agentsclimarketplace

Discovery playbook

Skill eltntawy/idea-discovery-playbook/skills/discovery-playbook

16 agent skills to validate software ideas before you build — Mom Test interviews, JTBD, market research, pretotype tests, unit economics, and go/no-go scorecards. For Cursor, Claude Code & skills.sh.

Install
npx -y skills add eltntawy/idea-discovery-playbook --skill discovery-playbook

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Orchestrates end-to-end software idea discovery and validation—stage gates, skill routing, artifact filenames, and kill checkpoints from assumption map through scorecard. Use when validating an idea end-to-end, asking what to do next in discovery, or starting a new topic research folder.

SKILL.md

5.8 KB, as published. Nobody here has run it

Discovery Playbook

Repository: idea-discovery-playbooknpx skills add eltntawy/idea-discovery-playbook -g -y

Start here for full idea validation. Invoke one child skill per stage; do not skip gates without user consent.

Validation phases

PhaseQuestionExit gate
0 — FrameWhat are we testing?Topic folder + assumption-map with top assumptions; regulatory-risk-scan if regulated
1 — IdeaIs the problem real?problem-discovery passed (kill criteria not met); or pivot segment
2 — MarketIs there a wedge and room?market-research + competitor-landscape; economics sketch OK
3 — EconomicsCan it pay?market-sizing, revenue-model, positioning-wedge
4 — FeasibilityCan we ship and win?feasibility-gate — not Reject
5 — Demand testWill they act/pay?validation-experiments — fail threshold not hit
6 — DecisionBuild, wait, or kill?idea-scorecard — Strong or Conditional go only for build
7 — SynthesisOne pack for stakeholdersdiscovery-synthesis

Product validation (after prototype): pmf-sean-ellis — not part of pre-build gates.

Skill router

User needSkill
Riskiest assumptions, test queueassumption-map
Mom Test interviewsproblem-discovery
Why buyers switch / JTBDjtbd-interviews
Live market + gap memomarket-research
Full competitor memocompetitor-landscape
TAM / SAM / SOMmarket-sizing
Category and positioningpositioning-wedge
Pricing and LTV:CACrevenue-model
Build / wait / reject feasibilityfeasibility-gate
Smoke test, fake door, conciergevalidation-experiments
End-to-end behavior memobehavior-led-validation
Weighted go/no-goidea-scorecard
Single researcher reportdiscovery-synthesis
Regulated domainregulatory-risk-scan

First run (workspace bootstrap)

If discovery/ is missing:

  1. Create discovery/INDEX.md listing active topic slugs, status, opened date, and last decision (see example below).
  2. Create discovery/<topic-slug>/ with TOPIC.md from problem-discoveryTOPIC-TEMPLATE.md.
  3. Create subfolders: briefs/, research/, experiments/, scorecards/.

INDEX.md example:

# Discovery index

## Active

| Slug | Status | Opened | Last decision |
| --- | --- | --- | --- |
| <slug> | active | YYYY-MM-DD | In progress |

## Archived

(none)

Artifact filenames (per topic)

KindPath pattern
Topic indexdiscovery/<slug>/TOPIC.md
Brief / interviewsbriefs/YYYY-MM-DD-<slug>-brief.md
Market memoresearch/YYYY-MM-DD-<slug>-market.md
Market sizingresearch/YYYY-MM-DD-<slug>-market-sizing.md (or section in -market.md)
Competitorsresearch/YYYY-MM-DD-<slug>-competitors.md
Revenueresearch/YYYY-MM-DD-<slug>-revenue.md
Positioningresearch/YYYY-MM-DD-<slug>-positioning.md
Feasibilityresearch/YYYY-MM-DD-<slug>-feasibility.md
Assumptionsresearch/YYYY-MM-DD-<slug>-assumptions.md
Experimentsexperiments/YYYY-MM-DD-<slug>-experiment.md
JTBDbriefs/YYYY-MM-DD-<slug>-jtbd.md
Regulatoryresearch/YYYY-MM-DD-<slug>-regulatory.md
Scorecardscorecards/YYYY-MM-DD-<slug>-scorecard.md
SynthesisYYYY-MM-DD-<slug>-synthesis.md (topic root or research/)
PMF (post-build)research/YYYY-MM-DD-<slug>-pmf.md

Default memo sections

Facts, Assumptions, Evidence, Analysis, Decision, Next experiment.

Build gate

No production implementation until idea-scorecard = Strong go or Conditional go with named gaps.

Related skills (external)

Optional complements — install separately:

  • npx skills add ferdinandobons/startup-skill — full strategy, pitch
  • npx skills add brandonsgitstub/jtbd-skill — JTBD docx workflow
  • npx skills add EmersonBraun/skills --skill brainstorm — divergent ideation

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.