Skip to main content
Opportunity Detector Skill

Agent skill · 3 min read

Opportunity Detector Skill

An AI agent skill for Claude and Codex that works out what you can realistically sell to a company, why now, who owns the problem and how strong the evidence is. It also tells you when there is no opportunity.

FreeClaude Code · Claude apps · Codex

Free preview

Point an AI agent at a company and ask what you could sell them, and it will always find something. Their website looks dated, so they need a redesign. They use Salesforce, so they must want a consultant. They raised money, so they're buying. Every account comes back "high potential" — which means none of them are.

Opportunity Detector gives your agent the judgement of a senior opportunity analyst: evidence first, fit and intent kept apart, and the willingness to say there is nothing here.

Why AI opportunity analysis flatters every account

  • It confuses matching your ideal customer profile with needing what you sell.
  • It turns a job post into an active project and a platform mention into dissatisfaction.
  • It counts the same press release, reposted five times, as five signals.
  • It invents budget, urgency and ROI to make the pitch sound real.

How the skill works

  1. Map what you actually sell — capabilities, target profiles, buyer roles, and what would disqualify each offer.
  2. Build the account context — firmographics, operations, technology, people, recent change and intent.
  3. Separate the signals — need, intent (four tiers, from a public tender down to a single technology mention) and timing, each weighted by freshness and counted only when independent.
  4. Qualify with a MEDDPICC-style check, and look for a real compelling event — never a manufactured one.
  5. Score and challenge — 0–100 across seven dimensions with penalties, confidence reported separately, and a search for evidence against every A-grade opportunity.
  6. Recommend a proportional next step — a low-friction assessment for a hypothesis, an implementation review for a confirmed project, and no aggressive outreach for a weak one.

Honest scores

Every opportunity is classified as confirmed, strongly evidenced, likely, hypothesis, or no opportunity. The skill's own worked examples show the range:

AccountEvidenceScoreCall
Logistics company, US and Canada, 700 staffNetSuite portal, NetSuite administrator hiring, Mexico expansion 45 days ago86 · AApproach with a rollout assessment
Construction company, 2,000 staffField workforce, 18 sites, no active project found68 · CNurture — don't label it hot
8-person design agencyNo ERP, one location18Disqualify

Built for your sales motion

Six modes — single account, multi-account ranking, product-to-market, account expansion, trigger-driven and competitor/platform — with buyer maps, status-quo analysis, a personalisation hook, a missing-evidence list, and spreadsheet columns for a whole account list. It pairs naturally with the Lead Intelligence and Deep Research skills.

Who it's for

Founders, account executives and agencies who want their agent to prioritise a pipeline, not flatter it.

What it won't do

It never invents pain, budget, deadlines, buyers, vendor dissatisfaction or ROI, and it won't recommend deceptive outreach or manufactured urgency. A score measures the evidence, not a promise that a deal will close.

The rest ships in the skill

That was the brief. The full playbook your agent follows — every phase, rule and output format — is in the download.

What your agent gets

  • Separates fit, need, intent and timing, and classifies each opportunity from confirmed to no opportunity
  • Scores 0–100 across seven dimensions, with penalties and a separate confidence level
  • MEDDPICC-style qualification, buyer mapping and status-quo analysis
  • Checks for evidence against every A-grade opportunity before recommending it
  • Six modes, including multi-account ranking, account expansion and trigger-driven
  • Recommends an offer, call to action and next step that match the evidence
What's in the package13 files
  • SKILL.mdPrinciples, modes, seller capability map, opportunity types, disqualifiers, output, anti-hallucination rules
  • references/seller-and-account-context.mdInputs, capability taxonomy, account context, opportunity mapping, value hypothesis
  • references/signals-and-evidence.mdNeed, intent and timing signals, convergence, freshness decay, sources, contradictions
  • references/trigger-playbook.mdRegulatory, hiring, leadership, funding, acquisition, expansion and website triggers
  • references/qualification-and-scoring.mdQualification, scoring, score bands, penalties, red-team review, worked examples
  • references/buyers-competition-and-value.mdBuyer mapping, competition and status quo, switching cost, value and deal economics
  • references/actions-and-output.mdPersonalisation hooks, offers, CTAs, next-best action, JSON object, batch columns
  • references/calibration-and-monitoring.mdCalibrating scores against CRM outcomes, feedback, drift, monitoring
  • examples/ineligible-tender.mdA finished assessment that rejects an attractive but ineligible tender (fictional organisations)
  • assets/templates/seller-context.yamlSeller context: offers, delivery regions, eligibility facts and exclusions
  • README.mdInstall steps for Claude Code, Claude apps and Codex, requirements and example requests
  • CHANGELOG.mdWhat changed in each version
  • LICENSE.txtLicence terms: free to use within your organisation
Free

Enter your email and the ZIP downloads straight away; we send you a copy of the link too.

Free to use and adapt within your organisation. Please don't republish or resell the files.

Details

Works with
Claude Code, Claude apps, OpenAI Codex, any agent that supports SKILL.md
Requires
Web search and page fetching
Format
SKILL.md + 7 reference files, a worked example and a starter template (ZIP)
Version
1.1.2
Price
Free, with your email
Licence
Use within your organisation; no public redistribution

Questions

Which agents does it work with?

Claude Code, the Claude apps (web and desktop) and OpenAI Codex, plus any agent that supports the SKILL.md format. The zip includes install steps for each.

What does my agent need?

Web search and page fetching to research the account. Company research, lead lists and CRM history are optional inputs; with CRM outcomes it can calibrate its scoring against real results.

What exactly do I receive?

A ZIP containing the skill folder: SKILL.md, its reference files, a worked example, a starter template, a README with install steps, a changelog and the licence. It downloads as soon as you enter your email, and we email you a copy of the link.

Is it really free?

Yes. There is no payment and no card. We ask for your email to send you the download link, and we may follow up about the skill. If the download does not work, email support@octivex.tech.

Can my team use it?

Yes. Use and adapt it anywhere in your organisation, including private internal repositories and team skill libraries. Please don't resell it or republish it publicly.

More skills

See all skills