- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add ScrapeCreators/social-media-research-skills --skill outlier-post-finder -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add ScrapeCreators/social-media-research-skills --skill outlier-post-finder -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add ScrapeCreators/social-media-research-skills --skill outlier-post-finder -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add ScrapeCreators/social-media-research-skills --skill outlier-post-finder -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/ScrapeCreators/social-media-research-skills/tree/HEAD/skills/outlier-post-finder來自發布者
Find social posts that beat an account's normal performance. The goal is not just to sort by views. The goal is to identify posts that performed unusually well for that creator or brand, then explain the repeatable patterns.
Use ScrapeCreators as the data layer. Pull recent public posts, normalize engagement metrics, calculate each account's baseline, and produce an outlier report with source URLs and practical takeaways.
Use this skill when the user asks to:
Do not use this for raw endpoint lookup only. Use scrapecreators-api for direct API routing.
Prefer the platform-specific feed endpoint, then enrich individual posts only when needed.
Before calling an endpoint, fetch its docs or per-endpoint OpenAPI spec if parameter names or response fields are uncertain.
Clarify scope only if needed
Fetch recent posts
Normalize metrics
Calculate the account baseline
Score outliers
view_lift = post_views / median_viewsengagement_lift = post_engagement / median_engagementEnrich the winners
Explain why they worked Look for:
# Outlier Posts Report: {creator_or_brand}
## Summary
- Sample: {n} posts from {platforms}
- Window: {window}
- Baseline: median {primary_metric} = {value}
- Confidence: High/Medium/Low
## Biggest Outliers
| Rank | Post | Platform | Date | Primary Metric | Lift | Why it likely worked |
|---:|---|---|---|---:|---:|---|
| 1 | [title/hook](url) | TikTok | 2026-01-01 | 1.2M views | 8.4x | Contrarian hook + clear before/after |
## Repeatable Patterns
1. **Pattern name** — evidence and examples.
2. **Pattern name** — evidence and examples.
## Hooks to Steal
- "Exact hook from caption or transcript"
- "Exact hook from caption or transcript"
## Content Ideas Based on the Outliers
1. ...
2. ...
## Notes and Caveats
- Public data only.
- Small samples are directional, not definitive.
Use when the user wants to find posts, videos, reels, shorts, tweets, or social content that overperformed versus a creator, brand, or competitor baseline. Finds outliers, explains why they worked, ex
---name: outlier-post-finderdescription: Use when the user wants to find posts, videos, reels, shorts, tweets, or social content that overperformed…---# skills/outlier-post-finder/SKILL.md總覽
Use when the user wants to find posts, videos, reels, shorts, tweets, or social content that overperformed versus a creator, brand, or competitor baseline. Finds outliers, explains why they worked, extracts hooks and formats, and produces a practical swipe file.
常見問題
從發布者下載 skills/outlier-post-finder/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/ScrapeCreators/social-media-research-skills。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。