ln-200-scope-decomposer

What this skill does

> **Paths:** File paths (`references/`, `../ln-*`) are relative to this skill directory.

# Scope Decomposer (Top Orchestrator)

**Type:** L1 Top Orchestrator
**Category:** 2XX Planning

Top-level orchestrator for complete initiative decomposition from scope to User Stories through Epic and Story coordinators.

## Purpose

### What This Skill Does

Coordinates the complete decomposition pipeline for new initiatives:
- Auto-discovers Team ID from kanban_board.md
- **Phase 1:** Discovery (Team ID)
- **Phase 2:** Epic Decomposition (delegates to ln-210-epic-coordinator)
- **Phase 3:** Story Decomposition Loop (precompute read-only inputs in batch, then delegate to ln-220-story-coordinator per Epic sequentially)
- **Phase 4:** RICE Prioritization Loop (optional, precompute child runtime inputs, then delegate to ln-230-story-prioritizer per applicable Epic sequentially)
- **Phase 5:** Summary (total counts + next steps)

## Runtime Contract

**MANDATORY READ:** Load `references/coordinator_runtime_contract.md`, `references/scope_decomposition_runtime_contract.md`, `references/scope_decomposition_summary_contract.md`, `references/epic_plan_summary_contract.md`, `references/coordinator_summary_contract.md`

Runtime family: `scope-decomposition-runtime`

Identifier:
- scope identifier

Phases:
1. `PHASE_0_CONFIG`
2. `PHASE_1_DISCOVERY`
3. `PHASE_2_EPIC_DECOMPOSITION`
4. `PHASE_3_STORY_LOOP`
5. `PHASE_4_PRIORITIZATION_LOOP`
6. `PHASE_5_FINALIZE`
7. `PHASE_6_SELF_CHECK`

Coordinator summary contract:
- consume `epic-plan` from `ln-210`
- consume `story-plan` from `ln-220`
- consume `story-prioritization-worker` from `ln-230`
- write final `scope-decomposition` coordinator summary during `PHASE_5_FINALIZE`

## Worker Invocation (MANDATORY)

**Host Skill Invocation:** `Skill(skill: "...", args: "...")` is mandatory delegation.
- Claude: call the Skill tool exactly as shown.
- Codex: if no Skill tool exists, locate the named skill in available skills, read its `SKILL.md`, treat `args` as `$ARGUMENTS`, execute that skill workflow, then return here with its result/artifact.
- Do not inline worker logic or mark the worker complete without executing the target skill.

Workers delegated by phase:

- Phase 2: `ln-210-epic-coordinator` — Epic decomposition (CREATE/REPLAN)
- Phase 3: `ln-220-story-coordinator` — Story decomposition per Epic (sequential)
- Phase 4: `ln-230-story-prioritizer` — Optional RICE prioritization per Epic (sequential)

```text
# Phase 2 — Epic decomposition
node references/scripts/epic-planning-runtime/cli.mjs start --identifier {scopeIdentifier} --manifest-file {epicManifestPath}
Skill(skill: "ln-210-epic-coordinator", args: "{scopeIdentifier} --manifest-file {epicManifestPath}")
node references/scripts/scope-decomposition-runtime/cli.mjs record-epic-summary --identifier {scopeIdentifier} --payload-file {epicSummaryArtifactPath}

# Phase 3 — Story decomposition (per Epic, sequential)
node references/scripts/story-planning-runtime/cli.mjs start --epic {epicId} --manifest-file {storyManifestPath}
Skill(skill: "ln-220-story-coordinator", args: "{epicId} --manifest-file {storyManifestPath}")
node references/scripts/scope-decomposition-runtime/cli.mjs record-story-summary --identifier {scopeIdentifier} --payload-file {storySummaryArtifactPath}

# Phase 4 — RICE prioritization (optional, per Epic, sequential)
node references/scripts/planning-worker-runtime/cli.mjs start --skill ln-230 --identifier {identifier} --manifest-file {prioritizationManifestPath} --run-id {childRunId} --summary-artifact-path {childSummaryArtifactPath}
child_run = { skill, run_id, identifier, summary_artifact_path }
childSummaryArtifactPath = .hex-skills/runtime-artifacts/runs/{parent_run_id}/story-prioritization-worker/ln-230--{identifier}.json
Skill(skill: "ln-230-story-prioritizer", args: "{identifier} --epic {epicId} --run-id {childRunId} --summary-artifact-path {childSummaryArtifactPath}")
Read {childSummaryArtifactPath}
node references/scripts/scope-decomposition-runtime/cli.mjs record-prioritization-summary --identifier {scopeIdentifier} --payload-file {childSummaryArtifactPath}
```

