How do I install the Sdd Full Lifecycle skill?

Run npx skillmds@latest add knuckles-team/sdd-full-lifecycle in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Sdd Full Lifecycle safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Sdd Full Lifecycle?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Sdd Full Lifecycle free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Sdd Full Lifecycle?

Knuckles-Team (@knuckles-team) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Sdd Full Lifecycle by knuckles-team

Name: Sdd Full Lifecycle
Author: Knuckles-Team

Sdd Full Lifecycle

Turn a feature request into verified implementation results by composing the catalog's atomic specification, planning, implementation, and test skills. Use when a user wants the complete spec-driven development lifecycle for an approved repository change rather than one isolated SDD phase.

Knuckles-Team 02ead49 2 files · 2.2 KB Updated Sep 17, 2026

File contents

SDD Full Lifecycle Workflow

Steps

Step 0: spec-intake-wizard [skill: spec-intake-wizard]

Invoke $spec-intake-wizard with the workflow request.

Expected: intake_result

Step 1: spec-generator [skill: spec-generator] [depends_on: Step 0]

Invoke $spec-generator with intake_result.

Expected: specification

Step 2: spec-verifier [skill: spec-verifier] [depends_on: Step 1]

Invoke $spec-verifier with specification.

Expected: verified_specification

Step 3: task-planner [skill: task-planner] [depends_on: Step 2]

Invoke $task-planner with verified_specification.

Expected: implementation_plan

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

Invoke $sdd-implementer with implementation_plan.

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

Run first: Step 0 — $spec-intake-wizard.
After Step 0: Step 1 — $spec-generator.
After Step 1: Step 2 — $spec-verifier.
After Step 2: Step 3 — $task-planner.
After Step 3: Step 4 — $sdd-implementer.
After Step 4: Step 5 — $automated-test-runner.

Execution: If graph-os 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.

---name: sdd-full-lifecycledescription: Turn a feature request into verified implementation results by composing the catalog's atomic specification, planning, implementation, and test skills. Use when a user wants the complete spec-driven development lifecycle for an approved repository change rather than one isolated SDD phase.license: MIT---# SDD Full Lifecycle Workflow## Steps### Step 0: spec-intake-wizard [skill: spec-intake-wizard]Invoke `$spec-intake-wizard` with the workflow request.Expected: `intake_result`### Step 1: spec-generator [skill: spec-generator] [depends_on: Step 0]Invoke `$spec-generator` with `intake_result`.Expected: `specification`### Step 2: spec-verifier [skill: spec-verifier] [depends_on: Step 1]Invoke `$spec-verifier` with `specification`.Expected: `verified_specification`### Step 3: task-planner [skill: task-planner] [depends_on: Step 2]Invoke `$task-planner` with `verified_specification`.Expected: `implementation_plan`### Step 4: sdd-implementer [skill: sdd-implementer] [depends_on: Step 3]Invoke `$sdd-implementer` with `implementation_plan`.Expected: `implementation_result`### Step 5: automated-test-runner [skill: automated-test-runner] [depends_on: Step 4]Invoke `$automated-test-runner` with `implementation_result`.Expected: `test_result`## Execution- **Run first:** Step 0 — `$spec-intake-wizard`.- **After Step 0:** Step 1 — `$spec-generator`.- **After Step 1:** Step 2 — `$spec-verifier`.- **After Step 2:** Step 3 — `$task-planner`.- **After Step 3:** Step 4 — `$sdd-implementer`.- **After Step 4:** Step 5 — `$automated-test-runner`.**Execution:** If graph-os 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.

Frequently asked questions