Crawl allow-listed personal archives and convert high-signal content into brain pages.
npx skills add https://github.com/weiping/gbrain-cn --skill archive-crawler
Please help me install this Agent Skill. Skill: archive-crawler Source: https://github.com/weiping/gbrain-cn/tree/main/skills/archive-crawler Command: npx skills add https://github.com/weiping/gbrain-cn --skill archive-crawler
archive-crawler turns scattered personal files (writing, ideas, relationships, and meaningful conversations) into searchable brain pages without you manually sorting through every folder and document.
gbrain.yml defines archive-crawler.scan_paths: to prevent over-scoping sensitive content.Tell the agent: "crawl my archive and surface the writing worth keeping," after you set archive-crawler.scan_paths: in gbrain.yml to your allowed folders.
High-intent search queries and answers about installing and using this skill.
Extracting personal writing from large file archives involves crawling allow-listed directories across local drives, Dropbox, and Gmail takeouts to filter for user-authored gold content while skipping system files and spam.
Yes, you can crawl Gmail takeout and mbox or PST exports for high-signal content. The crawler inventories mailbox exports, filters for meaningful conversations, and proposes items for interactive review.
To start crawling personal file archives safely, define your allowed folders in an explicit gbrain.yml allow-list under archive-crawler.scan_paths, then tell the agent to crawl your archive and surface writing worth keeping.
Yes, archive crawling requires an explicit allow-list to run safely. The crawler refuses to start unless gbrain.yml defines archive-crawler.scan_paths to prevent over-scoping sensitive content across your personal directories.
File triage during archive crawling works through a manifest-driven loop that inventories the directory tree, proposes a priority queue of gold content, captures user reactions, and never re-shows already triaged items.
During archive crawling, low-value items like system files, configuration files, spam, and binary-heavy artifacts are skipped unless explicitly requested, focusing only on user-authored writing and origin stories.
ngochuy13Scan personal file archives and ingest high-signal content into structured brain pages.
SigmacodeatSaves notes, files, and piped input into a searchable knowledge database.
coreyhaines31Capture, compile, query, and lint markdown-based Second Brain vaults.
NinatuziAutomate discovery and ingestion of personal content from file archives.