evaluatelisted

# Evaluate - PDCA Evaluation & Improvement A skill that analyzes sales activity result data, reports on performance, and applies the improvements it still owns — targeting definitions / search keywords (hypothesis generation that steers /build-list) and the discovery-strategy portfolio (`## Prospect Discovery Sources`). Messaging (message angles), channel ranking, and the outbound selection order (measured targeting lifts × ordering score) are optimized deterministically by the daily lever tick; evaluate **reads and narrates** those, it does not rewrite them as strategy prose and it does not touch selection order. **Before starting:** `Read` `${CLAUDE_PLUGIN_ROOT}/references/workspace-conventions.md` and follow the cross-cutting conventions there (data storage, MCP error handling, document writes, output discipline). ## Steps ### 1. Data Collection - Project ID: `$0` (required) In parallel, call: - `mcp__plugin_leadace_api__get_eval_data` with `projectId: "$0"` - `mcp__plugin_leadace_api__get_rejection_feedback_summary` with `projectId: "$0"`, `windowDays: 30`, `scope: "tactical"` - `mcp__plugin_leadace_api__get_lever_state` with `projectId: "$0"` — current message-variant draw weights, channel affinity, targeting lifts, and per-variant maturity (read-only) - `mcp__plugin_leadace_api__get_lever_decisions` with `projectId: "$0"` — the daily tick's decision history (newest first) for trend narration If `get_eval_data` returns a "Project not found" error, instruct the use