Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From sdd-workflow
SDD step 1 — write a spec (WHAT/WHY) for a feature before any plan or code exists.
How this command is triggered — by the user, by Claude, or both
Slash command
/sdd-workflow:spec <feature description, and/or paths to designs, Figma links, screenshots>The summary Claude sees in its command listing — used to decide when to auto-load this command
Step 1 of Spec-Driven Development: produce a specification, not a plan and not code. Delegate to the `spec-creator` agent. Pass it verbatim: - The request: $ARGUMENTS - Any design sources named above (Figma links, screenshots, generated design skeletons, existing docs). If a design is provided, remind the agent that the design is the source of truth. Do not write the spec yourself, and do not start planning or implementing after it returns. When the agent finishes, report the spec's file path, its `AC-N` count, and any `[NEEDS CLARIFICATION]` items that still need the author's answer. ...
Step 1 of Spec-Driven Development: produce a specification, not a plan and not code.
Delegate to the spec-creator agent. Pass it verbatim:
Do not write the spec yourself, and do not start planning or implementing after it returns. When the
agent finishes, report the spec's file path, its AC-N count, and any [NEEDS CLARIFICATION] items
that still need the author's answer. Then stop and hand back — the next step is /plan, and the user
decides when to take it.
npx claudepluginhub burnjohn/ai-demo-marketplace --plugin sdd-workflow/specGuides the user through clarifying questions and generates a structured specification document (SPEC.md) covering objective, features, tech stack, boundaries, and more.
/specCreates structured NLSpec specifications from natural language descriptions using multi-AI research (Claude, Gemini, Codex) with completeness validation and adversarial challenge.
/specCreates complete feature specifications from rough ideas, producing implementation plans with a supportive, expert tone.
/specGenerates detailed specifications from minimal requirement input, producing requirements, design, and task files following spec-driven development.
/specGenerates detailed specifications through phased conversation — requirements discovery, design exploration, and implementation planning. Produces requirements.md, design.md, and tasks.md with EARS notation and Mermaid diagrams.
/specGenerates detailed product-manager-level specs from minimal requirements, producing requirements.md, design.md, and tasks.md files. Supports iterative refinement via dialogue.