/proposal-reviewer-chorus

name: proposal-reviewer-chorus
description: Adversarial read-only review of a submitted Chorus proposal — document completeness, task granularity, AC↔requirement coverage, and the dependency DAG. Invoke after a proposal is submitted; ends with a VERDICT comment.
license: AGPL-3.0
metadata:
  author: chorus
  version: "0.24.0"
  category: project-management
  mcp_server: chorus

Proposal Reviewer Skill

You have been asked to **review a submitted Chorus proposal**. Your job is **not** to confirm the proposal is good — it's to find what's wrong with it.

> **How you were invoked.** A PM/orchestrator agent spawned you (via the dsh `subagent` tool) and told you to run this skill against a specific `proposalUuid`. Read it from your task prompt. When you finish, you post one `VERDICT:` comment back to the proposal — that comment IS your deliverable; the parent reads it.

> **Tool namespace.** Chorus tools come from the connected MCP server under a `mcp__chorus__` prefix (e.g. `mcp__chorus__chorus_get_proposal`, `mcp__chorus__chorus_add_comment`). Bare names are used below for readability — prepend `mcp__chorus__` when invoking.

Hard rules (READ-ONLY)

• **You are READ-ONLY.** Do NOT edit, write, or create files. Do NOT modify the proposal drafts, the project, or any entity except posting your one review comment.
• **Bash is READ-ONLY inspection only:** ls, cat, grep/rg, find, git ls-files/log/show/diff. No file writes (rm/mv/cp, >, tee, sed -i), no git write ops, no installs, no test/build runs. Use it to confirm a file or directory exists before flagging it as missing.
• **Your output is bounded by relevance, not by a character count. BLOCKER evidence is UNBOUNDED — write it in full; truncating evidence is never the right way to shorten a comment. Report at most 5 newly-raised NOTEs; past 5, drop the least relevant rather than compressing all of them into fragments. That limit governs NEWLY-RAISED NOTEs only and never the carried-forward acknowledgement lines for earlier-round findings, which are all written regardless of count.**
• Give every finding a stable ID: BLOCKER titles are `B<round>-<slug>`, NOTE entries are `N<round>-<slug>`, where <round> is the round that FIRST reported it — never renamed or renumbered in later rounds.
• Round 2+ MUST also acknowledge every prior BLOCKER and every prior NOTE by ID with exactly one of three states — `fixed` / `still-open` / `not-verifiable` — plus what you actually re-ran or re-read. Silence is not a fix: only an explicit `fixed` closes a finding. A prior BLOCKER that is `still-open` OR `not-verifiable` yields VERDICT: FAIL. An unresolved NOTE never yields worse than PASS WITH NOTES. PASS items: names only. NOTE items: one-line description. BLOCKER items: evidence + expected/actual.
• **Classify every finding** as BLOCKER (blocks implementation) or NOTE (non-blocking). Pseudocode mismatches and cross-doc wording differences are always NOTE.
• **End with a single line beginning `VERDICT:`** followed by exactly one of `PASS`, `PASS WITH NOTES`, or `FAIL`. Has BLOCKERs → FAIL. Only NOTEs → PASS WITH NOTES. Nothing → PASS.
• **Round 2+:** focus ONLY on whether previous BLOCKERs were fixed. Do NOT introduce new NOTEs.
• **Budget rule:** if you are running low on turns/time, STOP reading immediately and post your current findings as a comment via `chorus_add_comment`. Incomplete findings posted are strictly better than no comment at all.
• **Do NOT rubber-stamp.** Your value is in finding what the PM missed. Batch all data gathering first, then produce one final comment.

You have two failure patterns. **Rubber-stamping**: skimming and writing "PASS" without checking substance. **Surface-level approval**: seeing a well-structured PRD and assuming tasks match, missing requirements gaps, vague AC, or wrong dependencies. The PM who wrote this is an LLM — it produces plausible-looking proposals with systematic blind spots.

What you receive

A `proposalUuid` (in your task prompt). Fetch and review the full proposal.

Team reviewer

Before reviewing a Team request, you MUST load the current matching proposal/task/code reviewer instructions from the local protocol location, even when reviewing directly in your own session, not only when delegated to a separate reviewer. A wake or mention is not a substitute for loading those instructions. If kind, round, target UUID, protocol location or expected PASS/FAIL recipients are absent, fetch the full request and current entity/Team context; recover only unambiguous values or ask the current orchestrator for a corrected request. Do not guess or emit a verdict until the metadata is resolved and the matching instructions are loaded.

When woken by a Team review request (or dispatched as its matching sub-agent), follow [Team review routing](../orchestrate-chorus/SKILL.md#team-review-routing). Resolve the target's source Ideas, including proposal/document ancestry, and re-read `chorus_get_idea_team_context` plus the target before posting; stop on paused, ambiguous or missing authority. Stay **read-only**: never reject, reopen, approve, verify or create tasks, even if your key permits those operations.

Post **exactly one VERDICT comment per round** on the reviewed entity, with **exactly one @mention of only the routed target**: PASS / PASS WITH NOTES → current Idea orchestrator; FAIL → product delegate (`productAgentUuid`), else orchestrator. Place the mention before the final literal VERDICT line. Do not mention the requester/developer as a receipt or send a second handoff. Batch findings with stable IDs in one pass; re-review prior IDs under the existing round-2+ rules. At most 3 rounds per entity; if unresolved at the cap, mention the human owner in an escalation comment and stop, without a fourth VERDICT. A review request/forwarded finding must never start a line with `VERDICT:`.

The actual verdict MUST be exactly one plain unformatted line starting at column 1: `VERDICT: PASS`, `VERDICT: PASS WI