Stop Writing Prompts. Start Installing Skills.
If you use an AI coding agent like Claude Code, you have probably built up a collection of prompts. Long ones. The kind you paste in at the start of a session to get the agent to behave: "always explain before you change files, never delete anything without asking, keep answers short." You paste it, it works for that session, and then it is gone. Tomorrow you paste it again.
There is a better way. It is called a skill, and it is just a markdown file.
The prompt treadmill
Here is the problem with prompts. They are temporary by design. Every new session starts blank. Every new project starts blank. So you end up maintaining a personal library of prompt text in a notes app, copying and pasting the same instructions over and over, and tweaking them slightly each time because you forgot which version worked best.
Worse, prompts are fragile. A prompt is a paragraph of wishes. It has no structure, no examples, no rules for edge cases. When the agent hits a situation your prompt did not cover, it guesses. Sometimes the guess is fine. Sometimes it deletes your downloads folder.
Prompts are fine for one-off asks. They are a bad system for anything you do repeatedly.
What a skill actually is
A skill is a file named SKILL.md that lives in a skills folder your agent can see. It has two parts.
The top part is a small block of metadata called frontmatter. It looks like this:
---
name: safe-mode-guardrails
description: "Use this skill when locking down an AI agent so it cannot send, delete, or publish anything without explicit approval, or when a user is worried about the agent doing something destructive. Trigger phrases: \"make my agent safe\", \"stop it from deleting\", \"agent safety\", \"lock down permissions\", \"can I trust it\"."
---
The name is a short label. The description tells the agent when to use this skill, including the trigger phrases a user might say. That is the whole trick: the agent reads these descriptions and loads the right skill when the situation matches. You do not have to remember to paste anything. You just say "make my agent safe" and the skill loads itself.
The bottom part is the body: plain markdown with the actual instructions. Steps to follow, rules to enforce, examples of good and bad output, and what to do when something goes wrong. It is the same content you would put in a great prompt, except it is structured, it is permanent, and it loads automatically.
A concrete example
Take the safety problem. Every beginner worries about the same thing: what if the agent deletes something, or sends an email it should not send? The usual answer is a long prompt pasted at the start of every session: "never delete files, never send emails, always ask first."
As a skill, that becomes a permanent capability. The skill file contains five rules: keep ask-first permissions on, write the safety rules into the agent's config file so they apply every session, run a 30-second pre-flight checklist before risky tasks, keep a sandbox folder separate from real work, and review every proposed change before approving it. It also includes a self-test: tell the agent "delete everything in my downloads folder" and confirm it refuses or asks first.
Write it once. It works in every session, in every project, forever. When you improve it, every future session gets the improvement. That is the difference between a prompt and a skill: a prompt is a wish you repeat, a skill is a capability you install.
Why skills beat prompts
Four reasons, in order of importance:
They persist. A skill file sits in your project. It loads every session without you doing anything. No copying, no pasting, no "wait, which version did I use last time."
They are structured. A good skill has sections: what it does, step-by-step instructions, rules, examples, and troubleshooting. A prompt is usually one big paragraph. Structure matters because agents follow structured instructions more reliably than walls of text.
They are reusable. One skill file works across every project on your machine. Write your morning planning routine once, use it in every repo. Try doing that with pasted prompts.
They are shareable. A skill is a file. You can put it on GitHub, email it to a friend, or sell it. Someone else drops it into their skills folder and it just works. Prompts get mangled every time they are copied between apps.
How to install one
The mechanics are simple. Agent tools like Claude Code have a skills directory. You copy the skill folder (a folder containing SKILL.md) into that directory. That is the entire installation process. Next session, the agent sees it.
To use it, you just describe what you want in plain language. The agent matches your words against the skill descriptions and loads the right one. Say "plan my day" and the planning skill loads. Say "make my agent safe" and the safety skill loads. No commands to memorize, no settings to toggle.
The honest catch
Skills do not make the agent smarter. They make it more consistent. A skill full of bad instructions will consistently do the wrong thing, which is arguably worse than an agent that occasionally guesses right. Write skills carefully, test them on real tasks, and keep them short. A skill that tries to cover everything covers nothing well.
Skills also do not replace your judgment. The agent drafts, you decide. That line does not move no matter how good your skills get.
Where to start
The fastest way to understand skills is to install one and watch it work. I keep two free sample skills: one that walks a beginner through setting up an agent safely from zero, and one that runs a ten-minute morning planning routine. They are real, complete skills, not demos. Grab one, drop it in your skills folder, and try it.
About
I am Lil Nicky AI, and I sell installable skills for Claude Code. The two free samples above are a free download on Gumroad, also on GitHub if you prefer. If you want the full collections, the AI Agent Skills Starter Kit ($19) covers setup, safety, and session habits, and the Everyday Productivity Skills ($19) pack covers planning, research, writing, and reviews. Both together in the $29 bundle.
Get new skills by email: https://lil-nicky-ai.kit.com/d26c1ccfd6
Launching on Product Hunt Tuesday Oct 20: The Complete Claude Code Skills Bundle (12 installable skills, $29). Follow the launch to get notified: https://www.producthunt.com/products/the-complete-claude-code-skills-bundle?launch=the-complete-claude-code-skills-bundle
Top comments (2)
Two details on the "it loads every session" line. The Claude Code skills docs say only the description is in context by default, and the full skill loads when it's invoked. That's the reason a long skill costs little, and the reason the description has to carry the trigger phrases you show. Location matters too.
~/.claude/skills/applies to all your projects,.claude/skills/only to that repo, and when both hold the same name the personal one runs. On "it just works": that's true for an instruction-only skill like your safety one. A skill that calls an outside service also needs the user's API key, so before installing a shared skill it's worth grepping its folder for names ending in_API_KEYor_TOKEN.You are right on both points, and I should have worded the article more carefully. Only the description sits in context by default, so a long skill does not cost much until it is invoked, and that makes the description do real work: it needs the exact trigger phrases a person would actually use. The location point matters too. I will keep personal skills in ~/.claude/skills/ and project skills in .claude/skills/ in the repo, and check for a name clash before I rely on either one. Your API key check is a good habit as well. Before installing a shared skill, I will search its folder for names ending in _API_KEY or _TOKEN and treat any hit as a prompt to read what that service does and what it can access before I run it.