Lesson 7: Skills, packaging a workflow so the machine repeats it the same way

After this lesson, you'll be able to turn a repetitive process in your company (qualifying leads, preparing a quote package, compiling research…) into a skill: a trade-teaching file for the machine, after which one sentence is all it takes for the machine to run the whole process. This is the area we rate as the best value of Claude Code for businesspeople.

What a skill is: an SOP handed to the machine employee

Every properly run company has SOPs, meaning standard procedures: do task X in steps 1-2-3, note A, never do B. A new employee holding the SOP can do the job without anyone coaching them. A skill is exactly an SOP written for Claude Code: a small folder inside .claude/skills/, containing a file describing “what this trade does, when to use it, and what the steps are”.

The payoff is in the phrase “when to use”: each skill has a description of the situation that triggers it. Just talk normally (“find me 1,000 dental clinics in the US”), and the machine recognizes that the sentence matches the “scrape-leads” skill and runs it. No syntax to remember, no need to name the skill. And as lesson 6 explained: skill is only loaded into memory when called, so even a hundred skills don't make the chat session any heavier.

Watching a real skill run to see how worthwhile it is

The original course instructor demos a lead-filtering skill he uses for his own company. He used to do that process by hand: set the search filters (15-20 minutes), run a small test batch and check quality (10-15 minutes), run the big batch, dump it into Google Sheets, cross-check and add emails… about half an hour to a full hour in total, every week.

After packaging it as a skill, he types a single sentence. The machine first runs a 25-row test batch to check quality, and if it passes, it launches 4 parallel streams and gathers 1,000 rows of data in 87 seconds, pours it into the spreadsheet and fills in the missing emails itself. Midway it hit a file-name formatting error; the machine read the documentation, fixed it itself, then updated the skill file itself so it won't stumble again next time. This is worth pondering: a skill isn't rigid software that dies on an error; it's a process with a flexible brain in the middle that adapts when something goes wrong, like an employee who knows the job.

Anatomy of a skill

Open a skill folder and the structure is just this:

• skill.md: the orchestrating file. It contains the description (trade name + when to use), the goal, the required inputs, and the checklist of steps. It's like the conductor: it doesn't play the music itself, it just holds the full score and directs.
• scripts/: the pieces of program that do the heavy and repetitive work (querying data, processing files, pouring into spreadsheets). These are the “musicians”.

Why have scripts, why not let the machine do it from scratch every time? Because any job done the same way each time should be packaged into a fixed program: fast, cheap and consistent. The AI plays the person who presses the buttons and handles exceptions, not the person who plows through line by line. Combining the two, you get the best of both worlds: the steadiness of machinery + the adaptability of intelligence. And the nicest part: you don't need to read or understand those scripts. The original instructor admits he has never opened the script file of the skill he uses every day. Who wrote it? Claude did. He just sets the task and signs off on the result.

Creating your first skill: a 4-step process

Step 1: pick the right job. The golden criteria: a job that repeats weekly, has stable steps, and takes 30 minutes or more each time. A few suggestions close to Vietnamese businesses: compile the weekend sales report from the export file of the sales software; prepare a quote package from the company template using customer info; check orders undelivered for more than 3 days and draft reminder messages; gather customer reviews from various channels into one table.

Step 2: unload the process by voice. Tell the machine how you currently do the job, as if handing over to a new employee: what comes first and what comes after, where the data comes from, which template to follow, which spots tend to go wrong and should be avoided. Attach a sample of a correct result (the best quote file you've ever made, a standard report table) and a sample of input data. Then close with: “package this process as a skill following the Claude Code skill standard.”

Step 3: the machine asks back, you decide. It will ask things like: where should the output go, what is the data input, which image source to use. Answer from your business knowledge, and for questions that are too technical, choose the option the machine recommends.

Step 4: test run and refine. Hand the skill to a brand-new session (one with no context from when it was created) and run it on real data. Wherever it goes wrong, give feedback on that spot and say: “fix it in the skill file so it doesn't stumble next time.” After a few rounds like that, accuracy climbs from around 70% to 90%, then to 98-99%. At that threshold, honestly, few flesh-and-blood employees do the work more consistently.

A frank word before you get carried away

The original instructor says that thanks to this skill library, his company earns a large profit every month while almost no longer hiring people for repetitive operations work. That's a true story from a lean US service company, and it shows how high the ceiling of this tool is. But we want you to keep a cool head: a skill running on a personal machine is only suited to the process of one person or a small team. When a process touches several departments, sensitive customer data, and needs access control and legal accountability, the problem moves into the realm of disciplined operational software, in line with what we analyzed in the automation series on mona.media. Use skills to speed yourself up first, that's the surest gain.

Try it yourself before lesson 8

1. List 5 repetitive weekly tasks of your own, score them by the criteria “stable steps + over 30 minutes”, and pick the winner.
2. Unload that process by voice + give a sample of the correct result, and have the machine package it into a skill.
3. Run it in a new session with real data, refine it 2-3 rounds, and tell the machine to record the lessons in the skill itself.

Lesson 8 covers MCP (Model Context Protocol): put plainly, “skills written in advance by other people”, a way to plug outside tools into Claude Code so it can control the Chrome browser, read outside services, plus the caution needed when plugging unknown tools into your own machine.