By bennypowers
Unlock LSP code intelligence—autocomplete, hover docs, diagnostics, go-to-definition, references—for DTCG design tokens in JSON, YAML, TypeScript, CSS, HTML, JavaScript files, plus run a local MCP server for AI-native token discovery, validation, search, and format conversion.
npx claudepluginhub bennypowers/asimonim --plugin asimonim
A high-performance design tokens parser, validator, and language server, available as a CLI tool and Go library.
Asimonim (אֲסִימוֹנִים) (ahh-see-moh-NEEM) is Hebrew for "tokens".
Design systems use design tokens to store visual primitives like colors, spacing, and typography. Asimonim parses and validates token files defined by the Design Tokens Community Group (DTCG) specification, supporting both the current draft and the stable V2025_10 schema.
npm install -g @pwrs/asimonim
Enable the bennypowers overlay, then install:
eselect repository enable bennypowers
emaint sync -r bennypowers
emerge dev-util/asimonim
go install bennypowers.dev/asimonim@latest
Full documentation is available at bennypowers.dev/asimonim.
See CONTRIBUTING.md
GPLv3
Complete developer workflow toolkit. Includes 34 reference skills, 34 specialized agents, and 21 slash commands covering TDD, debugging, code review, architecture, documentation, refactoring, security, testing, git workflows, API design, performance, UI/UX design, plugin development, and incident response. Full SDLC coverage with MCP integrations.
LSP-backed code intelligence for Claude Code via MCP and native LSP - navigate definitions, references, call hierarchies, type hierarchies, and diagnostics across codebases
Ship design-to-production React 19 apps with Claude Code — Figma-to-code translation, automated code reviews, architecture guardrails, and accessibility enforcement for designers and engineers.
Custom agents and skills for AI-assisted development
Rafayel's engineering toolkit: end-to-end feature workflow with brainstorm-plan-work-review-compound pipeline, case-based memory layer with vector retrieval, pattern detection and auto-PR generation, pluggable orchestrator strategies, Obsidian vault researcher, ADR management, dev logs, and project bootstrapping.
ML Workbench for Claude Code. Full ML lifecycle: search papers across 7 academic sources, discover and download datasets from 5 repositories, explore and clean data, engineer features, train models (Naive Bayes, KNN, LDA/QDA, SVM, Decision Trees, Ensembles, GLM, Gaussian Process, Neural Networks), run autonomous experiments, build AI apps with LLMs and RAG, build MCP servers, deploy models with Docker and CI/CD, detect drift, explain predictions with SHAP, generate podcasts from papers, manage notebooks, extract YouTube content, and learn ML interactively with 3 university-grade courses (CS229, Applied ML, ML Engineering). 11 agents, 16 skills, 3 CLI tools (mlx-exp, mlx-search, mlx-status), 1 MCP server, 3 output styles, Python LSP via pyright.