From second-brain
Trigger a structured Opus-level advisor brief on a non-trivial topic. Returns intent read, prompt enrichment, clarifying questions, relevant specialists, and risk flags. Use for ambiguous prompts, design decisions, or multi-domain work where the persona's prior context matters. Costs ~$0.11/call with Opus.
How this skill is triggered — by the user, by Claude, or both
Slash command
/second-brain:think [topic][topic]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Call `persona_think` with `$ARGUMENTS` as the prompt.
Call persona_think with $ARGUMENTS as the prompt.
If the tool returns a brief, format it as a tight block:
clarifying_questions (if any)relevant_specialists (if any)risk_flags (if any)Omit any field that is empty. If all fields are empty, say "(no notable signal — proceed as planned)".
Spend is informational since 0.24.45 — no budget gate exists; the brief always runs. Mention the per-call cost (~$0.11 on Opus-class models) if the user asks about cost.
If the response has error, surface the error once and proceed without the brief.
/second-brain:query instead)The persona-context.sh hook also routes the /? prefix on a user prompt to this same backing tool — /? topic is shorthand for invoking this skill.
npx claudepluginhub cain-ish/claude-code-plugin --plugin second-brainCreates bite-sized, testable implementation plans from specs or requirements, with file structure and task decomposition. Activates before coding multi-step tasks.