Name: Popular Platform Data Collection Skill
Availability: InStock
Author: Agensi

See it in action

You say

I have a DATATOOL export for a public or authorized video post. Validate the metadata, video, cover image, page copy, and comments in the task folder. Transcribe the complete video audio locally with Whisper, anonymize comment identities, package the Chinese Excel, transcript TXT, segmented JSON, SRT, and SHA-256 manifest into a ZIP file, and verify the final archive.

Your agent does

Validation completed for the authorized task folder. The package includes the exported media, cover image, page copy, metadata, an anonymized comments worksheet, a full video transcript, segmented JSON, SRT subtitles, a Chinese Excel workbook, and a SHA-256 manifest.

ZIP verification passed. File paths, CRC values, file lists, byte counts, and hashes are consistent. No browser cookies, passwords, tokens, or raw comments were included.

About this skill

Popular Platform Data Collection Skill is a local-first workflow for authorized content research, content archiving, competitor analysis, and first-party account backups.

It guides users to manually export public, owned, or clearly authorized videos, cover images, page copy, tags, engagement data, and comments through DATATOOL. The Skill validates metadata, authorization details, public URLs, capture times, comment files, and video streams before packaging the results.

When OpenAI Whisper is installed, the Skill can transcribe the complete video audio track locally and generate transcript TXT files, segmented JSON, SRT subtitles, and an Excel transcript worksheet. It can also anonymize comment identities and create a standardized Chinese ZIP package containing metadata, media, page content, comments, transcripts, subtitles, usage instructions, file lists, byte counts, and SHA-256 hashes.

The workflow does not directly control DATATOOL, store browser cookies or passwords, bypass captchas, private-content restrictions, paywalls, login controls, or anti-bot systems. Videos are processed locally by default and are not uploaded to third-party transcription services.

This Skill is designed for content researchers, marketing and social-media teams, video creators, brand-content managers, data-archiving teams, and users who want to execute a repeatable workflow through Codex or another compatible agent.