# Sdd Full Lifecycle

> Compose intake, tracked Spec Kit specification, task planning, verification, implementation, and testing for an approved change with a supplied design plan.

- Skill: `knuckles-team/sdd-full-lifecycle-2` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx get-skill add knuckles-team/sdd-full-lifecycle-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/knuckles-team/sdd-full-lifecycle-2/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- License: MIT
- Author: Knuckles-Team (https://skillmd.com/u/knuckles-team)
- Updated: 2026-11-14
- Page: https://skillmd.com/skills/knuckles-team/sdd-full-lifecycle-2

---


# SDD Full Lifecycle Workflow

## Steps

### Step 0: speckit-specify [skill: speckit-specify]

Invoke `$speckit-specify` with the workflow request.

Expected: `specification`

### Step 1: speckit-plan [skill: speckit-plan] [depends_on: Step 0]

Invoke `$speckit-plan` with `specification` and the supplied design plan.

Expected: `plan`

### Step 2: speckit-tasks [skill: speckit-tasks] [depends_on: Step 1]

Invoke `$speckit-tasks` with `specification`, `plan.md` and the design artifacts.

Expected: `tasks`

### Step 3: speckit-analyze [skill: speckit-analyze] [depends_on: Step 2]

Invoke `$speckit-analyze` with `specification`, `plan.md` and `tasks`.

Expected: `verified_specification`

### Step 4: sdd-implementer [skill: sdd-implementer] [depends_on: Step 3]

Invoke `$sdd-implementer` with `verified_specification` and `tasks`.

Expected: `implementation_result`

### Step 5: automated-test-runner [skill: automated-test-runner] [depends_on: Step 4]

Invoke `$automated-test-runner` with `implementation_result`.

Expected: `test_result`

## Execution

The workflow input must include a tracked `specs/<stable-id>/plan.md` and applicable design artifacts produced with the repository’s Spec Kit plan command. The current DAG has no atomic plan-generation skill; it must stop before task planning if the design is absent. `.specify/memory/constitution.md` governs each step. Git-tracked `specs/` files are authoritative; KG sync is derived.

- **Run first:** Step 0 — `$speckit-specify`.
- **After Step 0:** Step 1 — `$speckit-plan`.
- **After Step 1:** Step 2 — `$speckit-tasks`.
- **After Step 2:** Step 3 — `$speckit-analyze`.
- **After Step 3:** Step 4 — `$sdd-implementer`.
- **After Step 4:** Step 5 — `$automated-test-runner`.

**Execution:** If arbora is reachable, offload the whole DAG via `graph_orchestrate action=execute_workflow` (or the `kg-delegate` skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet `depends_on` in parallel, then their dependents.

## Delivery practice

Follow the [delivery practice reference](https://github.com/Knuckles-Team/pipelines/blob/main/reference/delivery-practice.md) for waiting, branches, merge holds, worktree safety and verification. The [constitution](https://github.com/Knuckles-Team/pipelines/blob/main/.specify/memory/constitution.md) holds the binding articles: XXVIII (merges and releases), XXIX (checks tell the truth), XVIII (landed means reachable), XXV (small units) and XXXII (written text is self-evident: every pull request, review or issue comment and commit message states what changed, why, the behaviour impact and how it was verified, in plain words, with no hostname, private domain, local path, internal tool, private repository, workflow jargon or private handoff pointer, and every spec row ID beside its one-line meaning).