## TodoWrite format (mandatory)

```text
- Phase 1: Discover top-level scope context (pending)
- Phase 2: Run Epic decomposition (pending)
- Phase 3: Run sequential Story loop (pending)
- Phase 4: Run optional prioritization loop (pending)
- Phase 5: Finalize scope summary (pending)
- Phase 6: Self-check (pending)
```

### When to Use This Skill

This skill should be used when:
- Start new initiative requiring full decomposition (scope → Epics → Stories)
- Automate Epic + Story creation in single workflow
- Prefer full pipeline over manual step-by-step invocation
- Time-efficient approach for new projects (2-3 hours end-to-end)

**Alternative:** For granular control, invoke coordinators manually:
1. [ln-210-epic-coordinator](../ln-210-epic-coordinator/SKILL.md) - CREATE/REPLAN Epics
2. [ln-220-story-coordinator](../ln-220-story-coordinator/SKILL.md) - CREATE/REPLAN Stories (once per Epic)
3. [ln-230-story-prioritizer](../ln-230-story-prioritizer/SKILL.md) - RICE prioritization (once per Epic)

### When NOT to Use

Do NOT use if:
- Initiative already has Epics → Use ln-210-epic-coordinator REPLAN mode instead
- Need to replan existing Stories → Use ln-220-story-coordinator REPLAN mode per Epic
- Only need Epic creation → Use ln-210-epic-coordinator directly
- Only need Story creation for specific Epic → Use ln-220-story-coordinator directly

---

## Core Concepts

### Orchestrator Pattern

**ln-200-scope-decomposer is a pure coordinator** - it does NOT execute work directly:
- ✅ Discovers context (Team ID)
- ✅ Makes routing decisions (which coordinator to invoke)
- ✅ Delegates all work via Skill tool (ln-210, ln-220, ln-230)
- ✅ Manages workflow state (Epic creation → Story loop)
- ❌ Does NOT research project docs (ln-210 does this)
- ❌ Does NOT generate Epic/Story documents (ln-210/ln-220 do this)
- ❌ Does NOT create tracker issues (coordinators do this via the configured provider)
- ❌ Does NOT prompt user (coordinators handle all user interaction)

**Coordinators:**
- **ln-210-epic-coordinator:** Creates 3-7 Epics (Epic 0 for Infrastructure if applicable, Epic 1-N for business domains)
- **ln-220-story-coordinator:** Creates 5-10 Stories per Epic (with inline standards research)

### Sequential Story Decomposition

**CRITICAL CONSTRAINT:** Epic N Stories MUST complete before Epic N+1 starts (ln-220 includes user interaction — interactive dialog cannot be parallelized across Epics).

**Why sequential?**
- ln-220-story-coordinator includes user interaction (Story preview confirmation)
- Interactive dialog cannot be parallelized (user must review each Epic's Stories)
- Ensures Epic N Stories are approved and created before starting Epic N+1
- Read-only preparation MAY be batched first (Epic metadata, child manifests, artifact paths), but Story creation itself remains sequential

**Example:** 6 Epics → ln-220 invoked 6 times sequentially (Epic 0 → Epic 1 → Epic 2 → ... → Epic 5)

### Infrastructure Epic = Epic 0

**Reserved number:** Epic 0 is reserved for Infrastructure Epic (if proposed by ln-210).

**Numbering:**
- IF Infrastructure Epic exists → Epic 0 (Infrastructure), Epic 1-N (business domains)
- ELSE → Epic 1-N (business domains only)

**Decision:** ln-210-epic-coordinator Phase 1 Step 3 automatically determines if Infrastructure Epic is needed (new project, multi-stack, security/monitoring requirements).

### Auto-Discovery

**Team ID**: Auto-discovered from `docs/tasks/kanban_board.md` Tracker Configuration table (see CLAUDE.md "Configuration Auto-Discovery").

**Fallback:** If kanban_board.md missing → ln-210-epic-coordinator will ask user directly

---

## Workflow

### Phase 1: Discovery (Automated)

Auto-discovers Team ID from `docs/tasks/kanban_board.md`.

**Validation:**
- Team ID exists in kanban_board.md
- If missing → Skip (ln-210 will request from user)

**NO user confirm