Brain health checks: back-link enforcement, citation audit, filing validation, stale info detection, orphan pages, and benchmarks. Use when asked to check brain health, run maintenance, or audit quality.
75%
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-variants/gbrain-coding/skills/maintain/SKILL.mdThe canonical home for this skill is maintain in garrytan/gbrain
The 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 is mostly a brain-maintenance checklist, but it tells the agent to install a persistent autopilot daemon (`gbrain autopilot --install`) and run schema migrations with `--yes`, which change machine state without explicit consent, so I flag it at moderate severity.
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 dream-cycle synthesize phase (triggered by "run dream" or "process today's session") ingests session transcripts from the user's configured `dream.synthesize.session_corpus_dir`, which can carry outsider-authored text the agent fetched or the user pasted during those sessions, but no outsider can directly submit into that directory.
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.