Architecture Decision Record toolkit for AI coding agents: bootstrap, multi-format authoring, bounded deterministic enforcement, lifecycle workflows, context injection, generated graph indexes, and local health checks.
Material Design 3 / M3 Expressive guidelines: exact tokens, per-component specs, motion springs, shape morphing, emphasized typography, color roles, and 2,587 official reference images.
Quietly captures your Claude Code sessions and distills how your thinking, habits, and knowledge change over time — a dated growth archive with provenance, served over MCP. Also ingests any text corpus (notes, articles, market news) to track how THAT changed instead. Local, single Go binary.
★not rated 8 19d agoA
tokens not measured
originalMIT
Every skill in the pack except task-router (Claude Code's native skill discovery does the routing): the fullstack profile plus AI agent docs and Docker.
★not rated 8 yesterdayA
tokens not measured
originalMIT
A document tool for reading and editing HWPX files, the file format used by Hancom Hangul, a Korean word processor. It preserves the file’s raw data and checks its layout, typography, and structure.
★not rated 8 2d agoA
tokens not measured
originalMIT
The behavior gate for AI edits — proves each edit lost no auth guard, dropped no route, and grew no blast radius. Deterministic, <2s, offline, zero API key.
Drawing and maintaining the architecture diagram Ensemblr keeps for a workspace: the IR shape, how to derive it from the codebase, and the two control tools that read and store it.
★not rated 8 todayA
tokens not measured
originalApache-2.0
A cheap, persistent codebase memory for Claude Code — so your agent stops re-reading the repo. A separate large-context model learns your codebase passively across sessions and answers via the asklivememory MCP tool instead of re-loading files; read-only, zero-config on a Claude subscription.
★not rated 7 1mo agoA
tokens not measured
originalApache-2.0
Swift and Apple development to the max — skills covering the Swift language (6.x), SwiftUI, UX/HIG, App Store review, Apple legal/privacy compliance, and release operations.
★not rated 7 2mo agoA
tokens not measured
originalMIT
franke-skills. Agent-first CLI that runs Codex, Claude Code, and Grok as detached coding workers, while a stronger model keeps orchestration, steering, and review.
★not rated 7 7d agoA
tokens not measured
originalMIT
Design audit tool. Scores projects across 12 dimensions: color, typography, accessibility, layout, and more. WCAG, APCA, OKLCH color science. Zero dependencies.
★not rated 7
changed 9d agoA
tokens not measured
originalMIT
Minimal workflow for Claude Code & Codex - 8 commands, 16 dev skills, fresh-context subagent execution.
★not rated 7 4mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: