# Creator Attribution Lite

> Connect creator content outputs to practical business outcomes using a lightweight attribution model. Use when the user asks which posts drove clicks/leads/sales, wants to prioritize high-ROI content types, or needs simple performance decisions without full BI setup.

- Skill: `leooooooow/creator-attribution-lite` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add leooooooow/creator-attribution-lite`
- Raw SKILL.md: https://api.skillmd.com/api/skills/leooooooow/creator-attribution-lite/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: Leooooooow (https://skillmd.com/u/leooooooow)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/leooooooow/creator-attribution-lite

---


# Creator Attribution Lite

## Skill Card

- **Category:** Measurement
- **Core problem:** Which content actions actually move outcomes?
- **Best for:** Small-team performance review
- **Expected input:** Content list + campaign metadata + simple outcome fields
- **Expected output:** Lightweight attribution view + insight notes
- **Creatop handoff:** Feed winning patterns back to Creatop templates

## What this does

Show which content likely moved business outcomes, not just vanity metrics.

## Workflow

### 1) Validate data availability

Minimum fields per content item:
- content ID + date + platform
- views/watch metric
- click metric
- downstream metric (lead/signup/sale/GMV)

If real data is missing, run **simulation mode** and label outputs clearly as demo/synthetic.

### 2) Map funnel stage

Classify each content item as:
- awareness
- consideration
- conversion

### 3) Compute lightweight impact score

Use transparent weighted components:
- engagement quality
- click intent
- conversion signal

Explain formula and normalization assumptions.

### 4) Output action decisions

Return:
- ranked performers
- pause/optimize list
- next 3 content bets with rationale
- confidence note (sample size/data quality)

## Quality rules

- Keep model explainable and auditable.
- Avoid fake precision on tiny samples.
- Do not overclaim causality; treat as directional evidence.
## License

Copyright (c) 2026 **Razestar**.

This skill is provided under **CC BY-NC-SA 4.0** for non-commercial use.
You may reuse and adapt it with attribution to Razestar, and share derivatives
under the same license.

Commercial use requires a separate paid commercial license from **Razestar**.
No trademark rights are granted.