Teach Claude once.

Last week I mapped the spectrum: prompt to skill to scheduled workflow. Skills are the lowest-friction entry point. No Pro subscription, no desktop app, just Claude chat. This week: what to actually do with that.

Why does Claude forget you between chats?

Every time you open a new chat, Claude starts from scratch. It does not know your writing style, your brand colors, your format preferences, your constraints, or how you have told it to structure things a hundred times before. You either re-explain all of that, or you accept output that does not quite fit. This is not a complaint. It is a fact worth sitting with.

Most people compensate without realizing it. They keep a notes document full of "Claude context" that they paste at the start of each session. They retype the same instructions in slightly different words every time. They get inconsistent output and blame the tool, when the real issue is they are asking Claude to remember something it has no mechanism to remember.

This is the problem skills fix. You teach Claude who you are once. It knows from then on.

What is a Claude skill (and what is it not)?

A skill is a saved instruction set that lives inside Claude. When you activate one, Claude already knows the job before you type a word - the format, the context, the constraints, everything you would otherwise have to explain. You stop reconstructing. You just start.

Skills live in Claude chat. No Pro subscription. No desktop app. A skill is not a scheduled workflow - that is Cowork territory, and it requires different setup. A skill does not run automatically. You activate it when you need it, and it knows what to do.

Build a skill when:

• You do the same type of task more than once a week.
• You are re-explaining context that never changes.
• You want consistent output every time, not output that varies based on how well you remembered to explain things that day.

Do not bother when:

• It is a one-off task.
• A single-line prompt already handles it.
• You need it to run on a schedule.

On downloading skills from the internet: do not. Not from strangers. A skill built by someone else was built for someone else's workflow. It encodes their context, not yours. Generic output is the best you will get from it. There is one exception - official skills from verified sources. Anthropic publishes skills for specific technical tasks: creating Word documents, PowerPoint decks, Excel files, PDFs. These are reference tools that tell Claude how to use a specific library correctly, written by the people who built Claude. Same goes for Microsoft's Azure skills, Supabase's database skills, shadcn's component library. When the skill is about the tool and the tool's team built it, that is worth installing.

I have curated the ones worth knowing at brisk.vision/skills - 51 skills across 8 categories, filtered for quality and source.

How do you build a Claude skill?

Two official methods exist. I use one of them. And I will teach you a third.

Method 1: From scratch

Open Claude chat. Find the Skills section in the sidebar. Click Add new skill. Write the instruction set directly: what Claude should know, what it should always do, what format to use, what to never do. Name it. Save it.

This works when you already know exactly what the skill needs to say. If you are not sure - and most of the time you will not be - use Method 2.

Method 2: Chat, get it right, then package it

This is the method I use. The idea: prove the skill works before you save it. Before you start, check that skill-creator is active. Anthropic ships it pre-installed in Claude Desktop and Cowork. In Claude chat on the web, check under Customize > Skills. Skill-creator is what turns your conversation into a properly structured, installable skill file. Without it, you are formatting that file manually.

The process:

1. Open Claude. Do the task you want to systematize, normally.
2. Iterate until the output is genuinely good. Not fine. Good enough to use.
3. Tell Claude: "Use skill-creator to package everything we've worked out as a reusable skill."
4. Skill-creator generates a complete skill: trigger description, instruction set, example outputs, correct structure throughout.
5. Ask Claude to save the skill directly to your account. This skips downloading a file, renaming it, zipping it, and uploading it manually.
6. Review the saved skill. Adjust anything that is off.

The main mistake: packaging before the output is actually good. The conversation is the draft. The skill is the published version. Do not publish a draft.

Method 3: Record, analyze, package

Most people hit a wall before they even start: they do not know how to explain the skill. They do the task by feel, not by steps they could put into words.

Here is what to do instead. Record your screen while you do the task. Upload the recording to Claude and ask: "Watch this and describe exactly what I'm doing, step by step." Claude produces a summary of your own workflow. You proofread it, adjust anything that is off, then use that as the instruction set - and package it as a skill.

This works especially well in a company setting. Instead of trying to write down a team workflow in a document nobody reads, record someone doing it. One screen recording. Claude turns it into a replicable instruction set. You package it as a skill. Now the whole team has access to a process that used to live in one person's head - without a training session, without a manual, without anyone having to articulate from scratch what they cannot easily put into words.

What does a real Claude skill look like?

The brisk. Instagram carousel skill is the clearest example I have of what this looks like in practice.

Before it existed, every carousel started with me pasting roughly 300 words of context: brand colors, hex codes, font rules, logo variants per background type, the seven slide roles, overlay opacity logic for dark and light and teal backgrounds, image matching rules, caption format, the non-negotiables checklist. All of it. Every chat. Every carousel.

The skill was built because of one specific moment: the first carousel that came out good enough to post under my name. Not fine. Actually good, by my own standard. That moment made it clear this process needed to be repeatable. I could not re-explain 300 words every time.

I built v1 using Method 2. It took about 30 minutes, not 15. The reason: I gave Claude the brand brief (colors, fonts) but not a design example. Without something visual to reference, Claude approximated the aesthetic and I iterated more to get the look right. Time scales with how clearly you can picture the output before the conversation starts. Writing tasks, analysis tasks, structured formats - 15 minutes is realistic. Anything where you are discovering what "right" looks like as you go: add time for that discovery, because it is going to happen regardless.

The skill is now on v3. The gap between v1 and v3 was real carousels, specific friction, specific fixes. Text on bright backgrounds was unreadable, so the v3 solution was auto dark/light text selection based on composite brightness. Version 1 worked. Version 3 works better. The iterations come from using it, not from planning it. That is what you are building: not the finished version, the first version that is good enough to use. Then you improve it from there.

Sources and further reading

• Workflows. - the prompt to skill to scheduled workflow spectrum
• Agent Skills. - what skills are and why they matter
• The brisk. skills directory - 51 vetted skills across 8 categories
• Claude skill-creator and Skills documentation - Anthropic

Claude does not know you yet. Teach it once. Open Claude chat, think of the task you have re-explained more than three times, start the conversation, get the output right, then ask skill-creator to package it. If you cannot easily explain the steps, record your screen first and let Claude watch and describe. That is the whole method. The skill does the rest every time you use it.