Fit Scorer

Fit Scorer

Score each shortlisted creator on the typed C3 ACE creator rubric, then keep campaign-specific commercial fit in a separate prioritization matrix. The ACE result is portable and brand-independent; the commercial matrix is not an ACE score and never enters CVI.

Quick Start

Score one influencer:

Score @[handle] for [brand/campaign] and tell me if they're a good fit

Compare and rank a shortlist:

Compare and rank these influencers for [campaign]: @influencer1, @influencer2, @influencer3

Skill Contract

• Reads: brand/campaign context, target audience definition, campaign goal, and a shortlist of influencer handles (supplied by the user or carried over from influencer-discovery). Optional prior audience profiles from memory/influencer/audience-mapper/ and competitor partner benchmarks from memory/influencer/competitor-tracker/. For rostered creators, read partnership history and audience-stat provenance from memory/creators/<handle-slug>.md — the creator-registry roster record — as Partnership Potential inputs.
• Writes: only with explicit authorization, a report containing typed ACE results plus a separately labeled commercial-fit comparison at memory/influencer/fit-scorer/YYYY-MM-DD-<topic>.md.
• Promotes: only with separate authorization, evidence-backed top picks and their exact ACE profile/version; never promote an unscored or provisional result.
• Done when:
  • Every creator has all 12 ACE items explicitly Pass/Partial/Fail/Unknown/N/A with dated evidence or a gap reason.
  • The exact ace-<goal> profile/context and deterministic scorer result are preserved; Unknown prevents an ACE total.
  • Any commercial-fit ranking is visibly separate from ACE and cannot override a veto or missing evidence.
• Primary next skill: competitor-tracker — benchmark your top-scored picks against the creators competitors already partner with.

Handoff Summary

Emit the standard shape from skill-contract.md §Handoff Summary Format.

Data Sources

This family needs no live integrations (Tier 1). Fit Scorer works end to end by asking the user for the inputs it scores — handles, audience targets, brand values, and any metrics they have. A connector sharpens the numbers but none is required.

• ~~influencer database — follower counts, audience demographics, and partnership history.
• ~~social platform analytics — engagement rate, comment quality samples, posting cadence, growth trend.
• ~~audience intelligence — real-vs-bot follower estimates and audience overlap with your target.
• Roster record (keyless Tier 1) — prior contact, response reputation, and delivery history come from memory/creators/<handle-slug>.md when the creator is rostered (creator-registry curates it); ~~CRM is an optional Tier-2 sharpener for the same history when no roster record exists.

Measured YouTube inputs (free key): for YouTube candidates, python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/youtube.py" videos @handle --limit 10 supplies the engagement-authenticity inputs directly — per-video views/likes/comments against the displayed subscriber base (views-to-subs consistency, comment rate, cadence) — so those sub-scores come from Measured numbers instead of screenshots. Free YOUTUBE_API_KEY; shortlist vetting only (ToS refuses bulk-harvesting quota). See scripts/connectors/README.md.

With zero integrations, ask the user to supply each value the scoring tables request; the framework and weighting still produce a defensible ranking. See CONNECTORS.md for the free/keyless recipe per category.

Instructions

The commercial comparison layouts live in references/scoring-templates.md. They are optional decision support, not the C3 rubric.

1. Lock typed context. Declare creator target/version, goal (awareness|engagement|conversion|brand-building), profile ace-<goal>, scope: ace, assessment_time: forecast|actual, shared campaign rollup_id, observation date, platform/tier/niche cohort, and evidence window. Profile scope/goal must match context.
2. Freeze evidence. Use creator analytics, public observations, roster history, and cohort benchmarks with source/date/type/confidence. Missing or refused private access is Unknown, never Fail or Partial.
3. Score ACE only. Evaluate A1-A4 Audience, C1-C4 Credibility, and E1-E4 Engagement from ace-creator-benchmark.md. Creator-brand fit, exclusivity conflict, cost, and campaign conversion belong to ROI.O/I, not ACE.
4. Verify critical failures. C3-ACE.A2 fails only on verified real-follower rate below 70%; C3-ACE.C1 on verified disqualifying conduct; C3-ACE.E2 on verified bought/pod engagement. One verified veto yields DONE_WITH_CONCERNS/FIX and final=min(raw,59); two or more yield DONE/BLOCK with no final score. Operationally hold outreach while a critical issue remains, but do not relabel the typed verdict.
5. Run the deterministic scorer. Follow runtime-invocation.md, resolve AARON_SKILLS_ROOT="${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || true)}", verify the scorer and typed catalog, then execute python3 "$AARON_SKILLS_ROOT/scripts/rubric-score.py" score <run.json>. If the standalone install lacks them, return score_state: NOT_SCORED / score_confidence: not_scored; do not hand-calculate a total, verdict, or persistent artifact.
6. Build the separate commercial matrix when requested. Use audience-to-campaign fit, content style, campaign-specific brand/category fit, commercial terms, availability, and partnership potential. Label its 1-5 total commercial_fit_score; it is not ACE, cannot clear an ACE veto, and never enters CVI.
7. Rank transparently. Show ACE profile/result (or coverage/interval), critical controls, commercial fit separately, evidence confidence, and an outreach recommendation with owner/rerun condition. Do not rank an Unknown-heavy candidate as definitively superior.
8. Persist only with permission. Save the report only after authorization; request separate authorization before any hot-cache promotion or creator-registry proposal.