agentleFS
pchemguypchemguy/Skill-SDD-Manager/skills/sdd-design/SKILL.md

sdd-design

Skill0 starsChanged 37 days agoMITView on GitHub

Use when exploring a software project or feature, forming architecture decisions, developing a component decomposition, or creating and revising docs/dev/PROJECT.md, ARCHITECTURE.md, DECOMPOSITION.md, and scoped architectural change documents before specification.

8 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use sdd-requirements.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • GabrielaStarkSkill

    sdd-requirements

    Use this skill whenever generating, validating, or editing a requirements.md file for Spec-Driven Development. Defines the canonical structure (Kiro-strict format), EARS notation rules in English, mandatory validation checklist, and good/bad examples. Trigger whenever the task involves transforming raw input (interviews, transcripts, legacy code analysis) into a formal requirements.md, or when reviewing an existing requirements.md for compliance.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the relevant architecture or decomposition reference for read-only design review.

    line 34

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Explore and design

Choose the work requested and load only its reference. A request for a later stage can start there when its inputs are established; do not replay earlier stages as ceremony.

WorkLoad
Clarify the problem, compare alternatives, resolve decisions, or identify open questionsexploration
Define or revise major system blocks, dependency direction, and architectural decisionsarchitecture
Define or revise component responsibilities, collaboration, and provisional interfacesdecomposition

When the request crosses stages, load the next reference as that stage becomes relevant. Exploration can remain conversational. Do not create project documents solely because discussion has matured. Document creation or revision requires sdd-manage to coordinate the user's request and a current sdd-orient handoff identifying a usable Git worktree, applicable instructions, target paths, and unresolved dirty state. This skill does not perform orientation or authorize a different workflow.

Use the sdd-conventions modularity reference when defining or reviewing boundaries, and its design heuristics when assessing a chosen approach or comparing options. Keep these checks separate from the document-specific procedures below. Observe project instructions and existing contracts; do not overwrite unowned changes. If required project evidence conflicts, resolve the conflict before mutation.

PROJECT.md owns the concise project brief, ARCHITECTURE.md owns high-level design, and DECOMPOSITION.md owns detailed logical component boundaries. Both architecture and decomposition may have focused children. Scoped feature documents express a proposed architectural delta where necessary. These documents inform SPEC; they neither replace its behavioral contracts nor authorize implementation, planning, layout authoring, or task execution.

Document boundaries

DocumentGoverning concern
ARCHITECTUREMajor blocks, system-wide relationships and dependency direction, and consequential structural rationale.
DECOMPOSITIONLogical components within those blocks: responsibility, collaboration, state ownership, and design-level interface and verification seams.
SPECObservable behavior and precise success/failure contracts, required qualities, and acceptance.
PLANPractical delivery order, capability increments, dependencies, and exit/decision evidence.
layout.mdPhysical allocation of source, tests, documentation, and artifacts.

Support required modularity, extensibility, scalability, decoupling, and testability through the accepted design. Tie variation and load decisions to actual requirements and credible needs; these qualities do not require realizing every anticipated capability in the first increment.

Use the relevant architecture or decomposition reference for read-only design review. Incorporation of accepted feature design into main PROJECT, ARCHITECTURE, or DECOMPOSITION belongs to sdd-integrate-feature.

At completion, state what was explored or changed, the decisions established, unresolved material questions, and which documents were inspected or updated. Report design as design, never as implemented functionality.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.