Instagram Research
Scrape tracked Instagram accounts with Apify, flag outliers, and get Gemini-backed hook reports for content ideas.
Overview
instagram-research is an agent skill most often used in Idea (also Grow, content) that scrapes tracked Instagram accounts via Apify and analyzes top reels with Gemini for hook formulas.
Install
npx skills add https://github.com/bradautomates/head-of-content --skill instagram-researchWhat is this skill?
- Apify Instagram Scraper for posts and reels from configured accounts
- Identifies outlier performers and analyzes top videos with Gemini
- Reports include actionable hook formulas for reels
- Triggers cover trending reels, competitor IG analysis, and niche research
- Requires APIFY_TOKEN, GEMINI_API_KEY, and instagram-accounts.md context
- Top 5 videos analyzed with AI in reporting flow
Adoption & trust: 828 installs on skills.sh; 111 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You are guessing Instagram hooks without data on what reels and posts actually outperform in your niche.
Who is it for?
Solo content operators validating narrative and reel formats before filming or scheduling a growth sprint.
Skip if: Builders without Apify and Gemini credentials, or brands not using Instagram as a research channel.
When should I use this skill?
User asks for Instagram research, trending reels, IG competitor analysis, or trigger phrases like “what’s working on instagram”.
What do I get? / Deliverables
You receive outlier-focused reports with analyzed top videos and reusable hook patterns grounded in scraped account performance.
- Outlier identification report
- Top-video analysis with hook formulas
- Actionable content ideas from IG trends
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Primary shelf is Idea because the workflow discovers what performs in a niche before you commit to a content calendar or product angle. Competitor and trend research on Instagram maps directly to the research subphase—not publishing tooling.
Where it fits
Scan tracked accounts to see which reel formats spike before you pick a product story.
Quarterly refresh of outlier reels to update your hook playbook for new campaigns.
How it compares
Research and analysis integration—not a social scheduling or posting automation skill.
Common Questions / FAQ
Who is instagram-research for?
Indie founders and content leads who track competitor or inspiration accounts and want agent-driven Instagram trend reports.
When should I use instagram-research?
Use in Idea when exploring a niche or audience, in Validate when testing messaging angles, and in Grow when refreshing hooks—whenever triggers like “instagram research” or “find viral reels” apply.
Is instagram-research safe to install?
It uses paid third-party APIs and stores tokens in env; review Security Audits on this page and rotate APIFY_TOKEN and GEMINI_API_KEY if you share the repo.
SKILL.md
READMESKILL.md - Instagram Research
# Instagram Research Research high-performing Instagram posts and reels, identify outliers, and analyze top video content for hooks and structure. ## Prerequisites - `APIFY_TOKEN` environment variable or in `.env` - `GEMINI_API_KEY` environment variable or in `.env` - `apify-client` and `google-genai` Python packages - Accounts configured in `.claude/context/instagram-accounts.md` Verify setup: ```bash python3 -c " import os try: from dotenv import load_dotenv load_dotenv() except ImportError: pass from apify_client import ApifyClient from google import genai assert os.environ.get('APIFY_TOKEN'), 'APIFY_TOKEN not set' assert os.environ.get('GEMINI_API_KEY'), 'GEMINI_API_KEY not set' " && echo "Prerequisites OK" ``` ## Workflow ### 1. Create Run Folder ```bash RUN_FOLDER="instagram-research/$(date +%Y-%m-%d_%H%M%S)" && mkdir -p "$RUN_FOLDER" && echo "$RUN_FOLDER" ``` ### 2. Fetch Content ```bash 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 ```bash 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 ```bash 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:** ```markdown # 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 | |--