analyze-performance-rank-and-read
GitHub分析创意表现排名,按角度、钩子和格式对广告进行分组和评分,生成渠道阅读报告及后续制作建议。
触发场景
安装
npx skills add gooseworks-ai/goose-skills --skill analyze-performance-rank-and-read -g -y
SKILL.md
Frontmatter
{
"name": "analyze-performance-rank-and-read",
"version": "0.1.1",
"description": "Step of the analyze-performance playbook: ranks creative by angle, hook and format with spend gates, writes short per-channel reads and drafts what to make next. Run analyze-performance instead; not for direct use."
}
Creative ranking and channel reads (atom)
Load: ../analyze-performance/references/creative-and-channels.md.
Inputs: meta_read performance (ranked by spend; the scorecard on the settled days: 14 minus days: 3 window, 7- and 28-day reads for the fatigue trend); each Goose ad's angle annotation (ads_creative_read and the campaign concepts); the non-Goose export; UTM store conversion per angle; email export; social_analytics_get posts and accounts; Google export and search terms; app/local exports.
Do:
- Creative: group by angle → hook → format; rank by spend; apply minimum-spend gates; verdict with confidence; fatigue trend; name no winner if
insight.availableis false; state coverage. - Build the per-channel and per-ad scorecards against last run's rows and the angle history line (
../analyze-performance/references/run-memory.md). - Draft "what to make next" from the history: tiring 2+-run winners first, retire losers, fair test for too-early, organic overperformers as paid candidates; nothing that already failed without a new reason; unmade items carried with their first date — producer and date for each.
- Email & SMS, organic, Google (+ wasted-spend terms), apps, local: one short block each, or "not measured this week" / "not used".
- Future rows: creators (codes), outreach (reply rates), WhatsApp — named, never dropped.
Output: the scorecards for the run record; the report's Creative ranking, channel blocks, channel-table rows and What-to-make-next draft.
版本历史
- 1add09b 当前 2026-11-02 21:49


