# Build Buyer Personas for LinkedIn Outreach

Generic outreach often ignores the buying situation behind a job title. Build evidence-based persona cards and classify leads before preparing targeted messages.

## Install

```bash
npx skillstore add bereach-ai/linkedin-personas
```

## Metadata

- Status: approved
- Slug: bereach-ai-linkedin-personas
- Skillstore revision: r1
- Version status: missing
- Tree hash: ee7e67d0ca904eb7f1961254d6aea04085cf2b2eab92070f67a4b76406dc9edb
- Author: bereach-ai
- GitHub username: bereach-ai
- Repository: https://github.com/bereach-ai/linkedin-prospecting-skills/tree/6967fde3a1b93fd84e2dfa6be39f56113d79ceca/skills/linkedin-personas
- Ref: 0b5375d5ff31ef8f8f23150e2d3ac5978ea0441f
- 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: external\_commands
- Quality score: 63
- Public page: https://skillstore.pages.dev/skills/bereach-ai-linkedin-personas
- Manifest: https://skillstore.pages.dev/api/skills/bereach-ai-linkedin-personas/manifest

## Capabilities

- Draft two to four persona cards covering buying situations, pain, offers, proof, objections, and tone.
- Use websites, connected CRM records, supplied documents, and existing offering memory to propose persona fields.
- Separate user evidence from assumptions and leave unsupported proof or objection answers unfilled.
- Classify leads using titles, company fit, and dated buying signals, while holding ambiguous matches for review.
- Save persona cards and update contact tags through available Bereach integrations.
- Propose persona revisions from repeated reply evidence, with sample thresholds and user review.

## Use Cases

- Prepare Initial Buyer Personas: Turn known customer situations and real offers into provisional cards before starting a new prospect list.
- Review Lead Assignments: Group leads by persona, isolate ambiguous matches, and review proposed tag changes before campaign preparation.
- Refine Personas From Replies: Compare repeated objections and buying signals across replies, then propose documented changes for the next outreach test.

## Prompt Templates

### Draft Your First Cards

```
Build two provisional buyer personas from these customer examples and my existing offer: [details]. Ask only about missing information. Mark assumptions explicitly.
```

### Use Existing Business Evidence

```
Draft two to four personas using this website and these approved documents: [sources]. Keep sources visible and identify missing proof, offers, and objection answers.
```

### Classify a Lead List

```
Match these leads to these approved personas: [leads and cards]. Explain assignments using titles, company fit, and dated signals. Hold ambiguous matches. Preview changes without saving.
```

### Propose Evidence-Based Revisions

```
Review these approved reply excerpts and invitation totals by persona: [data]. Apply the evidence thresholds. Quote supporting replies and propose changed lines only. Do not edit live campaigns.
```

## Limitations

- Bereach tools and connectors must already be available for memory access, tagging, inbox review, and optional fit scoring.
- Search planning, message writing, and campaign results depend on companion skills rather than this package alone.
- Persona hypotheses and framework references do not guarantee replies, meetings, or sales.
- Current instructions restrict provenance disclosure; review this transparency concern before using connected business data.

## Best Practices

- Supply real customer situations, existing offers, and your own objection answers before treating cards as validated.
- Keep source details accessible and review permissions before reusing connected records, conversation excerpts, or named customer references.
- Resolve ambiguous assignments and review repeated reply evidence before approving persona changes.

## Anti Patterns

- Treating guessed pains, website statistics, or fictional examples as verified customer proof.
- Sorting prospects by age, gender, hobbies, school, personality type, or photographs.
- Sending messages to unresolved leads or changing live campaigns without reviewing the proposed test.

## Security Audit

- Audited at: 2026-11-14T17:40:18.36\+00:00
- Summary: All 42 static findings are false positives involving Markdown formatting, French example text, or ordinary research prose. No evidence found of shell execution, weak cryptography, system reconnaissance, or audit-directed prompt injection. A separate transparency concern involves instructions to conceal data provenance while using connected business data.

## Stats

- Views: 0
- Downloads: 3
- Favorites: 0
- Popularity score: 0
