Proposal

Proposal Skill

This skill covers the Planning stage of the AI-DLC workflow: creating Proposals that contain document drafts (PRD, tech design) and task drafts with dependency DAGs, then submitting them for Admin review.

Overview

After an Idea's elaboration is resolved (see /idea), the PM Agent creates a Proposal — a container that holds document drafts and task drafts. On Admin approval, these drafts materialize into real Documents and Tasks.

Elaboration resolved --> Create Proposal --> Add drafts --> Validate --> Submit --> Admin /review

Tools

Proposal Management:

Document Drafts:

Task Drafts:

Post-Approval (tasks exist):

Shared tools (checkin, query, comment, search, notifications): see /chorus

Workflow

Step 1: Create an Empty Proposal

Resolve the spec mode (Step 1.5) BEFORE this create. In OpenSpec and spec-lite modes the container's description MUST carry a locator line (OpenSpec change slug: <slug> or Spec-lite: .chorus/specs/<slug>/<YYYY-MM-DD>-<change-slug>/), and description can only be set at creation — so decide the mode + slug/dated-path first and include that line in this single call. Do NOT create a bare container and then realize you needed the line (that would strand it without the locator or force a duplicate). Free-form mode omits any locator line.

Recommended approach: Create the proposal container first (with the mode's locator line in description when applicable), then incrementally add document and task drafts one by one.

chorus_pm_create_proposal({
  projectUuid: "<project-uuid>",
  title: "Implement <feature name>",
  description: "Analysis and implementation plan for Idea #xxx\n\n<locator line here in OpenSpec / spec-lite mode>",
  inputType: "idea",
  inputUuids: ["<idea-uuid>"]
})

Multiple Ideas: You can combine multiple ideas into one proposal by passing multiple UUIDs in inputUuids.

A theme cannot be a proposal input — chorus_pm_create_proposal rejects any input idea with isContainer = true. Derive a child idea from the theme and write the proposal on the child instead. (See the theme-ideas section of the /idea skill.)

Step 1.5: Select spec mode

The spec mode is already computed for you by the SessionStart hook (bin/resolve-spec-mode.sh) — do NOT re-derive it. Read the ## Spec Mode section of your SessionStart context: it states CHORUS_SPEC_MODE=<lite|openspec|off> plus a one-line routing note. (Spawned without that context? Source the same bin/resolve-spec-mode.sh to get SPEC_MODE/SPEC_FAIL — never hand-roll the rule.) Just act on that value:

• If the section says the requested mode cannot be honored (e.g. CHORUS_SPEC_MODE=openspec but OpenSpec isn't usable — it prints "cannot be honored" with a config-conflict or install-hint reason), halt and surface that reason; do not fall back.

• Otherwise branch on the stated mode:

• resolved = spec-lite → load the spec-lite skill (skills/spec-lite/SKILL.md) and follow it: pick $SLUG (a capability/feature name — .chorus/specs/<slug>/ holds the durable local spec spec.md, edited in place across changes, not one folder per change). Ensure the durable spec.md exists (local-only, no Chorus ids — Intent / plain-prose Requirements + - [ ] acceptance points / Non-goals; use the spec-lite skill's inline durable-spec template) and update it in place to the new truth. Create this change's dated folder .chorus/specs/<slug>/<YYYY-MM-DD>-<change-slug>/ and write its synced Chorus-typed docs — prd.md (primary), plus tech_design.md etc. only if warranted (shape = the spec-lite skill's inline dated-folder document template). Put the literal locator line Spec-lite: .chorus/specs/<slug>/<YYYY-MM-DD>-<change-slug>/ in the Step 1 create description (that's why the mode is resolved before creating), then mirror each dated-folder <type>.md to its persistent Document (chorus_pm_add_document_draft --arg-file the first time a doc is authored, chorus_pm_update_document --arg-file after) via chorus mcp call … --arg-file content=.chorus/specs/<slug>/<YYYY-MM-DD>-<change-slug>/<type>.md. spec.md is never mirrored. Skip Step 2 below — the file-fill mirror replaces inline drafting for these documents. (Add tasks via chorus_pm_add_task_draft as usual — there is no tasks.md.)

• resolved = OpenSpec (the ## Spec Mode section shows CHORUS_OPENSPEC_ACTIVE=1 — i.e. CHORUS_SPEC_MODE=openspec or unset, with OpenSpec usable) → follow openspec-aware §3. Pick $SLUG, scaffold openspec/changes/<slug>/, author proposal.md / design.md / specs/<capability>/spec.md locally, then put the literal line OpenSpec change slug: <slug> in the Step 1 create description (mode resolved before creating), and mirror each local file into a document draft.

  ⛔ Mandatory in OpenSpec mode: mirror calls fill content from the local file — prefer chorus mcp call … --arg-file content=<file>, falling back to the chorus-api.sh wrapper with json_encode_file when chorus is not on PATH — see openspec-aware §3.6. Do not call chorus_pm_add_document_draft directly from the MCP harness with a hand-typed content field. Re-typing thousands of lines through the LLM burns 20k+ content tokens per proposal and breaks byte-equality with the local source of truth (openspec-aware §2 Rule 1 explains the full reasoning). Skip Step 2 below when in OpenSpec mode — the file-fill flow in openspec-aware §3.6 replaces it for documents.

