Write down how you do a job, turn it into a Claude Code skill (one folder, one SKILL.md), and test it on a real job until it does it your way.
Swipe or tap Next · checked on 2026-10-06
Write down how you do the job in a text file in your project folder (rough is fine), start Claude Code there, and paste this. Claude drafts the skill, you run it on a real job, and Claude fixes what went wrong.
Start Claude in your project
cd <your project folder>
claudeThe prompt (copy all of it) · lines 1-4 of 11. Copy all copies the whole prompt; read it in full on the page.
Help me turn how I do a job into a Claude Code skill, following this guide:
https://receiptsgroup.com/guides/claude-code-skill
My notes on how I do it are in <file name>. The skill's job, in one line: <what it should do>.This is the manual way: the file, where it goes, and how to test it.
.claude/skills/<name>/SKILL.md. For every project on your computer: ~/.claude/skills/<name>/SKILL.md.--- lines. The important field is description: what the skill does and when to use it. Claude reads the descriptions to decide which skill fits the job./<name> in Claude Code, with anything after it as the job.SKILL.md. Anthropic's docs suggest keeping SKILL.md under 500 lines and moving detail into those files.The steps you really follow, in your words: which tool, which folder, what you check before you call it done, and what usually goes wrong. Rough is fine; Claude asks about the gaps. If you learned it from someone else's course or video, write your own version of what you do now. Don't paste their material into a skill, and don't publish it as yours.
Save it in your project
cd <your project folder>
mkdir -p notes
# write your steps into notes/howto.txt with any text editor, then check:
wc -w notes/howto.txtOne folder per skill
mkdir -p .claude/skills/<short-name>Start claude in the project and ask it to fill this in from notes/howto.txt. The description is the part people rush and regret: if it doesn't say when to use the skill, Claude won't.
Prompt: write it
Read notes/howto.txt. Fill in the template in this guide as .claude/skills/<short-name>/SKILL.md for my setup: exact commands, my folders, my tools. Leave Mistakes to avoid empty for now. Show me before you save..claude/skills/<short-name>/SKILL.md (template) · Part 1 of 2 · Copy copies all 23 lines
---
name: <short-name>
description: <What it does, in one sentence>. Use when <the words or situations that should trigger it, e.g. "the user asks to X", "a file in Y changes">.
---
# <Short name>
## Before you start
- Read <the files it needs>. Check <what must be true first>.
## Steps
1. <The first action, with the exact command or click.>
2. <...>
3. <...>.claude/skills/<short-name>/SKILL.md (template) · Part 2 of 2 · Copy copies all 23 lines
## What good looks like
- <How you know it worked: the file it makes, the output it prints.>
## Mistakes to avoid
- <Filled in after the test. One line each.>
## Never
- <Anything it must not do: spend money, post, delete, print keys.>Open a new Claude Code session (so it starts fresh) and use it on something real. Watch where it hesitates, guesses or goes off script.
Two ways to test
/<short-name> <a real job, e.g. "set up the weekly report for October">
# or, to check that Claude finds it on its own, just describe the job without the name:
<the job, in the words you'd normally use>Every wrong turn becomes one line under Mistakes to avoid, or a fix to a step. Then test again. Two or three rounds is normal.
Prompt: fix it
In that run you <what went wrong>. Update .claude/skills/<short-name>/SKILL.md so it doesn't happen again: fix the step, and add one line to Mistakes to avoid. Show me the diff before you save.Example (made up): a skill that turns a call transcript into a follow-up email draft. Short, specific, with a never list.
.claude/skills/follow-up/SKILL.md · Part 1 of 2 · Copy copies all 25 lines
---
name: follow-up
description: Drafts a follow-up email from a sales call transcript in calls/. Use when the user asks for a follow-up, a recap email, or "what do I send after this call".
---
# Follow-up email from a call
## Before you start
- Read the transcript the user names (calls/<date>-<name>.txt) and brain/VOICE.md.
## Steps
1. List what the customer asked for, in their words, and every promise we made.
2. Draft the email: thank them in one line, recap what they asked for, the next step with a date, nothing else.
3. Under 120 words. My voice from brain/VOICE.md.
4. Save it as drafts/<date>-<name>-follow-up.md and show it..claude/skills/follow-up/SKILL.md · Part 2 of 2 · Copy copies all 25 lines
## What good looks like
- Every promise in the email is in the transcript. Nothing new is promised.
## Mistakes to avoid
- Don't summarize the whole call; one recap line per thing they asked for.
- Don't invent a date; if none was agreed, ask the user.
## Never
- Never send the email. Never add prices that aren't in the transcript.1. Turn this chat into a skill
We just did <the job> together and it took a lot of back and forth. Turn what worked into a skill: .claude/skills/<short-name>/SKILL.md with the steps we ended up using and a Mistakes to avoid list from what went wrong. Show me before you save.2. Check your descriptions
Read every SKILL.md under .claude/skills/ and ~/.claude/skills/. For each, tell me in one line when Claude would pick it, and flag any two whose descriptions overlap enough to confuse you. Read-only.3. Split a skill that got too long
SKILL.md for <name> is getting long. Keep the steps and the mistakes in SKILL.md; move background and reference material into reference.md in the same folder and link it. Show me the diff.4. Make it manual-only
I only want <name> to run when I type /<name>. Add disable-model-invocation: true to its header and explain what changes.My three run my video setup. One directs the edit (brief, checks, render, the quality gate). One renders my HeyGen avatar with my look and my voice, Avatar IV every time. One schedules the finished posts.
They're short, about twenty lines each: a description that says when to use it, and pointers to the longer docs in the project where the detail lives and gets updated. So the skill stays a map, and nobody has to keep two copies of the instructions in sync.
The description doesn't say when to use it. Add the words you actually type when you need it (“Use when the user asks for a recap, a follow-up...”).
Narrow the description, or add disable-model-invocation: true so it only runs when you type /<name>.
/<name> isn't foundCheck the path is exactly .claude/skills/<name>/SKILL.md (capital SKILL, inside a folder), and start a new Claude Code session.
The skill is missing your specifics: your tools, folders and checks. Add them; that's most of what makes it yours.
Move reference material into a second file and link it (real-use prompt 3). Anthropic's docs suggest keeping SKILL.md under 500 lines.
What each page backs up is listed at the end of the full guide.
A page of steps in your words, tested on a real job, with a list of the mistakes it already made so it doesn't make them again. Make one for the thing you explain most often.
Want help setting this up? Receipts Group builds these systems.
Open the full guide as a page (every file in full, plus the table of contents).