new-ddd
Initialize a new project using Documentation-Driven Development.
Skill by buildomator
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/buildomator-new-ddd
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, writing, research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/new-ddd
What's inside
- Skill name
new-ddd- Description
- Initialize a new project using Documentation-Driven Development. Research, then write user-facing docs (SPEC.md) as the spec, then user validates docs, then phases derive from doc sections. Best for CLIs, libraries, SDKs, APIs, plugin systems, anything with a well-defined user-facing surface.
- License
- MIT
- Instructions
- 63 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- allowed-tools: must be a space-separated string
Files (1)
- SKILL.md
SKILL.md (first lines)
<runtime_note>
**Copilot (VS Code):** Use `vscode_askquestions` wherever this workflow calls `AskUserQuestion`. They are equivalent, `vscode_askquestions` is the VS Code Copilot implementation of the same interactive question API.
</runtime_note>
<context>
**Documentation-Driven Development (DDD) mode for project initialization.** Differs from `/bm:new-project`:
1. Users validate `SPEC.md` (user-facing docs: README, USAGE, CONCEPTS, API surface) rather than `REQUIREMENTS.md` (REQ-IDs + acceptance criteria).
2. Phases derive from `SPEC.md` sections / chapters rather than REQ-ID clusters.
3. Each phase's success criterion is "implementation matches the corresponding SPEC.md section" rather than "tests pass and UAT satisfied."
**When to use DDD vs. standard new-project:**
- CLIs (the help text IS the spec)
- Libraries / SDKs (README + API reference is the contract)
- APIs (OpenAPI-style docs-as-spec)
- Plugin / extension systems (extension API surface = docs)
- Any project where the user-facing surface is the deliverable
**When to skip DDD and use standard new-project:**
- Exploratory research where the system shape is unknown
- Pure refactors or performance optimization
- Backend services with no human-readable interface
**Flags:**
- `--auto`, Automatic mode. After config questions, runs research → docs → roadmap without further interaction. Expects idea document via @ reference.
</context>
<objective>
Initialize a new project through Documentation-Driven Development:
1. Questioning (deep context gathering, same as new-project)
2. Research (parallel, same as new-project)
3. **SPEC.md drafting** (NEW, writes user-facing documentation as the spec)
4. **User validation of SPEC.md** (NEW, read-through and approve before any phase work)
5. Roadmap generation (phases derived from SPEC.md sections)
6. STATE.md initialization
**Creates:**
- `.planning/PROJECT.md`, project context
- `.planning/config.json`, workflow preferences (`mode: ddd` set)
- `.planning/research/`, domain research (optional)
- `docs/SPEC.md`, user-facing documentation as the spec
- `.planning/REQUIREMENTS.md`, thin traceability shell, each entry pointing at a SPEC.md section
- `.planning/ROADMAP.md`, phase structure derived from SPEC.md sections
- `.planning/STATE.md`, project memory (with `mode: ddd` marker)
**After this command:** Run `/bm:plan-phase 1` to start execution. Per-phase work proceeds as standard GSD; SPEC.md is the spec each phase implements against. Manual doc updates during execution are expected; per-phase doc-sync automation is held for a future release.
</objective>
<execution_context>
@${CLAUDE_PLUGIN_ROOT}/workflows/new-ddd.md
@${CLAUDE_PLUGIN_ROOT}/workflows/new-project.md
@${CLAUDE_PLUGIN_ROOT}/references/questioning.md
@${CLAUDE_PLUGIN_ROOT}/references/ui-brand.md
@${CLAUDE_PLUGIN_ROOT}/templates/project.md
</execution_context>
<process>
Execute the new-ddd workflow from @${CLAUDE_PLUGIN_ROOT}/workflows/new-ddd.md end-to-end.
Where the workflow says "as in new-project step N", follow the matching step from @${CLAUDE_PLUGIN_ROOT}/workflows/new-project.md to avoid duplicated logic.
Preserve all workflow gates (validation, approvals, commits, routing).
