instagram-reels-analyzer
Skill0 starsChanged 48 days agoMITView on GitHub
Download, inspect, and summarize Instagram Reels locally with zero personal account risk and built-in rate-limiting guards. Use whenever the user provides an Instagram Reel link or asks to inspect, summarize, or transcribe an Instagram Reel.
In this repository8 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Zero Personal Credentials: Never asks for or uses personal Instagram credentials or cookies.
- Distinctive: line 19
Graceful Handling on Limit: If the rate limit is hit, informs the user of the exact reset cooldown without crashing.
- Distinctive: line 26
Run the downloader script passing the Reel URL and an output directory:
- Distinctive: line 45
Use local video inspection tools or ffmpeg/whisper to extract:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Instagram Reels Analyzer
Downloads public Instagram Reels safely without authenticating to any personal Instagram account (0% account ban risk), respects IP rate limits, and performs multimodal video, speech, and on-screen text analysis locally.
🛡️ Safety & Rate Limiting Rules
- Zero Personal Credentials: Never asks for or uses personal Instagram credentials or cookies. All downloads are performed anonymously.
- Built-in Rate Guard:
- Maximum 10 Reels per hour (rolling 60-minute window).
- Mandatory 15-second cooldown between consecutive downloads.
- Guard state is maintained in
~/.cache/reels_rate_limit.json.
- Graceful Handling on Limit: If the rate limit is hit, informs the user of the exact reset cooldown without crashing.
🚀 Execution Workflow
Step 1: Download with Rate Limiting
Run the downloader script passing the Reel URL and an output directory:
python3 scripts/download_reel.py "<INSTAGRAM_REEL_URL>" --output-dir "./output"The script outputs structured JSON:
{
"success": true,
"file_path": "/path/to/video.mp4",
"id": "C7xxxxxx",
"title": "...",
"uploader": "username",
"duration": 28
}Step 2: Multimodal Video & Audio Inspection
Use local video inspection tools or ffmpeg/whisper to extract:
- On-Screen Text (OCR): Subtitles, key text overlays, and hooks.
- Visual Progression: Scene transitions, product demonstrations, and visual actions.
- Spoken Dialogue: Full spoken transcript.
Step 3: Structured Output Format
### 🎬 Instagram Reel Breakdown
* **Creator:** @{uploader}
* **Duration:** {duration}s
* **Quota Remaining:** {remaining}/{max_per_hour}
---
#### 🎯 Hook & Core Thesis
{1-2 sentences explaining what the Reel is about and why it hooks attention}
#### 👁️ On-Screen Text (Captions / Overlays)
> "{Verbatim text overlays and on-screen cards}"
#### 🎞️ Visual Sequence & Scene Pacing
1. **00:00 - 00:03:** {Hook shot, visual setup, movement}
2. **00:04 - 00:15:** {Core demonstration / storytelling}
3. **00:16 - end:** {CTA, ending frame}
#### 💡 Key Takeaways
* {Insight 1}
* {Insight 2}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
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.

