Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add HashLips/agent-skills --skill opportunity-gap-findergit clone --depth 1 https://github.com/HashLips/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hashlips/agent-skills/opportunity-gap-finder)<a href="https://agentmods.dev/skills/hashlips/agent-skills/opportunity-gap-finder"><img src="https://agentmods.dev/badge/skills/hashlips/agent-skills/opportunity-gap-finder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hashlips/agent-skills/opportunity-gap-finder"><img src="https://agentmods.dev/badge/skills/hashlips/agent-skills/opportunity-gap-finder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00067 | $0.01313 |
| Opus 5 | $0.00034 | $0.00656 |
| Sonnet 5 | $0.00013 | $0.00263 |
| Haiku 4.5 | $0.00007 | $0.00131 |
Grade A, and why
opportunity-gap-finder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
- Discover before inventing — Never present an assumed problem, demand level, market fact, or success probability as established.
- Do not skip the problem — Trace context → actors → current behaviour → friction or blocked progress → root cause → need → opportunity mechanism.
- 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.
- 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.
- Ask progressively — Ask 3–6 related questions per round unless the user requests a full questionnaire or a rapid scan.
- Follow evidence — Investigate strong signals and contradictions instead of completing a static questionnaire.
- Compare against reality — Include direct competitors, indirect substitutes, manual workarounds, doing nothing, and failed prior attempts.
- Separate attractiveness from confidence — A promising hypothesis with weak evidence is not a recommendation to build.
- Prefer behaviour over opinion — Separate attention, complaints, stated intent, attempted solutions, commitment, adoption, retention, payment, and measurable impact.
- No guaranteed-success language — Explain uncertainty, dependencies, disconfirming evidence, and the cheapest next test.
Workflow
- Choose a mode and establish the user's pursuit criteria — references/session-rules.md.
- Frame the search from the supplied domain, actor, problem, change, capability, asset, or idea.
- Investigate actors, behaviour, frictions, blocked progress, causes, alternatives, and needs — references/investigation-phases.md.
- Gather and grade relevant evidence; distinguish sourced facts, user observations, inferences, and unknowns — references/evidence.md.
- Generate materially different opportunity mechanisms using references/archetypes.md, then screen and rank them with references/scoring.md.
- Stress-test the leaders and choose the cheapest tests of their riskiest assumptions — references/validation.md.
- Deliver a decision-ready brief — references/opportunity-brief.md.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/archetypes.md 2.7 KB
- references/evidence.md 4.5 KB
- references/example-cross-domain.md 4.2 KB
- references/investigation-phases.md 8.3 KB
- references/opportunity-brief.md 3.2 KB
- references/quality-checklist.md 2.7 KB
- references/questioning-logic.md 4.2 KB
- references/scoring.md 7.7 KB
- references/session-rules.md 4.6 KB
- references/validation.md 3.8 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 85 lines · 67 tokens per session scan A 531fe86bfa47
opportunity-gap-finder is a skill published in the GitHub repository HashLips/agent-skills (27 stars, last pushed 16d ago), licensed MIT. It adds 67 tokens to every session and 1,313 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…