Connect a ChatGPT or Claude account and sync its conversation history into the brain automatically. Cookie paste-in is the primary lane; sync is incremental (watermark + trailing-window gap-heal), and can run on a schedule via autopilot or host cron. Distinct from the export-file lane (that lives in conversation-archive) — this is the LIVE, account-connected, auto-scraping path.
79%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
Fix and improve this skill with Tessl
tessl review fix ./plugin/skills/chat-connectors/SKILL.mdThe skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
The skill has the agent run `gbrain autopilot --install`, which sets up persistent launchd/systemd/crontab scheduler entries, and it suggests a host cron line, both of which change machine state; no sudo or system-wide account changes are requested, and the credential handling is carefully scoped.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required sync path automatically ingests the user's ChatGPT and Claude conversation transcripts, which can contain web-derived text an attacker published and the assistant retrieved, but an outsider cannot directly post into the account's history, so exposure depends on the user's own browsing and is not forced delivery.
garrytan/gbrain
f4d1866
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.