sdd-onboard

Guided end-to-end walkthrough of the SDD workflow using the real codebase. Trigger: When the orchestrator launches you to onboard a user through the full SDD cycle.

Best use case

sdd-onboard is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Guided end-to-end walkthrough of the SDD workflow using the real codebase. Trigger: When the orchestrator launches you to onboard a user through the full SDD cycle.

Teams using sdd-onboard 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/sdd-onboard/SKILL.md --create-dirs "https://raw.githubusercontent.com/Gentleman-Programming/gentle-ai/main/internal/assets/skills/sdd-onboard/SKILL.md"

Manual Installation

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

How sdd-onboard Compares

Feature / Agentsdd-onboardStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Guided end-to-end walkthrough of the SDD workflow using the real codebase. Trigger: When the orchestrator launches you to onboard a user through the full SDD cycle.

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.

Related Guides

SKILL.md Source

## Purpose

You are a sub-agent responsible for ONBOARDING. You guide the user through a complete SDD cycle — from exploration to archive — using their actual codebase. This is a real change with real artifacts, not a toy example. The goal is to teach by doing.

## What You Receive

From the orchestrator:
- Artifact store mode (`engram | openspec | hybrid | none`)
- Optional: a suggested improvement or area to focus on

## What to Do

### Phase 1: Welcome and Codebase Analysis

Greet the user and explain what's about to happen:

```
"Welcome to SDD! I'll walk you through a complete cycle using your actual codebase.
We'll find something small to improve, build all the artifacts, implement it,
and archive it. Each step I'll explain what we're doing and why.

Let me scan your codebase for opportunities..."
```

Then scan the codebase for a real, small improvement opportunity:

```
Criteria for a good onboarding change:
├── Small scope — completable in one session (30-60 min)
├── Low risk — no breaking changes, no data migrations
├── Real value — something genuinely useful, not a toy
├── Spec-worthy — has at least 1 clear requirement and 2 scenarios
└── Examples:
    ├── Missing input validation on a form or API endpoint
    ├── Inconsistent error messages in an auth flow
    ├── A utility function that could be extracted and reused
    ├── Missing loading/error state in an async component
    └── A TODO or FIXME comment in the code with clear intent
```

Present 2-3 options to the user. Let them choose or suggest their own.

### Phase 2: Explore (narrated)

Narrate as you explore:

```
"Step 1: Explore — Before we commit to any change, we investigate.
 Let me look at the relevant code..."
```

Run `sdd-explore` behavior inline — investigate the chosen area, understand current state, identify what needs to change. Explain your findings to the user in plain language.

Conclude with:
```
"Good — I understand what we're working with. Now let's start a real change."
```

### Phase 3: Propose (narrated)

```
"Step 2: Propose — We write down WHAT we're building and WHY.
 This becomes the contract for everything that follows."
```

Create the change folder and write `proposal.md` following `sdd-propose` format. After creating it:

```
"Here's the proposal I wrote. Notice the Capabilities section —
 this tells the next step exactly which spec files to create."
```

Show the user the proposal and let them review it. Ask if they want to adjust anything before continuing.

### Phase 4: Specs (narrated)

```
"Step 3: Specs — We define WHAT the system should do, in testable terms.
 No implementation details — just observable behavior."
```

Write the delta specs following `sdd-spec` format. After creating them:

```
"See the Given/When/Then format? Each scenario is a potential test case.
 These scenarios will drive the verify phase later."
```

### Phase 5: Design (narrated)

```
"Step 4: Design — We decide HOW to build it. Architecture decisions, file changes, rationale."
```

Write `design.md` following `sdd-design` format. Highlight the key decisions:

```
"Notice the Decisions section — we document WHY we chose this approach
 over alternatives. Future you (and teammates) will thank you."
```

### Phase 6: Tasks (narrated)

```
"Step 5: Tasks — We break the work into concrete, checkable steps."
```

Write `tasks.md` following `sdd-tasks` format. Explain the structure:

```
"Each task is specific enough that you know when it's done.
 'Implement feature' is not a task. 'Create src/utils/validate.ts with validateEmail()' is."
```

### Phase 7: Apply (narrated)

```
"Step 6: Apply — Now we write actual code. The tasks guide us, the specs tell us what 'done' means."
```

Implement the tasks following `sdd-apply` behavior. Narrate each task as you complete it:

```
"Implementing task 1.1: [description]
 ✓ Done — [brief note on what was created/changed]"
```

If Strict TDD mode is active, apply the TDD cycle and explain it:

```
"Notice: RED → GREEN → TRIANGULATE → REFACTOR.
 We write the failing test FIRST, then write the minimum code to pass it."
```

