nw-deliver-orchestration

DELIVER wave orchestration workflow -- 9 phases from baseline to finalization. Load when user invokes *deliver command. Covers state tracking, smart skip logic, retry, resume, and quality gate enforcement.

322 stars

Best use case

nw-deliver-orchestration is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

DELIVER wave orchestration workflow -- 9 phases from baseline to finalization. Load when user invokes *deliver command. Covers state tracking, smart skip logic, retry, resume, and quality gate enforcement.

Teams using nw-deliver-orchestration should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/nw-deliver-orchestration/SKILL.md --create-dirs "https://raw.githubusercontent.com/nWave-ai/nWave/main/nWave/skills/nw-deliver-orchestration/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/nw-deliver-orchestration/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How nw-deliver-orchestration Compares

Feature / Agentnw-deliver-orchestrationStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

DELIVER wave orchestration workflow -- 9 phases from baseline to finalization. Load when user invokes *deliver command. Covers state tracking, smart skip logic, retry, resume, and quality gate enforcement.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# DELIVER Wave Orchestration

When invoked via `*deliver "{feature-description}"`, Apex orchestrates the complete DELIVER wave lifecycle.

## Orchestration Role

Parse feature description, derive feature ID, execute 9 phases in order. Track state for resume capability.

**Invocation**: `*deliver "Implement user authentication with JWT tokens"`

## 9 Phases

### Phase 1-2: Baseline Creation + Review
Create: `docs/feature/{feature-id}/deliver/baseline.yaml`. Reviewer: @nw-software-crafter-reviewer.
Smart skip: yes (if file exists AND `validation.status == "approved"`).

### Phase 3-4: Roadmap Creation + Dual Review
Create: `docs/feature/{feature-id}/deliver/roadmap.json`.
Reviewer 1: @nw-product-owner-reviewer (business) | Reviewer 2: @nw-software-crafter-reviewer (technical). Sequential reviews.
Smart skip: yes (if approved).

### Phase 5-6: Split + Review Each Step
Define steps in: `docs/feature/{feature-id}/deliver/roadmap.json`. Reviewer: @nw-software-crafter-reviewer (per roadmap step).
Smart skip: yes (if all approved).

### Phase 7: Execute All Steps
For each step: invoke `@nw-software-crafter` with step ID. Automatic dependency ordering (topological sort via Kahn's algorithm). 11-phase TDD per step (PREPARE through COMMIT). Local commit after each step (no push). Stop immediately if any step fails.

### Phase 8: Finalize
Archive to: `docs/evolution/{timestamp}_{feature-id}.md`. Clean up workflow files.

### Phase 9: Report Completion
Display comprehensive statistics | List all quality gates passed | Show next steps (review evolution doc, push commits, proceed to DEVOPS wave validation).

## Smart Skip Logic
- File exists AND `validation.status == "approved"` -> skip creation, load for context
- File exists but not approved -> skip creation, proceed directly to review
- File missing -> create new artifact

## Quality Gates

| Gate | Reviews | Reviewer |
|------|---------|----------|
| Baseline | 1 | nw-software-crafter-reviewer |
| Roadmap | 2 | nw-product-owner-reviewer + nw-software-crafter-reviewer |
| Step files | N (per step) | nw-software-crafter-reviewer |
| TDD phases | 2N (per step) | REVIEW + POST-REFACTOR REVIEW |

**Total reviews per feature**: 3 + 3N (where N = number of steps)

## Retry Logic
- Max 2 attempts per review
- Rejected: regenerate artifact with feedback, retry review
- Rejected after 2 attempts: stop workflow, require manual intervention

## Stop-on-Failure Policy
- Any review fails after 2 attempts -> stop entire workflow
- Any step execution fails -> stop entire workflow
- User fixes issue manually, re-runs `*deliver` (resumes from failure point)

## State Tracking

Progress tracked in `docs/feature/{feature-id}/deliver/.deliver-progress.json`:

```json
{
  "project_id": "user-authentication",
  "started_at": "2025-01-13T10:30:00",
  "last_updated": "2025-01-13T12:45:00",
  "completed_phases": ["Phase 1", "Phase 2"],
  "current_phase": "Phase 3",
  "failed_phase": null,
  "failure_reason": null,
  "completed_steps": ["01-01", "01-02"],
  "failed_step": null,
  "skip_flags": {
    "baseline": true,
    "roadmap": false,
    "split": false
  },
  "orchestration_complete": false
}
```

## Resume Capability
On re-invocation: Load `.deliver-progress.json` -> Skip completed phases -> Resume from failure point or current phase.

## Post-Completion
After DELIVER wave completes: All code committed locally (one commit per step) | Evolution document in `docs/evolution/` | User reviews commits and evolution document | User pushes: `git push` | Validate production readiness: `*validate-completion`.

Related Skills

nw-deliver

322
from nWave-ai/nWave

Orchestrates the full DELIVER wave end-to-end (roadmap > execute-all > finalize). Use when all prior waves are complete and the feature is ready for implementation.

nw-ux-web-patterns

322
from nWave-ai/nWave

Web UI design patterns for product owners. Load when designing web application interfaces, writing web-specific acceptance criteria, or evaluating responsive designs.

nw-ux-tui-patterns

322
from nWave-ai/nWave

Terminal UI and CLI design patterns for product owners. Load when designing command-line tools, interactive terminal applications, or writing CLI-specific acceptance criteria.

nw-ux-principles

322
from nWave-ai/nWave

Core UX principles for product owners. Load when evaluating interface designs, writing acceptance criteria with UX requirements, or reviewing wireframes and mockups.

nw-ux-emotional-design

322
from nWave-ai/nWave

Emotional design and delight patterns for product owners. Load when designing onboarding flows, empty states, first-run experiences, or evaluating the emotional quality of an interface.

nw-ux-desktop-patterns

322
from nWave-ai/nWave

Desktop application UI patterns for product owners. Load when designing native or cross-platform desktop applications, writing desktop-specific acceptance criteria, or evaluating panel layouts and keyboard workflows.

nw-user-story-mapping

322
from nWave-ai/nWave

User story mapping for backlog management and outcome-based prioritization. Load during Phase 2.5 (User Story Mapping) to produce story-map.md and prioritization.md.

nw-tr-review-criteria

322
from nWave-ai/nWave

Review dimensions and scoring for root cause analysis quality assessment

nw-tlaplus-verification

322
from nWave-ai/nWave

TLA+ formal verification for design correctness and PBT pipeline integration

nw-test-refactoring-catalog

322
from nWave-ai/nWave

Detailed refactoring mechanics with step-by-step procedures, and test code smell catalog with detection patterns and before/after examples

nw-test-organization-conventions

322
from nWave-ai/nWave

Test directory structure patterns by architecture style, language conventions, naming rules, and fixture placement. Decision tree for selecting test organization strategy.

nw-test-design-mandates

322
from nWave-ai/nWave

Four design mandates for acceptance tests - hexagonal boundary enforcement, business language abstraction, user journey completeness, walking skeleton strategy, and pure function extraction