Stats
Actions
Tags
From media-ads-skill
Run comprehensive ads data analysis across any platform — budget health, creative Hook/Body diagnosis, audience saturation, scaling curves, funnel analysis, and trend prediction. Accepts StandardSchema input from any data layer (Meta, XHS, or custom). Outputs a complete .md report maximizing the user's north star metric.
How this skill is triggered — by the user, by Claude, or both
Slash command
/media-ads-skill:data-analysisThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
当用户提到以下任何一种情况时，启动本 Skill：
当用户提到以下任何一种情况时，启动本 Skill：
严格按以下 5 步执行，不可跳步。
向用户确认：
你的北极星指标是什么？（CPL / CPC / CTR / ROAS / 其他）
目标值多少？（例如 CPL ≤ RM 50）
必须获得：
metric）：cpl、cpc、ctr、roastarget）：如 50lower_is_better；CTR/ROAS → higher_is_better加载脚本调用指南：Read({base}/skills/data-analysis/scripts-guide.md)
按指南完成：数据收集 → validate → full_report.py --analyze。
默认拉取 28 天数据（覆盖新+旧广告）。脚本自动按广告年龄（7天为界）分段输出。
读取 --analyze 的 JSON 输出，不可直接照搬脚本输出，必须跨模块推理：
加载诊断知识：Read({base}/skills/data-analysis/diagnosis.md)
按 diagnosis.md 的报告模板，保存到 data/reports/YYYY-MM-DD-analysis.md。
Searches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.
npx claudepluginhub owenleezy/media-ads-skill --plugin media-ads-skill