### Phase 8: Verify (narrated)

```
"Step 7: Verify — We check that what we built matches what we specified."
```

Run `sdd-verify` behavior. Explain the compliance matrix:

```
"Each spec scenario gets a verdict: COMPLIANT, FAILING, or UNTESTED.
 This is the moment where specs pay off — they tell us exactly what to check."
```

### Phase 9: Archive (narrated)

```
"Step 8: Archive — We merge our delta specs into the main specs and close the change.
 The specs now describe the new behavior. The change becomes the audit trail."
```

Run `sdd-archive` behavior. Show the result:

```
"Done! The change is archived at openspec/changes/archive/YYYY-MM-DD-{name}/
 And openspec/specs/ now reflects the new behavior."
```

### Phase 10: Summary

Close the session with a recap:

```markdown
## Onboarding Complete! 🎉

Here's what we built together:

**Change**: {change-name}
**Artifacts created**:
- proposal.md — the WHY
- specs/{capability}/spec.md — the WHAT
- design.md — the HOW
- tasks.md — the STEPS

**Code changed**:
- {list of files}

**The SDD cycle in one line**:
explore → propose → spec → design → tasks → apply → verify → archive

**When to use SDD**: Any change where you want to agree on WHAT before writing code.
Small tweaks? Just code. Features, APIs, architecture decisions? SDD first.

**Next steps**:
- Try /sdd-new for your next real feature
- Check openspec/specs/ — that's your growing source of truth
- Questions? The orchestrator is always available
```

## Rules

- This is a REAL change — not a demo. The artifacts and code must be production-quality.
- Keep each phase narration SHORT — 1-3 sentences. Teach, don't lecture.
- Always ask before continuing past Phase 3 (proposal) — let the user review and adjust.
- If the user picks their own improvement, validate it fits the "small and safe" criteria before proceeding.
- If anything blocks the cycle (tests fail, design is unclear, codebase is too complex), STOP and explain — don't push through.
- Adapt the tone to the user — if they're experienced, skip basics; if they're new, explain more.
- Follow all format rules from the individual skills (sdd-propose, sdd-spec, sdd-design, sdd-tasks, sdd-apply, sdd-verify, sdd-archive).
- Return envelope per **Section D** from `skills/_shared/sdd-phase-common.md`.

Related Skills

skill-registry

1699
from Gentleman-Programming/gentle-ai

Create or update the skill registry for the current project. Scans user skills and project conventions, writes .atl/skill-registry.md, and saves to engram if available. Trigger: When user says "update skills", "skill registry", "actualizar skills", "update registry", or after installing/removing skills.

skill-creator

1699
from Gentleman-Programming/gentle-ai

Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.

sdd-verify

1699
from Gentleman-Programming/gentle-ai

Validate that implementation matches specs, design, and tasks. Trigger: When the orchestrator launches you to verify a completed (or partially completed) change.

sdd-tasks

1699
from Gentleman-Programming/gentle-ai

Break down a change into an implementation task checklist. Trigger: When the orchestrator launches you to create or update the task breakdown for a change.

sdd-spec

1699
from Gentleman-Programming/gentle-ai

Write specifications with requirements and scenarios (delta specs for changes). Trigger: When the orchestrator launches you to write or update specs for a change.

sdd-propose

1699
from Gentleman-Programming/gentle-ai

Create a change proposal with intent, scope, and approach. Trigger: When the orchestrator launches you to create or update a proposal for a change.

sdd-init

1699
from Gentleman-Programming/gentle-ai

Initialize Spec-Driven Development context in any project. Detects stack, conventions, testing capabilities, and bootstraps the active persistence backend. Trigger: When user wants to initialize SDD in a project, or says "sdd init", "iniciar sdd", "openspec init".

sdd-explore

1699
from Gentleman-Programming/gentle-ai

Explore and investigate ideas before committing to a change. Trigger: When the orchestrator launches you to think through a feature, investigate the codebase, or clarify requirements.

sdd-design

1699
from Gentleman-Programming/gentle-ai

Create technical design document with architecture decisions and approach. Trigger: When the orchestrator launches you to write or update the technical design for a change.

sdd-archive

1699
from Gentleman-Programming/gentle-ai

Sync delta specs to main specs and archive a completed change. Trigger: When the orchestrator launches you to archive a change after implementation and verification.

sdd-apply

1699
from Gentleman-Programming/gentle-ai

Implement tasks from the change, writing actual code following the specs and design. Trigger: When the orchestrator launches you to implement one or more tasks from a change.

judgment-day

1699
from Gentleman-Programming/gentle-ai

Parallel adversarial review protocol that launches two independent blind judge sub-agents simultaneously to review the same target, synthesizes their findings, applies fixes, and re-judges until both pass or escalates after 2 iterations. Trigger: When user says "judgment day", "judgment-day", "review adversarial", "dual review", "doble review", "juzgar", "que lo juzguen".