Save any thought or content into the brain via one CLI command. The single human-facing entrypoint that replaces "put_page vs commit-then-sync vs autopilot-wait" with one command that just works.
71%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./plugin/skills/capture/SKILL.mdThe canonical home for this skill is capture in garrytan/gbrain
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 workflow saves user-supplied text (inline, `--file`, or `--stdin`) and never fetches or searches outsider content itself, but pasted "article snippets" may originate from web pages the agent or user pulled in, so outsider text could reach the agent indirectly.
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.