Social Research Analyzer

Content Research — stop guessing what to post

by Ootto-AI · MIT license · ★ 139 on GitHub

Turn Claude into a content research machine for any niche. Point it at any creator or account and it pulls their posts, finds the exact ones that blew up (the outliers), then breaks down WHY — the hook, the format, and the retention…

---
name: content-research
description: >
  Turn Claude into a content research machine for any niche. Point it at any creator or account and it
  pulls their posts, finds the exact ones that blew up (the outliers), then breaks down WHY — the hook,
  the format, and the retention patterns — and surfaces the repeatable playbook you can copy. Use when
  the user says "research this niche", "what's working for @account", "find what's going viral in
  [niche]", "what should I post about", "study this creator", or wants a content strategy grounded in
  real data instead of guessing.
user-invokable: true
argument-hint: "[creator @handle, account URL, or niche]"
license: MIT
metadata:
  author: Ootto
  version: "1.0.0"
  category: content
---

Overview

Most people spend hours scrolling to figure out what to post. This skill turns Claude into a research machine: point it at any account or niche and it finds the exact moments that went viral and the patterns behind them — so you copy what works instead of guessing.

What you get

Pull the postsFor a creator/account, gather their recent reels + view counts (Instagram Graph
Find the spikesRank posts by views and flag the outliers — the exact posts where the account
Break down WHYFor each outlier, study the reel frame-by-frame + transcript (hand off to the
Surface the playbookAcross the outliers, surface the repeatable patterns — the hook types,

Manual install (npx, ZIP)

Claude Codenpx skills add Ootto-AI/claude-content-skills --skill content-research -g -a claude-code

Claude Code (degit)npx degit Ootto-AI/claude-content-skills/skills/content-research#main ~/.claude/skills/content-research

Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md3.4 KB

Read SKILL.md here

Ootto-AI/main1 file shown

SKILL.md3.4 KB

Browse every file on GitHub↗

SKILL.md

Show the full text66 lines

content-research/SKILL.md66 lines · 3.4 KB

PreviewCode

Outline

RawView on GitHub

Content Research — stop guessing what to post

What it does

Pull the posts. For a creator/account, gather their recent reels + view counts (Instagram Graph API via Composio, or any list of reel URLs the user provides).
Find the spikes. Rank posts by views and flag the outliers — the exact posts where the account blew up vs their baseline. Those are the moments worth studying.
Break down WHY. For each outlier, study the reel frame-by-frame + transcript (hand off to the reel-analyzer skill / ootto-watch) and extract the hook (first 2s), the format/structure, the pacing, and the retention pattern.
Surface the playbook. Across the outliers, surface the repeatable patterns — the hook types, formats, and topics that consistently earn saves/shares — and turn them into a short, copyable plan for the user's own niche.

How to run it

Ask for a creator @handle, an account URL, or a niche (+ a few example accounts).
Pull their reels + view counts. Options:
- sandcastles.ai — a research engine that pulls top channels and auto-surfaces the viral outliers + the frameworks behind them (fastest path; connect it to Claude and let it do the heavy lifting).
- Composio Instagram tools — free/DIY: list a creator's media + insights from the Graph API.
- Or a plain list of reel URLs the user pastes.
Rank by views, compute each post's ratio vs the account median, and mark anything ~2-3x median as an outlier ("blew up here").
For the top 3-5 outliers, run reel-analyzer (or ootto-watch — github.com/Ootto-AI/ootto-watch) to break down hook / format / retention.
Synthesize: list the winning hook patterns, formats, and topics, then write 3 ready-to-shoot ideas for the user's own account modeled on what actually worked.

Output

A short research report:

The spikes — which posts blew up and by how much (vs baseline).
Why they worked — hook / format / retention breakdown per outlier.
The playbook — the repeatable patterns + 3 original ideas for your niche.

Honesty

Model the technique, never copy another creator's exact script, visuals, or caption. Cite the source reels you studied. View counts come from real data (Composio / what the user provides) — never fabricate.

Part of the Ootto content-skills marketplace. Pairs with reel-analyzer, going-viral, and reel-scripter.

1	---
2	name: content-research
3	description: >
4	Turn Claude into a content research machine for any niche. Point it at any creator or account and it
5	pulls their posts, finds the exact ones that blew up (the outliers), then breaks down WHY — the hook,
6	the format, and the retention patterns — and surfaces the repeatable playbook you can copy. Use when
7	the user says "research this niche", "what's working for @account", "find what's going viral in
8	[niche]", "what should I post about", "study this creator", or wants a content strategy grounded in
9	real data instead of guessing.
10	user-invokable: true
11	argument-hint: "[creator @handle, account URL, or niche]"
12	license: MIT
13	metadata:
14	author: Ootto
15	version: "1.0.0"
16	category: content
17	---
18
19	# Content Research — stop guessing what to post
20
21	Most people spend hours scrolling to figure out what to post. This skill turns Claude into a research
22	machine: point it at any account or niche and it finds the exact moments that went viral and the
23	patterns behind them — so you copy what works instead of guessing.
24
25	## What it does
26
27	1. Pull the posts. For a creator/account, gather their recent reels + view counts (Instagram Graph
28	API via Composio, or any list of reel URLs the user provides).
29	2. Find the spikes. Rank posts by views and flag the outliers — the exact posts where the account
30	blew up vs their baseline. Those are the moments worth studying.
31	3. Break down WHY. For each outlier, study the reel frame-by-frame + transcript (hand off to the
32	`reel-analyzer` skill / ootto-watch) and extract the hook (first 2s), the format/structure, the
33	pacing, and the retention pattern.
34	4. Surface the playbook. Across the outliers, surface the repeatable patterns — the hook types,
35	formats, and topics that consistently earn saves/shares — and turn them into a short, copyable plan
36	for the user's own niche.
37
38	## How to run it
39
40	1. Ask for a creator @handle, an account URL, or a niche (+ a few example accounts).
41	2. Pull their reels + view counts. Options:
42	- sandcastles.ai — a research engine that pulls top channels and auto-surfaces the viral outliers + the
43	frameworks behind them (fastest path; connect it to Claude and let it do the heavy lifting).
44	- Composio Instagram tools — free/DIY: list a creator's media + insights from the Graph API.
45	- Or a plain list of reel URLs the user pastes.
46	3. Rank by views, compute each post's ratio vs the account median, and mark anything ~2-3x median as an
47	outlier ("blew up here").
48	4. For the top 3-5 outliers, run `reel-analyzer` (or ootto-watch — github.com/Ootto-AI/ootto-watch) to
49	break down hook / format / retention.
50	5. Synthesize: list the winning hook patterns, formats, and topics, then write 3 ready-to-shoot ideas for
51	the user's own account modeled on what actually worked.
52
53	## Output
54
55	A short research report:
56	- The spikes — which posts blew up and by how much (vs baseline).
57	- Why they worked — hook / format / retention breakdown per outlier.
58	- The playbook — the repeatable patterns + 3 original ideas for your niche.
59
60	## Honesty
61
62	Model the technique, never copy another creator's exact script, visuals, or caption. Cite the source
63	reels you studied. View counts come from real data (Composio / what the user provides) — never fabricate.
64
65	Part of the Ootto content-skills marketplace. Pairs with `reel-analyzer`, `going-viral`, and `reel-scripter`.
66