From brain-os
Enters deep thinking mode for open-ended reflection, idea exploration, pattern finding, and vault content analysis. Supports sub-commands for digesting agent output, challenging beliefs, surfacing implied ideas, tracing idea evolution, and connecting domains.
How this skill is triggered — by the user, by Claude, or both
Slash command
/brain-os:thinkThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**IMPORTANT: Before starting, check for un-audited knowledge.**
IMPORTANT: Before starting, check for un-audited knowledge.
Run: python3 ${CLAUDE_PLUGIN_ROOT}/skills/audit/scripts/audit.py {vault}/knowledge/raw --status
If any book shows ❌ or 👁️, warn: "⚠️ Un-audited knowledge: [book]. Run /audit to verify."
Vault path: Read from ${CLAUDE_PLUGIN_ROOT}/brain-os.config.md
/think Open-ended reflection and exploration
/think digest Review agent-output, promote insights to proper vault zones
/think challenge <topic> Stress-test a belief against vault evidence
/think emerge Surface ideas the vault implies but never stated
/think drift Compare stated goals vs actual behavior (30-60 days)
/think trace <topic> Track how an idea evolved over time
/think connect <A> <B> Find bridges between two domains
/think ideas Brainstorm across all vault domains
/think ghost <question> Answer a question as the user would
If no angle given, show the menu above and ask: "What's on your mind?"
{vault}/thinking/, {vault}/daily/, and {vault}/context/{vault}/thinking/agent-output/YYYY-MM-DD-<angle>-<topic>.mdReview agent-output files and promote insights to proper thinking/ zones:
{vault}/thinking/agent-output/ (skip README.md)📂 Agent Output (N files)
1. [filename] — summary
→ Suggested zone: patterns/ | ideas/ | connections/ | reflections/ | principles/
→ Key insight: one-liner
2. [filename] — summary
→ Suggested zone: ...
→ Key insight: ...
agent-output/ to the target zone (rename if needed for clarity)promoted: YYYY-MM-DD, update zone fieldRules:
YYYY-MM-DD-topic.md (drop the grill-insights- prefix)Pressure-test a belief or decision:
Surface ideas the vault implies but user never explicitly stated:
Compare stated intentions vs actual behavior:
Track how an idea evolved over time:
Find bridges between two domains:
Comprehensive idea generation:
Answer a question as the user would:
Follow skill-spec.md § 11. Append to {vault}/daily/skill-outcomes/think.log:
{date} | think | {action} | ~/work/brain-os-plugin | thinking/agent-output/{date}-{angle}-{topic}.md | commit:{hash} | {result}
action: think, digest, challenge, emerge, drift, trace, connect, ideas, or ghostresult: pass if output written, partial if gaps flagged or vault data sparse, fail if no relevant vault content foundargs="{angle} {topic}"npx claudepluginhub sonthanh/brain-os-pluginSearches an Obsidian vault exhaustively on a topic, surfaces non-obvious patterns and contradictions, and challenges the user to generate original synthesis.
Reviews conversation, extracts learnings, and persists to auto-memory or vault. Run after substantial work sessions to avoid knowledge rot.
Queries bundled research knowledge graph for knowledge systems methodology guidance via 3-tier KB (WHY claims, HOW docs, examples) with cited, practical answers.