# Classify Businesses Against a Single Sector

Business descriptions can make industry matching and website template selection inconsistent. This guide outlines keyword-based sector matching and site archetype choices for an AI assistant.

## Install

```bash
npx skillstore add nexaiguy/nex-one-sector-classifier
```

## Metadata

- Status: approved
- Slug: nexaiguy-nex-one-sector-classifier
- Version: 1.0
- Author version: 1.0
- Skillstore revision: r1
- Version status: invalid
- Tree hash: b1acc16f6dfec109c0f658502043757c9785793239ae37654cece61f10c285be
- Author: nexaiguy
- GitHub username: nexaiguy
- License: MIT
- Repository: https://github.com/nexaiguy/nex-ai-skills/tree/463aaff26593654193deb52f24d18e80ec21e323/skills/nex-one-sector-classifier
- Ref: 3ddfdca559084abffbfdd188f2ba14b597dcfd9c
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: allowed
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: network
- Quality score: 77
- Quality tier: bronze
- Public page: https://skillstore.pages.dev/skills/nexaiguy-nex-one-sector-classifier
- Manifest: https://skillstore.pages.dev/api/skills/nexaiguy-nex-one-sector-classifier/manifest

## Capabilities

- Describes keyword-based matching of a business description against one configured sector.
- Provides a bakery example with identified keywords, a match result, and an illustrative score.
- Outlines sector-based choices for website sections, tone, imagery, and calls to action.
- Recommends a generic site archetype when classification confidence is low.
- Describes generating a standalone Python classifier, but does not include the implementation.

## Use Cases

- Review Lead Sector Matches: Compare supplied prospect descriptions with one selected sector before assigning industry labels in a CRM.
- Plan Sector-Based Demo Sites: Use business evidence to propose website sections, tone, imagery, and calls to action, with a generic fallback for uncertain cases.
- Prototype a Lightweight Classifier: Ask an assistant to draft a single-sector Python classifier, then inspect and test the generated implementation before integration.

## Prompt Templates

### Match One Business

```
Classify this description against Food and Beverage: Artisanal bakery in Ghent specializing in sourdough bread and local pastries. Identify supporting keywords.
```

### Assess an Uncertain Match

```
Evaluate [business description] against [sector] using [keywords]. Explain missing evidence and recommend a generic archetype when confidence is low.
```

### Propose a Site Archetype

```
Using [business description] and [public listing text], assess [sector]. Propose sections, tone, imagery, and a call to action. Separate evidence from assumptions.
```

### Draft and Test a Classifier

```
Draft classifier_lite.py for [sector] using [keywords]. Define scoring explicitly. Include positive, negative, and ambiguous tests. Do not claim the guide supplies executable code.
```

## Limitations

- Only SKILL.md is included; executable scripts, extension source, and templates are absent.
- The free approach addresses one configured sector at a time, not comprehensive multi-sector classification.
- The guide targets Belgian and Benelux SMEs; unusual or multi-activity businesses may require a generic result.
- No keyword dictionary, scoring formula, confidence calibration, or concrete JSON schema is supplied.

## Best Practices

- Supply the target sector, explicit keywords, and relevant business text before requesting a classification.
- Use a generic archetype when evidence is sparse or the business spans several activities.
- Review generated scripts and test representative matches, nonmatches, and ambiguous cases before pipeline integration.

## Anti Patterns

- Treating the public guide as an installed classifier with bundled executable assets.
- Interpreting an illustrative keyword score as a calibrated probability or independently verified business classification.
- Assuming the free single-sector approach includes the paid version's 12 archetypes or AI-driven analysis.

## Security Audit

- Audited at: 2026-11-02T11:53:26.515\+00:00
- Summary: All four static findings are false positives: attribution links and ordinary FAQ text do not demonstrate network execution or system reconnaissance. No evidence found of prompt injection, credential access, or data exfiltration in SKILL.md. The package contains only a public guide, so advertised script and pipeline behavior cannot be verified.

## Stats

- Views: 0
- Downloads: 0
- Favorites: 0
- Popularity score: 0