agentleFS
r0undm1dn1ghty-starr0undm1dn1ghty-star/ds_content-radar/.claude/skills/instagram-research/SKILL.md

instagram-research

Skill0 starsChanged 35 days agoMITView on GitHub

Research high-performing Instagram content (posts and reels) from tracked accounts using instaloader (Apify-free). Identifies outlier content, analyzes top 5 videos with AI, and generates reports with actionable hook formulas.

  • Reads credentials

5 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read {RUN_FOLDER}/outliers.json and {RUN_FOLDER}/video-analysis.json, then generate {RUN_FOLDER}/report.md.

    line 107

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Instagram Research

Research high-performing Instagram posts and reels, identify outliers, and analyze top video content for hooks and structure.

Prerequisites

  • Instagram via instaloader: one-time python -m instaloader --login YOU, set IG_SESSION_USER + IG_SESSION_DIR in .env (no APIFY_TOKEN)
  • GEMINI_API_KEY environment variable or in .env
  • instaloader and google-genai Python packages
  • Accounts configured in .claude/context/instagram-accounts.md

Verify setup:

python3 -c "
import os
try:
    from dotenv import load_dotenv
    load_dotenv()
except ImportError:
    pass
import instaloader
from google import genai
assert os.environ.get('IG_SESSION_USER'), 'IG_SESSION_USER not set (run: python -m instaloader --login YOU)'
assert os.environ.get('GEMINI_API_KEY'), 'GEMINI_API_KEY not set'
" && echo "Prerequisites OK"

Workflow

1. Create Run Folder

RUN_FOLDER="instagram-research/$(date +%Y-%m-%d_%H%M%S)" && mkdir -p "$RUN_FOLDER" && echo "$RUN_FOLDER"

2. Fetch Content

python3 .claude/skills/instagram-research/scripts/fetch_instagram.py \
  --type reels \
  --days 30 \
  --limit 50 \
  --output {RUN_FOLDER}/raw.json

Parameters:

  • --type: "posts", "reels", or "stories"
  • --days: Days back to search (default: 30)
  • --limit: Max items per account (default: 50)

3. Identify Outliers

python3 .claude/skills/instagram-research/scripts/analyze_posts.py \
  --input {RUN_FOLDER}/raw.json \
  --output {RUN_FOLDER}/outliers.json \
  --threshold 2.0

Output JSON contains:

  • total_posts: Number of posts analyzed
  • outlier_count: Number of outliers found
  • topics: Top hashtags and keywords
  • accounts: List of accounts analyzed
  • outliers: Array of outlier posts with engagement metrics

4. Analyze Top Videos with AI

python3 .claude/skills/video-content-analyzer/scripts/analyze_videos.py \
  --input {RUN_FOLDER}/outliers.json \
  --output {RUN_FOLDER}/video-analysis.json \
  --platform instagram \
  --max-videos 5

Extracts from each video:

  • Hook technique and replicable formula
  • Content structure and sections
  • Retention techniques
  • CTA strategy

See the video-content-analyzer skill for full output schema and hook/format types.

5. Generate Report

Read {RUN_FOLDER}/outliers.json and {RUN_FOLDER}/video-analysis.json, then generate {RUN_FOLDER}/report.md.

Report Structure:

# Instagram Research Report

Generated: {date}

## Top Performing Hooks

Ranked by engagement. Use these formulas for your content.

### Hook 1: {technique} - @{username}
- **Opening**: "{opening_line}"
- **Why it works**: {attention_grab}
- **Replicable Formula**: {replicable_formula}
- **Engagement**: {likes} likes, {comments} comments, {views} views
- [Watch Video]({url})

[Repeat for each analyzed video]

## Content Structure Patterns

| Video | Format | Pacing | Key Retention Techniques |
|-------|--------|--------|--------------------------|
| @username | {format} | {pacing} | {techniques} |

## CTA Strategies

| Video | CTA Type | CTA Text | Placement |
|-------|----------|----------|-----------|
| @username | {type} | "{cta_text}" | {placement} |

## All Outliers

| Rank | Username | Likes | Comments | Views | Engagement Rate |
|------|----------|-------|----------|-------|-----------------|
[List all outliers with metrics and links]

## Trending Topics

### Top Hashtags
[From outliers.json topics.hashtags]

### Top Keywords
[From outliers.json topics.keywords]

## Actionable Takeaways

[Synthesize patterns into 4-6 specific recommendations]

## Accounts Analyzed
[List accounts]

Focus on actionable insights. The "Top Performing Hooks" section with replicable formulas should be prominent.

Quick Reference

Full pipeline:

RUN_FOLDER="instagram-research/$(date +%Y-%m-%d_%H%M%S)" && mkdir -p "$RUN_FOLDER" && \
python3 .claude/skills/instagram-research/scripts/fetch_instagram.py --type reels -o "$RUN_FOLDER/raw.json" && \
python3 .claude/skills/instagram-research/scripts/analyze_posts.py -i "$RUN_FOLDER/raw.json" -o "$RUN_FOLDER/outliers.json" && \
python3 .claude/skills/video-content-analyzer/scripts/analyze_videos.py -i "$RUN_FOLDER/outliers.json" -o "$RUN_FOLDER/video-analysis.json" -p instagram

Then read both JSON files and generate the report.

Engagement Metrics

Engagement Score: likes + (3 × comments) + (0.1 × views)

Outlier Detection: Posts with engagement rate > mean + (threshold × std_dev)

Engagement Rate: (score / followers) × 100

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.