A DDD spec pipeline plus data-model tooling. The ddd-* skills take a project from an interactive brief through a ubiquitous-language glossary, event flows, and EARS use cases to a development plan — with every artifact living in spec/ as the single source of truth and a mechanical alignment gate (ddd-align) proving the cross-references. In the middle sits erd-modeler, which turns the glossary into a clean, normalized DBML model and proves it works against an in-memory Postgres (PGlite), live-testing each use case's data assertions. The manual /erd-diagram command renders any DBML model into a self-contained, interactive HTML ER diagram.
Plugin napkin from marketplace jann0z-claude-plugins in jannosiilbek/jann0z-claude-plugins. Commands read from the repo's manifest — 11 days ago.
ddd-alignUse when the user wants to check, validate, or audit the consistency of a spec/ directory — glossary vs data model, use cases vs plan, spec drift, traceability, or "is my spec still aligned". Also runs as the exit gate of every napkin DDD pipeline skill (ddd-brief, ddd-domain, ddd-usecases, erd-mode
ddd-apiUse when the user wants to write an API contract, derive interface operations from use cases, specify REST endpoints, function signatures, or CLI commands from the napkin DDD pipeline — including "write the API spec", "what endpoints do we need", or the step after use cases exist. Reads spec/usecase
ddd-briefUse when the user wants to start a spec, scope a project or feature, write a project brief, kick off the DDD spec pipeline, or clarify what to build before designing anything — including "let's spec this out", "help me define this product", or when they hand over requirement documents/transcripts to
ddd-domainUse when the user wants to build a glossary or ubiquitous language, define domain terms, run an event storming, capture domain events/commands/flows, or model the domain language of a system — including "what are the concepts in this domain", "define our terminology", or the step after a project bri
ddd-planUse when the user wants a development plan, an implementation roadmap, milestones, or a task breakdown derived from a spec — including "plan the build", "break this spec into tasks", or the final step of the napkin DDD pipeline after use cases and a data model exist. Produces spec/plan.md with miles
ddd-screensUse when the user wants a screen inventory, a list of screens/pages/views derived from use cases, or UI structure planning in the napkin DDD pipeline — including "what screens do we need", "map the UI", or the step after use cases (and api.md) exist for a project with a human-facing UI. Reads spec/u
ddd-usecasesUse when the user wants to write use cases, user stories, acceptance criteria, EARS requirements, or testable requirements for a system — including "derive the use cases", "write the acceptance criteria", or the step after a glossary/flows exist in the napkin DDD pipeline. Produces spec/usecases.md
erd-diagramRenders an existing DBML data model into a single, self-contained, professional HTML ER diagram (clean dbdiagram.io-style layout, interactive pan/zoom) and opens it in the browser.
erd-modelerUse when the user wants to design a data model, create an ERD, model a domain, design a database schema, build a data model from a spec/glossary, or validate an existing DBML/schema for best practices. Turns a natural-language domain description into a clean, normalized DBML model, validates it agai
Productivity tools for Claude Code workflows. The /goal skill sharpens a vague intent into a precise, self-checkable completion condition through a focused interview (one question at a time, max three), then hands it off to Claude Code's built-in /goal command. Includes /ui-first — a dual-mode UI-structure designer/auditor that derives navigation from the user's work, never the domain model.
6 skills
Small, sharp, multi-purpose skills. Starts with /lean-spec: writes, edits and validates superconcise, filler-free specs and technical docs at the right level of detail, keeps scope focused, and gates every doc with a two-pass alignment check and a 10-question litmus test.
1 skill
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
10 skills · 2 commands · 3 agents
Conventions and task skills for contributing to diffusers
4 skills
Real-time statusline showing context usage, active tools, running agents, and todo progress. Always visible below your input, zero config required.
1 skill
PowerPoint generation and editing plugin with text-only QA (no vision required). Uses subagents for cover, TOC, content, section dividers, summary slides, and template-based PPT editing workflows.
5 skills · 5 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.