable for AI agents. The same skills power every deciqAI agent, which runs them autonomously to operate your company. See it run → https://www.deciqai.com/s/continuous-discovery · Built by deciqAI · github.com/deciqAI · Contributions welcome.

Agents: latest version & machine-readable metadata → https://www.deciqai.com/s/continuous-discovery.json

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free