Kc Ai Skills banner
KerberosClaw KerberosClaw

Kc Ai Skills

AI community

Description

AI Skills That Actually Do Things — 中文優先的 Claude Code / Codex agent skills 合集 · Reusable bilingual skills for any LLM workflow

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

AI Skills That Actually Do Things

[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)

[正體中文](README_zh.md)

A collection of AI agent skills that solve real problems — not "summarize this PDF" kind of skills, but "scan my repo for leaked API keys before I push" kind of skills. Works with any LLM client that supports skill/prompt loading, cloud or local.

Skills follow the [Claude Code skill convention](https://code.claude.com/docs/en/skills) (SKILL.md + scripts/), but the concepts are framework-agnostic. Think of them as reusable checklists your AI actually follows.

**Security Notice:** These skills are designed for local development and trusted LAN environments. Skills that interact with external services (e.g., `searxng`) default to secure settings (TLS verification enabled), but do not implement additional authentication layers. Review each skill's configuration before deploying in sensitive environments.

Skills

Grouped by what you're trying to get done — every skill is still a self-contained top-level folder, the grouping is just a map.

Workflow entrypoint

Skill What It Actually Does
workflow-router The front door for the confusing middle: PRD, SD, FR, AC, ADR, tickets, implementation, release, or unattended runs. It asks at most one clarifying question, tells you which specialist skill to use, explains why in plain language, then hands off. It deliberately does not write the PRD/spec/ADR itself

Generate & create

Skill What It Actually Does
gpt-image-gen Talk Codex into drawing it for you. Drafts a tight bilingual prompt, iterates until you give an explicit go, then fires Codex CLI for text-to-image — the hard confirmation gate exists because "looks good" is not "yes" and every generation costs real quota. Does text-to-image, img2img (drop an on-disk reference image to lock a face/char