Skills
A collection of 33 reusable agent skills for coding agents, packaged as a Claude Code plugin, covering a PIV loop, planning, worktrees, and meta-skills for building custom AI layers.
coleam00 · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add coleam00/skills技能说明
Cole's AI Skills
The skills I actually use to build software with coding agents. Straight out of my .claude/skills/ folder.
What this is
A skill is a folder with a SKILL.md in it: a name, a description of when to use it, and the procedure the agent
should follow. Your agent loads the description at startup and pulls in the full skill only when the work matches.
That's the whole idea, and it's why skills scale where a 2,000-line CLAUDE.md doesn't.
These 33 skills are the AI Layer from my Agentic Coding course. They're built around one loop I run on nearly every ticket:
prime → plan → implement → validate → review → commit → PR
Around that loop sit the pieces that feed it (PRD, architecture, epic slicing), the pieces that run it in parallel (worktrees), and the meta-skills that let you build more of your own AI Layer (rules, hooks, skills, opportunity scans).
Nothing here is a framework. Each skill is a plain markdown file you can read in two minutes, disagree with, and edit. That's the point: read them, take the ones that fit how you work, rewrite the rest.
Bring them in
As a Claude Code plugin (easiest, stays updated)
Run these two commands inside Claude Code:
/plugin marketplace add coleam00/skills
/plugin install skills@cole-medin
That's it. All 33 skills, managed and read-only, and /plugin marketplace update pulls new ones as I add them.
Plugin skills are namespaced, so you invoke them as /skills:piv-implement.
The whole set costs roughly 4,200 tokens of always-on context (just the descriptions; the bodies load only when a
skill fires). Run claude plugin details skills to see the per-skill breakdown, and disable the plugin any
time with /plugin.
If that first command fails with
Permission denied (publickey): theowner/reposhorthand prefers SSH, and your SSH key isn't authenticating to GitHub. Recent Claude Code versions detect that and fall back to HTTPS on their own. If you