# Rank Influencers for Campaign Fit

Creator shortlists are difficult to compare consistently across audience, credibility, engagement, and campaign needs. This skill applies typed ACE scoring and separates commercial fit.

## Install

```bash
npx skillstore add aaron-he-zhu/fit-scorer
```

## Metadata

- Status: approved
- Slug: aaron-he-zhu-fit-scorer
- Version: 17.0.0
- Author version: 17.0.0
- Skillstore revision: r1
- Version status: valid
- Tree hash: 2da4c52a304606d2a39e2cfd0b6f3d71b1c17f3b33c8b3aa77d73c1d3aaf8436
- Author: aaron-he-zhu
- GitHub username: aaron-he-zhu
- License: Apache-2.0
- Repository: https://github.com/aaron-he-zhu/aaron-marketing-skills/tree/main/influencer/discover/fit-scorer
- Ref: d71c7417a35d5c2624161bd2fe8de8a41a362128
- 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: filesystem, external\_commands, network, env\_access
- Quality score: 77
- Quality tier: bronze
- Public page: https://skillstore.pages.dev/skills/aaron-he-zhu-fit-scorer
- Manifest: https://skillstore.pages.dev/api/skills/aaron-he-zhu-fit-scorer/manifest

## Capabilities

- Evaluates all 12 Audience, Credibility, and Engagement items with typed evidence states.
- Preserves evidence dates, confidence, cohort context, profile version, and scoring coverage.
- Runs the deterministic repository scorer when its runtime and typed catalog are available.
- Builds a separate commercial-fit matrix across audience, content, brand, terms, availability, and partnership potential.
- Ranks shortlisted creators while showing critical controls, evidence gaps, and outreach recommendations.

## Use Cases

- Prioritize a Campaign Shortlist: Compare shortlisted creators under one campaign goal and identify evidence-backed outreach priorities.
- Standardize Client Recommendations: Apply one typed rubric across creators while keeping client-specific commercial fit separate.
- Audit Creator Evidence: Review credibility vetoes, missing metrics, and confidence before approving a partnership.

## Prompt Templates

### Score One Creator

```
Score @[handle] for [campaign]. Use goal [goal] and list the evidence needed before making a recommendation.
```

### Compare a Shortlist

```
Compare @[handle1], @[handle2], and @[handle3] for [campaign]. Show ACE results separately from commercial fit.
```

### Assess Evidence Gaps

```
Audit these creator metrics for [campaign]. Mark missing data Unknown, identify critical controls, and explain what prevents a final score.
```

### Build an Advanced Ranking

```
Rank [creators] for [campaign] using [goal]. Include typed context, dated evidence, veto checks, commercial terms, confidence, and rerun conditions.
```

## Limitations

- Requires a creator shortlist and current campaign context from the user.
- Cannot produce a complete ACE total when required evidence remains Unknown.
- Deterministic scoring depends on repository scripts and catalogs that may be absent from standalone installs.
- Does not discover new creators, negotiate terms, or send outreach.

## Best Practices

- Use the same evidence window, cohort, and campaign goal for every compared creator.
- Keep ACE results separate from campaign-specific commercial-fit scores.
- Verify critical failures and refresh stale metrics before approving outreach.

## Anti Patterns

- Do not treat missing or refused private data as a failure.
- Do not hand-calculate an ACE total when the deterministic scorer is unavailable.
- Do not let commercial fit override an ACE veto or unresolved evidence gap.

## Security Audit

- Audited at: 2026-07-12T12:27:19.622\+00:00
- Summary: Most findings are scanner false positives caused by Markdown code fences, inline code, and relative documentation links. The skill explicitly runs local Python tooling, uses shell command substitution, and expects a YouTube API key. No prompt injection or data-exfiltration intent was found in the reviewed files.

## Stats

- Views: 1
- Downloads: 5
- Favorites: 0
- Popularity score: 0