</process>From buildomator/buildomator, MIT.
More from buildomator/buildomator
- 0.670score
discuss-phase
buildomator
Gather phase context through adaptive questioning before planning.
SkillAFreshness: A★ 98Claude Code +9 - 0.667score
ai-integration-phase
buildomator
Generate AI design contract (AI-SPEC.md) for phases that involve building AI systems — framework selection, implementation guidance from official docs, and…
SkillAFreshness: A★ 98Claude Code +9 - 0.667score
eval-review
buildomator
Retroactively audit an executed AI phase's evaluation coverage — scores each eval dimension as COVERED/PARTIAL/MISSING and produces an actionable…
SkillAFreshness: A★ 98Claude Code +9 - 0.667score
code-review-fix
buildomator
Auto-fix issues found by code review in REVIEW.md.
SkillAFreshness: A★ 98Claude Code +9 - 0.667score
forensics
buildomator
Post-mortem investigation for failed GSD workflows — analyzes git history, artifacts, and state to diagnose what went wrong
SkillAFreshness: A★ 98Claude Code +9 - 0.667score
ingest-docs
buildomator
Scan a repo for mixed ADRs, PRDs, SPECs, and DOCs and bootstrap or merge the full .planning/ setup from them.
SkillAFreshness: A★ 98Claude Code +9 - 0.664score
graphify
buildomator
Build, query, and inspect the project knowledge graph in .planning/graphs/
SkillAFreshness: A★ 98Claude Code +9 - 0.664score
milestone-summary
buildomator
Generate a comprehensive project summary from milestone artifacts for team onboarding and review
SkillAFreshness: A★ 98Claude Code +9 - 0.664score
note
buildomator
Zero-friction idea capture.
SkillAFreshness: A★ 98Claude Code +9 - 0.664score
from-gsd2
buildomator
Import a GSD-2 (.gsd/) project back to GSD v1 (.planning/) format
SkillAFreshness: A★ 98Claude Code +9 - 0.664score
intel
buildomator
Query, inspect, or refresh codebase intelligence files in .planning/intel/
SkillAFreshness: A★ 98Claude Code +9 - 0.664score
new-milestone
buildomator
Start a new milestone cycle — update PROJECT.md and route to requirements
SkillAFreshness: A★ 98Claude Code +9
Signals
- Stars
- 98
- Forks
- 13
- Open issues
- 4
- Last commit (this folder)
- Aug 4, 2026 (2 months ago)
- Last release
- Oct 22, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/buildomator/buildomator
- Website
- www.buildomator.com
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from buildomator
- 0.670score
discuss-phase
buildomator
Gather phase context through adaptive questioning before planning.
SkillAFreshness: A★ 98Claude Code +9 - 0.667score
code-review-fix
buildomator
Auto-fix issues found by code review in REVIEW.md.
SkillAFreshness: A★ 98Claude Code +9 - 0.667score
ai-integration-phase
buildomator
Generate AI design contract (AI-SPEC.md) for phases that involve building AI systems — framework selection, implementation guidance from official docs, and…
SkillAFreshness: A★ 98Claude Code +9 - 0.667score
eval-review
buildomator
Retroactively audit an executed AI phase's evaluation coverage — scores each eval dimension as COVERED/PARTIAL/MISSING and produces an actionable…
SkillAFreshness: A★ 98Claude Code +9 - 0.667score
forensics
buildomator
Post-mortem investigation for failed GSD workflows — analyzes git history, artifacts, and state to diagnose what went wrong
SkillAFreshness: A★ 98Claude Code +9 - 0.667score
ingest-docs
buildomator
Scan a repo for mixed ADRs, PRDs, SPECs, and DOCs and bootstrap or merge the full .planning/ setup from them.
SkillAFreshness: A★ 98Claude Code +9
Cite this page
new-ddd skill. Agent Mart. https://agentmart.dev/skills/buildomator-new-ddd (last updated 2026-10-24)