Kc AI Skills
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
Install: git clone https://github.com/KerberosClaw/kc_ai_skills
Works with Claude Code, Codex · 79 GitHub stars
Install
git clone https://github.com/KerberosClaw/kc_ai_skillsInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →AI Skills That Actually Do Things
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 (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.
Plugins
Some skills now ship as plugins in kc_ai_plugins: a plugin bundles the skills for one job together with the MCP servers they need, and installs in one step on both Claude Code and Codex.
| Plugin | Skills | Install |
|---|---|---|
| doc-qa | project-docs, qa, md2pdf |
/plugin marketplace add KerberosClaw/kc_ai_plugins then /plugin install doc-qa@kc-ai-plugins |
Skills that moved into a plugin are still listed below, marked 📦, with links to their new home. You can also copy a single skill folder from there, as before.
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 |
| 📦 project-docs | Moved to the doc-qa plugin. Turn an existing codebase into documentation someone can actually use — for two different readers. Maintainers get evidence-mapped technical docs: architecture, contracts, data models, operations, release handoff, diagrams as Mermaid source. End users and administrators get an operations manual instead: what you must have before you start, step-by-step screens, and what to do when you get stuck. Reuses templates and updates incrementally without changing product code. Defaults to Traditional Chinese technical prose with English summaries for GitHub |
Generate & create
Similar plugs
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Production-grade engineering skills for AI coding agents.
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create prototypes, websites, apps, dashboards, presentations, images, and videos with your team…