What problem does it solve? Research findings, external document reviews, and cross-agent insights often go straight into code changes without evaluation, causing unvetted structural decisions. This Skill routes every finding through a governed pipeline before it can affect implementation. ## Core Features & Use Cases - Structured Research Submission: Submit findings via the Agent Hub UI at http://127.0.0.1:13020/?tab=agent-loop or by POSTing to /api/agent-research with title, body, source agent, and target agents. - Mandatory Evaluation Pipeline: Enforces the INTAKE → BRAINSTORM → EVALUATE → PROMOTE sequence, requiring at least one brainstorm note and a composite score of 65 or higher before promotion. - Governance Rules: Classifies external pastes as EXTERNAL_CRITIC (L1) and blocks workstream changes based on research alone (L3). - Use Case: After pasting a ChatGPT analysis that suggests reordering build steps, submit it through the hub so it is brainstormed and scored before any code changes are made. ## Quick Start Submit my completed research findings to the Sina Agent Hub research pipeline for brainstorming and evaluation.