agentsclimarketplace

Discovery synthesis

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

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-synthesis

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

Compiles discovery artifacts into one researcher or stakeholder pack—executive summary, evidence table, open assumptions, economics, decision, and next tests. Use when summarizing validation, writing a discovery report, or packaging idea research for review.

SKILL.md

1.7 KB, as published. Nobody here has run it

Discovery Synthesis

Merge existing work under discovery/<topic-slug>/ into one readable pack. Do not invent evidence — cite artifacts and URLs.

Inputs (read in order)

  1. discovery/INDEX.md and TOPIC.md
  2. Latest briefs/, research/, experiments/, scorecards/
  3. assumption-map ledger if present

Workflow

  1. Executive summary — hypothesis, decision, one-line why (3–5 sentences).
  2. Evidence table — claim | source artifact | tier (1–5) | confidence.
  3. Problem and ICP — from briefs / problem-discovery.
  4. Market and competition — wedge, key competitors, gap (from market + competitor memos).
  5. Economics — TAM/SAM/SOM sketch, LTV:CAC band, pricing logic.
  6. Experiments run — method, thresholds, result, ILI if any.
  7. Assumption ledger — open vs validated vs killed.
  8. Scorecard snapshot — total and decision if scored.
  9. Risks and regulatory — include regulatory-risk-scan if run.
  10. Next 3 actions — single owner and date if known.

Quality bar

  • Separate facts, assumptions, and interpretation.
  • Flag weakest evidence (tier 1–2) driving the decision.
  • State what was not tested.

Output

Save to discovery/<topic-slug>/YYYY-MM-DD-<slug>-synthesis.md using SYNTHESIS-TEMPLATE.md.

Offer to update TOPIC.md Current decision and Next experiment one-liners.

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.