Knowledge Plan

Phase 1 of the inverted pipeline (plan → curate → fetch → ingest → compose → verify → finalize). This skill decomposes a research topic into a structured plan that downstream phases (knowledge-curate, knowledge-fetch, …) consume.

Read ${CLAUDE_PLUGIN_ROOT}/references/inverted-pipeline.md once at the start of a session to anchor on the phase boundaries and the contract.

When to run

• User wants to start a new research run on a topic against an existing bound knowledge base
• User explicitly invokes /cogni-knowledge:knowledge-plan

Never run when

• No binding.json exists at the resolved knowledge root — offer knowledge-setup first. Plan output lives in a fresh project directory under the bound knowledge root; without a binding there is no anchor.
• The user wants the legacy research+ingest flow — that chain is archived under _archive/ (see _archive/README.md). The inverted pipeline is the only live path; if they truly want a one-shot report outside the knowledge base, point at cogni-research:research-setup.

Parameters