C

claude-code

Skill registry manager for AI coding agents.

AK體 · 數據驅動的 Threads 寫文決策系統。用你的歷史貼文、演算法與社媒心理學，協助選題、起草、發文前診斷、表現預估與復盤。Data-driven Threads writing advisor — topic selection, drafting, diagnosis, prediction & review based on your own post history.

Custom skills for Claude Code to extend its capabilities

Multi-repo workspace manager: MCP server + web dashboard for GitLab, GitHub, and BitBucket

My opinionated configuration for Claude Code, optimized for my personal workflow. And no—I do not vibe code.

An exercise in AI assisted software development.

Yet another software engineering agent orchestration system. This time with a mythical theme. Originally designed for Claude Code, now with support for OpenCode, Github Copilot, and OpenAI Codex.

Public skill registry for AI coding agents. Used by rune.

Ambiente di test per lavorare sui servizi digitali della PA con Linee Guida, Form.IO e AI

Populates an empty Git repository with scaffolding files and folders for development of CLI tools, libraries, and (micro) services for C++, Go, and Java. The pre-populated repository is prepared for specification driven development with support of an AI coding assistant (Claude Code).

Databricks skills plugin for Factory Droid, Claude Code, and Cursor. Cluster management, job submission, interactive REPL, notebook workflows, and Unity Catalog exploration.

Frontend für meinen Arztrechnungs-Manager

Structural biology agent skill — PyMOL, ChimeraX, AlphaFold DB, and Rosetta automation for AI coding agents

A user-friendly desktop application that brings the power of Claude Code to non-technical users.

Portable skill for adding a Claude Code lane to OpenAI Symphony + Linear workflows

Backend für meinen Arztrechnungs-Manager

A skill and toolkit for running self-improving AI agent teams. Codex or Claude Code orchestrates over Symphony workers with Linear-managed execution. Includes dispatch, review gates, concurrent workers, runbook-driven learning loops, and durable guidance promotion. No auto-merge.

A custom statusline script for Claude Code that displays working directory, git status, context window usage, and model info — all color-coded with ANSI escape sequences.

Reference architecture for LLM-correct codebases. Four primitives: derived obligations, prescriptive failure, bundled enforcement, vacuity detection.