mini-sdd-planner

Plan Mini-SDD workflows and generate `.spec/<feature-slug>/plan.md` for smaller software changes.

1|Updated Apr 18, 2026
One-click install
npx skills add https://github.com/nushey/sdd-flow --skill mini-sdd-planner
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mini-sdd-planner
Source: https://github.com/nushey/sdd-flow/tree/main/skills/mini-sdd-planner
Command: npx skills add https://github.com/nushey/sdd-flow --skill mini-sdd-planner

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents small feature work from becoming ambiguous or inconsistent by forcing a guided intake, grounded research, and a reusable plan contract before any code is written.

Core Features & Use Cases

  • Mini-SDD planning workflow: Merges scope/intent and technical decomposition into a single orchestration pass for smaller features, refactors, and bug fixes.
  • Structured grilling protocol: Collects unambiguous feature behavior, confirms reference “gold standards,” and validates architecture fit with one question at a time.
  • Harness-neutral Bootstrap contract: Produces a .spec/<feature-slug>/plan.md that tells the developer exactly which skills to load and which MCP tools to re-invoke with copy-pastable JSON args.

Quick Start

Provide a feature request like “Add OAuth login with Google” and include any relevant existing files so the planner can ground the plan and generate .spec/<feature-slug>/plan.md.

Frequently Asked Questions about mini-sdd-planner

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I plan software features before writing implementation code?

Software feature planning requires a guided intake process and grounded research to generate a reusable plan contract. This skill merges scope clarification and technical decomposition into a single orchestration pass to produce a `.spec/<feature-slug>/plan.md` before any code is written.

What is spec-driven development for smaller software changes?

Spec-driven development for smaller software changes is a workflow that applies structured interrogation and architecture-fit validation to eliminate ambiguity. It forces zero-assumption research and explicit recording of unverified assumptions to prevent drifting or hallucinated implementations.

How do I prevent unverified assumptions from causing implementation drift?

Preventing implementation drift requires explicitly recording unverified assumptions during the planning phase. This skill uses a structured grilling protocol that validates architecture fit and confirms reference gold standards one question at a time.

Does the generated plan.md specify which MCP tools to invoke for development?

Yes, the generated `plan.md` serves as a harness-neutral bootstrap contract that tells the developer exactly which skills to load and which MCP tools to re-invoke with copy-pastable JSON arguments for implementation.

What's the best way to create an implementation plan for a small refactor or bug fix?

Creating an implementation plan for small refactors or bug fixes requires merging initialization and technical design into a grounded orchestration pass. Provide a feature request and relevant existing files to ground the plan and generate the structured plan document.

Can I use this spec-driven planning workflow without loading specific skill components?

Yes, the workflow is harness-neutral and requires zero specific component dependencies. It produces a bootstrap contract containing skill and MCP instructions that can be executed by a developer subagent in any environment.