creator-registry

Featured

Use when the user asks "what did we pay this creator last time" or to "update the creator roster"; maintains one durable record per creator — verified handles, rate history, exclusivity windows, dated compliance events, performance baselines. Not for scoring fit — use fit-scorer; not for reviewing content — use content-reviewer. 创作者档案/达人名册

AI & Automation 2,354 stars 322 forks Updated today Apache-2.0

Install

View on GitHub

Quality Score: 98/100

Stars 20%
100
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Creator Registry The canonical creator roster SSOT — the entity-optimizer analog for the IMPACT discipline. Curates the canonical per-creator record — **registry, not gate**: no `class: auditor`, no cap fields, no veto scoring, no roll-up labels; it stores dated facts and history, and the existing gates and scorers judge against it. One durable record per creator holds: verified cross-platform handles (identity dedup — is `@sarah_ig` the same person as `@sarahtok`?), audience stats each carrying an as-of date and a Measured / User-provided / Estimated label, rate card and negotiation history, past-campaign performance baselines, dated disclosure/FTC compliance events (each citing the content-reviewer verdict ID that produced it), exclusivity windows and contract status, and the confirmed contact path (with which waterfall step produced it). The registry registers, reconciles, and versions the record; it never scores, gates, or judges. **Scope seams** — who keeps what: - Fit verdicts stay with [fit-scorer](../../influencer/discover/fit-scorer/SKILL.md); the registry supplies audience history, response-history facts, and past-partnership facts — never a score or a "reputation" rating. - FTC/content judgment stays with [content-reviewer](../../influencer/activate/content-reviewer/SKILL.md) (the C³ ART gate); the registry stores its outcomes as dated events citing verdict IDs — never a compliant/risky label. - Finding new creators stays with [influencer-discovery](../../inf...

Details

Author
aaron-he-zhu
Repository
aaron-he-zhu/aaron-marketing-skills
Created
6 months ago
Last Updated
today
Language
Python
License
Apache-2.0

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Featured

offer-claims-registry

Use when the user asks to "register this claim", "log our current offers", or "where is the proof for this figure"; curates the canonical claims ledger and live-offers table under memory/claims/ — exact claim text, evidence provenance, approved wording, claim-level disclaimers, and offer terms — and resolves "[needs source]" flags from ad and content drafts. Not for scoring O1/O2 vetoes or issuing SHIP/FIX/BLOCK verdicts — use ad-account-auditor; not for gating creator content — use content-reviewer. 广告声明台账/优惠信息登记/证据溯源

2,354 Updated today
aaron-he-zhu
AI & Automation Listed

creator-fit-scoring

Scores one or more TikTok Shop creators for real sell-through fit using evidence (conversion over followers), returning a fit verdict + recommendation strength + outreach suggestion, with a lookalike-expansion recruiting mode. Use when the user wants to score, rank, evaluate, shortlist, compare, or find lookalike creators, or to process the sample creators returned by preview_target_collab. Affiliate (分销) context. Chinese triggers: 打分 / 评估 / 筛选 / 找相似达人 / 这批达人合不合适.

4 Updated 4 days ago
crevideo
AI & Automation Featured

influencer-discovery

Use when the user asks to "find influencers", "build an influencer list", or "discover creators in [niche]"; produces a multi-platform candidate pool, per-influencer profiles with audience and engagement metrics, authenticity red-flag screening, and a tiered shortlist with fit scores. Not for scoring or ranking a known shortlist — use fit-scorer.

2,354 Updated today
aaron-he-zhu