compound-knowledge

Search docs/knowledge/ for saved learnings that are relevant to the current topic. Returns insights, corrections, playbooks, and patterns from past sessions. This is the agent that closes the compounding loop.

Search plans/ and docs/solutions/ for related past work. Returns structured findings of what was decided, what data was used, and what worked. Use when /kw:plan needs to ground a new plan in prior context.

After a new learning is extracted, search docs/knowledge/ for entries that the new learning contradicts or supersedes. Returns candidates for update or removal. Prevents knowledge base from accumulating contradictions.

Use this agent when you need to verify that numbers, metrics, and data claims in knowledge work artifacts are accurate, sourced, and fresh. This includes checking that every number has a cited source, comparison baselines are explicit, data matches canonical definitions, and known caveats are acknowledged. <example>Context: The user has a plan that references conversion rates and revenue numbers.\nuser: "Check the data in this brief before I send it to the team"\nassistant: "I'll use the data-accuracy-reviewer agent to verify all numbers and sources"\n<commentary>Since the brief contains data claims, use the data-accuracy-reviewer to verify sources, freshness, and accuracy.</commentary></example><example>Context: The user is reviewing a strategy doc with metrics.\nuser: "Are these numbers right?"\nassistant: "Let me run the data-accuracy-reviewer to check every data claim against its source"\n<commentary>The user is specifically asking about data accuracy, which is this reviewer's specialty.</commentary></example>

Use this agent when you need to review knowledge work artifacts (plans, briefs, strategy docs, campaign proposals) for strategic alignment. This includes checking whether goals are explicit, hypotheses are falsifiable, success metrics are measurable, scope is proportional to impact, and the work serves stated objectives. <example>Context: The user has just created a plan with /workflows:plan.\nuser: "Review this plan before I share it with leadership"\nassistant: "I'll use the strategic-alignment-reviewer agent to check strategic alignment"\n<commentary>Since the user wants to validate a plan before sharing with stakeholders, use the strategic-alignment-reviewer to ensure goals, hypotheses, and metrics are sound.</commentary></example><example>Context: The user has written a campaign brief.\nuser: "Does this brief make sense strategically?"\nassistant: "Let me run the strategic-alignment-reviewer agent to evaluate this brief"\n<commentary>The user is asking about strategic soundness, which is exactly what this reviewer checks.</commentary></example>

Brain dump and compile knowledge before structuring a plan. Use when starting any non-trivial knowledge work — after a meeting, when tackling a new problem, or when you need to pull together what you know before planning.

Extract and save learnings from a completed knowledge work session. Saves to docs/knowledge/ so future plans automatically find them.

Gut-check what you know and don't know before proceeding. Use at any point to assess confidence, surface gaps, and decide whether to proceed or dig deeper.

Research past work and structure a knowledge work plan. Use when starting strategy docs, campaign plans, content briefs, research synthesis, or operational playbooks.

Multi-reviewer quality check for knowledge work. Runs strategic alignment and data accuracy reviewers on plans, briefs, and strategy docs.

Execute a knowledge work plan. Break it into tasks, do the work, and track what happened. Use after planning to actually produce the deliverables.