• resolved = free-form (explicit CHORUS_SPEC_MODE=off) → proceed with Step 2 unchanged. Author drafts inline as free-form Markdown via direct MCP chorus_pm_add_document_draft.

Step 2: Add Document Drafts

Add document drafts one at a time:

# Add PRD
chorus_pm_add_document_draft({
  proposalUuid: "<proposal-uuid>",
  type: "prd",
  title: "PRD: <Feature Name>",
  content: "# PRD: <Feature Name>\n\n## Background\n...\n## Requirements\n..."
})

# Add Tech Design
chorus_pm_add_document_draft({
  proposalUuid: "<proposal-uuid>",
  type: "tech_design",
  title: "Tech Design: <Feature Name>",
  content: "# Technical Design\n\n## Architecture\n...\n## Implementation\n..."
})

Document types: prd, tech_design, adr, spec, guide

Step 3: Add Task Drafts

Add task drafts one at a time. The response returns the new draft's draftUuid — use it directly for dependsOnDraftUuids in subsequent drafts.

acceptanceCriteriaItems is required — every task draft must include at least one item with a non-blank description, or the call is rejected. Use the structured acceptanceCriteriaItems array (the legacy acceptanceCriteria Markdown string does not satisfy the requirement).

# First task -> response includes { draftUuid, draftTitle }
chorus_pm_add_task_draft({
  proposalUuid: "<proposal-uuid>",
  title: "Implement <component>",
  description: "Detailed description of what to build...",
  priority: "high",
  storyPoints: 3,
  acceptanceCriteriaItems: [
    { description: "Criteria 1", required: true },
    { description: "Criteria 2", required: true }
  ]
})

# Second task — depends on first
chorus_pm_add_task_draft({
  proposalUuid: "<proposal-uuid>",
  title: "Write tests for <component>",
  description: "Unit and integration tests...",
  priority: "medium",
  storyPoints: 2,
  acceptanceCriteriaItems: [
    { description: "Test coverage > 80%", required: true }
  ],
  dependsOnDraftUuids: ["<draftUuid-from-first-task>"]
})

To edit a draft's criteria later via chorus_pm_update_task_draft, pass a non-empty acceptanceCriteriaItems to replace them; omit the field to leave them unchanged. The field cannot be used to clear criteria.

Task priority: low, medium, high

Step 4: Review and Refine Drafts

# Review current state. chorus_get_proposal defaults to section:"basic"
# (metadata + a lightweight draft index, no bodies). Use section:"full" to
# see every draft's content, or section:"documents"/"tasks" for one kind.
chorus_get_proposal({ proposalUuid: "<proposal-uuid>", section: "full" })

# Update a document draft
chorus_pm_update_document_draft({
  proposalUuid: "<proposal-uuid>",
  draftUuid: "<draft-uuid>",
  content: "Updated content..."
})

# Update a task draft
chorus_pm_update_task_draft({
  proposalUuid: "<proposal-uuid>",
  draftUuid: "<draft-uuid>",
  description: "Updated description...",
  dependsOnDraftUuids: ["<other-draft-uuid>"]
})

# Remove a draft
chorus_pm_remove_task_draft({
  proposalUuid: "<proposal-uuid>",
  draftUuid: "<draft-uuid>"
})

Step 5: Validate and Submit

Before submitting, validate to preview issues:

chorus_pm_validate_proposal({ proposalUuid: "<proposal-uuid>" })

Returns { valid, issues } with error, warning, and info levels. Fix errors before submitting.

When validation passes:

chorus_pm_submit_proposal({ proposalUuid: "<proposal-uuid>" })

This changes the status from draft to pending. An Admin will review it (see /review).

Add a comment explaining your reasoning:

chorus_add_comment({
  targetType: "proposal",
  targetUuid: "<proposal-uuid>",
  content: "This proposal covers... Key decisions: ..."
})

Step 6: Handle Feedback

After submission, a chorus:proposal-reviewer may run and post a VERDICT comment. If the VERDICT is FAIL, or an Admin rejects the proposal, you need to revise and resubmit.

IMPORTANT: A proposal in pending status cannot be edited. You must reject it first to return it to draft status before editing any drafts.

1. Read feedback:

   chorus_get_proposal({ proposalUuid: "<proposal-uuid>", section: "full" })
   chorus_get_comments({ targetType: "proposal", targetUuid: "<proposal-uuid>" })
   

   Identify BLOCKERs from the reviewer VERDICT or rejection note.

2. Reject the proposal (self-reject your own, or ask admin to reject someone else's):

   chorus_pm_reject_proposal({
     proposalUuid: "<proposal-uuid>",
     reviewNote: "Reviewer FAIL. Fixing BLOCKERs: <list>"
   })
   

   This returns the proposal to draft status. PM agents can only reject their own proposals; admin agents can reject any proposal.

