Skip to content
OpenAgentSkill
Browsing is open · Catalog captured 2026-11-21 · Automatic updates and account services are paused.
Search & research

opportunity-gap-finder

Discovers and ranks evidence-backed opportunities by tracing unmet needs, underserved outcomes, weak alternatives, and viable ways to create value in any domain. Use when someone wants to identify a business, service, personal project, community initiative, physical product, creative pursuit, research direction, or other worthwhile problem to pursue.

HashLips · Static checks on file

Installation

Read the source and dependencies before running a command. Copying does not install or execute anything.

npx skills add HashLips/agent-skills --skill opportunity-gap-finder

About this skill


name: opportunity-gap-finder description: Discovers and ranks evidence-backed opportunities by tracing unmet needs, underserved outcomes, weak alternatives, and viable ways to create value in any domain. Use when someone wants to identify a business, service, personal project, community initiative, physical product, creative pursuit, research direction, or other worthwhile problem to pursue.

Opportunity Gap Finder

Turn an open domain, observed problem, change, capability, audience, or early idea into ranked opportunity hypotheses and a validation plan. Find valuable progress that people or organisations struggle to make, then determine whether the user has a credible way to help. Investigate before ideating and never imply that success is guaranteed.

Core Rules

  1. Discover before inventing — Never present an assumed problem, demand level, market fact, or success probability as established.
  2. Do not skip the problem — Trace context → actors → current behaviour → friction or blocked progress → root cause → need → opportunity mechanism.
  3. Stay domain- and format-agnostic — Do not default to software, commercial ventures, or scalable products. The best response may be a service, physical intervention, practice, programme, community, research effort, policy, creative work, or a decision not to proceed.
  4. Define success for this user — Clarify desired impact, income or non-financial value, available resources, timeframe, geography, risk tolerance, motivation, and ethical boundaries before ranking.
  5. Ask progressively — Ask 3–6 related questions per round unless the user requests a full questionnaire or a rapid scan.
  6. Follow evidence — Investigate strong signals and contradictions instead of completing a static questionnaire.
  7. Compare against reality — Include direct competitors, indirect substitutes, manual workarounds, doing nothing, and failed prior attempts.
  8. Separate attractiveness from confidence — A promising hypothesis with weak evidence is not a recommendation to build.
  9. Prefer behaviour over opinion — Separate attention, complaints, stated intent, attempted solutions, commitment, adoption, retention, payment, and measurable impact.
  10. No guaranteed-success language — Explain uncertainty, dependencies, disconfirming evidence, and the cheapest next test.

Workflow

  1. Choose a mode and establish the user's pursuit criteria — references/session-rules.md.
  2. Frame the search from the supplied domain, actor, problem, change, capability, asset, or idea.
  3. Investigate actors, behaviour, frictions, blocked progress, causes, alternatives, and needs — references/investigation-phases.md.
  4. Gather and grade relevant evidence; distinguish sourced facts, user observations, inferences, and unknowns — references/evidence.md.
  5. Generate materially different opportunity mechanisms using references/archetypes.md, then screen and rank them with references/scoring.md.
  6. Stress-test the leaders and choose the cheapest tests of their riskiest assumptions — references/validation.md.
  7. Deliver a decision-ready brief — references/opportunity-brief.md.

Use references/questioning-logic.md to branch the interview rather than asking every question.

Output Contract

For a completed guided or evidence-assisted investigation, include:

  • Pursuit criteria and scope
  • Context and relevant actors, when applicable
  • Current behaviour, alternatives, and non-consumption, when applicable
  • Ranked frictions or blocked outcomes with evidence strength
  • Root causes and outcome-focused need statements
  • 3–5 distinct opportunity hypotheses, or fewer when justified
  • Comparative ranking, evidence strength, consistency, resulting confidence, and kill factors
  • Recommended lead opportunity and value proposition
  • Smallest useful validation plan
  • Unknowns, disconfirming evidence, and conditions that would change the decision
  • Decision: investigate now | validate before committing | pursue a small version | monitor | reframe | reject for now

For a rapid scan, provide only:

  • scope and assumed pursuit criteria,
  • 2–5 provisional search territories or opportunity hypotheses,
  • evidence available, evidence missing, and major caveats,
  • the most useful next investigation step.

For open search, first deliver a checkpoint containing:

  • pursuit criteria and accessible assets,
  • 2–3 search territories with selection reasons,
  • the first evidence-gathering questions for each.

A full investigation is complete only when it yields either one sufficiently supported opportunity with a validation plan or a clear conclusion that evidence does not justify pursuit and exactly what to learn next. A rapid scan or open-search checkpoint is complete when its smaller output contract is met; never present it as a validated recommendation. Do not manufacture an opportunity to satisfy the format.

Reference Index

  • Modes, intake, session behaviour, and language: references/session-rules.md
  • End-to-end investigation sequence: references/investigation-phases.md
  • Evidence collection and confidence rules: references/evidence.md
  • Screening, comparative ranking, and kill factors: references/scoring.md
  • Stress tests and validation experiments: references/validation.md
  • Final brief and completion rules: references/opportunity-brief.md
  • Dynamic interview branching: references/questioning-logic.md
  • Gap archetypes for broad solution discovery: [references/archetypes.md](references/arc
Read the complete source ↗