A collection of GitHub Copilot CLI skills that guide software development from domain language all the way to production-ready code, covering ubiquitous language mapping, requirements clarification, PRD, TDD, and codebase improvement.
Generate Postman collection from .sdd/{feature}/ scenarios. Triggered by: "api test", "postman", "generate collection", "/api-test".
Reach 100% intent consensus with the user, then compile a requirements brief for handoff to PRD. Never edits source code. Triggered by: "clarify", "/clarify".
Improve the design quality of an existing codebase by identifying fragmented logic and consolidating it into deep modules — simple interfaces hiding complex internals. Triggered by: "improve codebase", "deep module", "/improve-codebase".
Two modes: (1) FEATURE — conduct a requirements interview and generate a PRD file under .sdd/; (2) PROJECT — analyze UL-MAP.md and project architecture to produce or update .sdd/PROJECT.md (vision, tech stack, conventions). Triggered by: "prd", "write a PRD", "feature spec", "product requirement", "/prd", "/prd project", "project overview", "project map".
Drive implementation via TDD. Reads a PRD, extracts test cases, then runs red-green-refactor per test case. Tests verify behavior only. Triggered by: "tdd", "implement with tdd", "/tdd".
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A collection of GitHub Copilot CLI skills that guide software development from domain language all the way to production-ready code.
This project was sparked by Matt Pocock's talk "It Ain't Broke: Why Software Fundamentals Matter More Than Ever".
The core argument: AI coding tools are powerful, but the developers who succeed with them are the ones who double down on engineering fundamentals — not the ones who try to skip them. Ubiquitous Language, vertical slices, TDD, and deep modules don't become less important when AI is in the loop. They become more important, because AI can produce spaghetti faster than any human ever could.
"The devs who succeed aren't the ones who delegate everything or nothing to AI. They're the ones who fall back on engineering fundamentals... the principles that make it work didn't break. They got more important." — Matt Pocock
Forge turns those fundamentals into a concrete, skill-by-skill workflow for the SDD ecosystem.
Forge provides a structured, repeatable development workflow powered by Copilot CLI skills. Each skill owns one phase of the process, keeping responsibilities sharp and handoffs clean.
ubiquitous-language-mapping → clarify → prd → tdd → improve-codebase
↑ ↑ ↑
└─── foundation ─────┴── anytime, standalone ┘
The .sdd/ folder (Software Design Documents) is the shared workspace — skills read from and write to it, giving you a living record of domain knowledge, requirements, and decisions.
ubiquitous-language-mapping — Ubiquitous Language MapRun this first. Scans the codebase and creates .sdd/UL-MAP.md — a domain glossary that bridges business terms, code names, and UI labels.
INIT: generate a fresh map from existing source filesUPDATE: add, refine, or deprecate terms as the domain evolvesAll downstream skills depend on this map to phrase questions and generate artifacts in the project's own language.
clarify — Requirements BriefReaches full intent consensus with you before a single line is written. Produces a structured BRIEF.md that feeds directly into PRD.
.sdd/{date}-{feature}/BRIEF.mdprd — Product Requirements DocumentConducts a requirements interview grounded in the UL Map, then generates a formal PRD. Two modes:
/prd): interview → PRD for a specific feature; also updates UL-MAP with any new terms/prd project): analyze architecture + UL-MAP → produce/update .sdd/PROJECT.md (vision, tech stack, conventions)Standalone use: run
/prd projectanytime to keep the project overview in sync with reality — no feature needed.
tdd — Test-Driven ImplementationReads a PRD and drives implementation through red-green-refactor cycles.
Tracks progress in SQL so sessions can be resumed mid-cycle.
improve-codebase — Deep Module RefactoringImproves design quality by finding scattered logic and consolidating it into deep modules — stable interfaces that absorb complexity so callers stay simple.
Standalone use: run anytime to keep code quality high, independent of any active feature.
1. /ubiquitous-language-mapping ← initialize the Ubiquitous Language Map
2. /prd project ← document vision, tech stack, and conventions
3. /clarify ← reach consensus on what to build → BRIEF.md
4. /prd ← conduct requirements interview → PRD.md
5. /tdd ← implement test-by-test → green suite
/prd project ← refresh PROJECT.md when architecture evolves
/improve-codebase ← consolidate fragile or scattered code
/ubiquitous-language-mapping update ← extend the domain glossary as language shifts
.sdd/
├── UL-MAP.md # Ubiquitous Language Map (ubiquitous-language-mapping)
├── PROJECT.md # Project overview (prd project)
└── {yyyy-MM-dd}-{feature}/
├── BRIEF.md # Requirements brief (clarify)
└── PRD.md # Product requirements (prd)
A collection of skills covering .NET Core best practices and general engineering methodology, including architecture, EF Core, refactoring, unit testing, and tidy-first principles.
npx claudepluginhub codemachine0121/sdd-skill --plugin sdd-skillsDesign fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Complete developer toolkit for Claude Code