3. Revise the drafts:

   chorus_pm_update_document_draft({ proposalUuid: "<proposal-uuid>", draftUuid: "<uuid>", content: "..." })
   chorus_pm_update_task_draft({ proposalUuid: "<proposal-uuid>", draftUuid: "<uuid>", ... })
   

4. Resubmit:

   chorus_pm_submit_proposal({ proposalUuid: "<proposal-uuid>" })
   

Step 7: Post-Approval

When the Admin approves:

• Document drafts become real Documents
• Task drafts become real Tasks (status: open, ready for developers)
• The Idea's displayed status is automatically derived from Proposal and Task progress -- no manual update needed

Step 8: Manage Task Dependencies (Optional)

After tasks are created, you can manage dependencies:

Batch create tasks with intra-batch dependencies:

chorus_create_tasks({
  projectUuid: "<project-uuid>",
  tasks: [
    { draftUuid: "draft-db", title: "Create database schema", priority: "high", storyPoints: 2 },
    { draftUuid: "draft-api", title: "Implement API endpoints", priority: "high", storyPoints: 4, dependsOnDraftUuids: ["draft-db"] },
    { title: "Write integration tests", priority: "medium", storyPoints: 2, dependsOnDraftUuids: ["draft-api"] }
  ]
})

Add/remove dependencies on existing tasks:

chorus_update_task({ taskUuid: "<task-B-uuid>", addDependsOn: ["<task-A-uuid>"] })
chorus_update_task({ taskUuid: "<task-B-uuid>", removeDependsOn: ["<task-A-uuid>"] })

Dependencies are validated: same project, no self-dependency, no cycles (DFS detection).

Step 9: Assign Tasks to Developer Agents (Optional)

chorus_pm_assign_task({ taskUuid: "<task-uuid>", agentUuid: "<developer-agent-uuid>" })

# Optional: pin the task to a specific (agent, host, cwd) AgentInstance
chorus_pm_assign_task({ taskUuid: "<task-uuid>", agentUuid: "<developer-agent-uuid>", instanceUuid: "<agent-instance-uuid>" })

• Task must be open or assigned
• Target agent must have task: ["write"] permission
• Pass instanceUuid to pin the task to a specific online instance (assigns as agent_instance); omit it for a plain agent assignment that inherits the root idea's pinned instance at wake time

Document Writing Guidelines

PRD Structure

# PRD: <Feature Name>

## Background
Why this feature is needed.

## Requirements
### Functional Requirements
- FR-1: ...

### Non-Functional Requirements
- NFR-1: ...

## User Stories
- As a <role>, I want <action>, so that <benefit>

## Out of Scope
What is NOT included.

Tech Design Structure

# Technical Design: <Feature Name>

## Overview
High-level approach.

## Architecture
System design, component interactions.

## Data Model
Schema changes, new tables.

## API Design
New/modified endpoints.

## Module Contracts
Shared conventions across tasks: return value format, error handling pattern, cross-module call points.

## Implementation Plan
Step-by-step implementation order.

## Risks & Mitigations
Potential issues and how to address them.

Task Writing Guidelines

Good tasks are:

• Module-scoped — One cohesive functional module per task, not a single function or file
• Testable — Clear, cohesive acceptance criteria are required on every task (at least one non-blank item; max 6; group related checks into one criterion but list key coverage, e.g. "All tests pass: service layer unit tests, API integration tests, edge case handling")
• Sized — 1-8 story points (hours of agent work)
• Ordered — Use dependsOnDraftUuids / dependsOnTaskUuids to express execution order
• Descriptive — Include enough context for a developer agent to start without questions. For tasks with cross-module dependencies, reference the tech design's Module Contracts in the AC
• Integration checkpoints — For DAGs with 4+ tasks, include at least one integration checkpoint task at a convergence point whose AC requires end-to-end execution of preceding modules together
• Hallucination-aware — When tasks involve external dependencies, note in the task description that developers should verify specifics (API signatures, CLI flags, config keys, model IDs, etc.) against official docs rather than relying on LLM memory

Task Granularity

Each task should correspond to an independently runnable and testable functional module — not a single function, file, or API endpoint. Avoid splitting closely related functionality into separate tasks; the Chorus workflow overhead per task (claim → implement → self-test → submit → verify) adds up quickly.

Bad → Good examples:

• Bad: Book Search + Book CRUD (2 tasks) → Good: Book Management (1 task covering CRUD + Search for the same entity)
• Bad: Chart Rendering + Statistics Calculation (2 tasks) → Good: Data Analytics (1 task covering stats + visualization as one module)

Tips

• Keep PRD focused on what and why; tech design focused on how
• Break large features into cohesive module-scoped tasks — but avoid over-splitting related functionality into too many tiny tasks
• Add storyPoints to help prioritize and estimate effort
• Keep acceptance criteria cohesive — group related verifications into one item rather than listing each check separately
• Always set up task dependency DAG — tasks without dependencies are assumed parallelizable
• When multiple tasks share data formats or call each other, define contracts in the tech design before writing task AC
• When combining multiple ideas, explain how they relate in the proposal description

Next

• After submission, an Admin will review using /review
• After approval, Developers claim tasks using /develop
• For Idea elaboration, see /idea
• For platform overview, see /chorus