Theme

Font

Size

Text width

Line spacing

Controls accent

0 of 0 0%
MODULE 1.1

Understand what a skill teaches

Separate instruction, tool, and result before automating.

At the end: Choose a repeatable task and explain where the skill fits in.

6 topics
45 min practice estimate
6 commented exercises
1 final check
1

Separate the recipe from who cooks

Ingredients Recipe Cook Assessed dish
The recipe guides the work, but it doesn’t buy ingredients or taste the dish by itself.

What it is

A skill is a reusable procedure that guides an agent through a task. In the video analogy, the result is the pancake, the agent is the cook, and the skill is the recipe. The file records decisions you don’t want to explain again with every request.

Why learn

Without a procedure, the agent has to fill in gaps: size, format, sources, and quality criteria. Recording these choices reduces avoidable variation. This doesn’t make generation infallible: different ingredients and unavailable tools still change the outcome.

Key concepts

Inputthe received material.
Processthe actions and decisions.
Outputthe delivered artifact.
Acceptanceevidence that the delivery serves its purpose.
COMMENTED EXAMPLE · 1.1.1
Loose request: “Make my report.”
Contracted request: “Turn this CSV into a
weekly summary, with totals by channel, period, and pending items.”

✓ Do it like this

Name the input and show an approved output.

✗ Avoid this mistake

Promise identical results just for existing an SKILL.md.

Practice before revealing

Choose a task you repeated three times and describe the input and output in one sentence.

View commented response

Example: “From a weekly sales CSV, produce a Markdown report with totals per channel and questions for review.” A task with boundaries lets you test the skill.

2

Differentiate prompt, skill, rule, and tool

Request Guidelines Procedure Tools
The layers answer different questions: what, which rules, how, and with what capabilities.

What it is

A prompt asks for something in this interaction. A skill stores a specialized procedure. AGENTS.md records durable project guidance. A tool carries out a concrete capability, like reading a file or querying a service. These pieces complement each other.

Why learn

When everything goes into the global rule, details of one task start influencing unrelated tasks. When everything stays in the prompt, you repeat instructions. Separating roles helps you find the correct place for each correction.

Key concepts

Promptintent and execution data.
Skillreusable method.
AGENTS.mdproject conventions.
Toolcapability and access.
COMMENTED EXAMPLE · 1.1.2
Prompt: “Make the September report.”
AGENTS.md: “Project documentation is in Portuguese.”
Skill: “Validate data, calculate, write, and verify.”
Tool: a CSV reader or a calculation script.

From concept to action

  1. Request: identify the initial condition.
  2. Guidelines: apply the described decision.
  3. Procedure: verify the effect in the example.
  4. Tools: record the evidence of output.

✓ Do it like this

Put the calculation rule next to the process that uses it.

✗ Avoid this mistake

Treat MCP as a synonym for skill or for automatic access.

Practice before revealing

Where should the rule “don’t invent missing numbers in the report” go?

View commented response

In the report skill contract, with behavior for missing data. If it’s a general project requirement, it can also appear in the project guidance without duplicating contradictory versions.

3

Find tasks that deserve a skill

Frequency Visible output Low impact Good first case
Choose a small case that’s enough to verify the first run manually.

What it is

The best first candidate is a frequent task with a definition of “good” that you can demonstrate. It doesn’t need to be complex. A video description, a text review, or a short report already lets you learn the whole cycle.

Why learn

Starting with “manage my business” mixes planning, writing, accounting, and publishing. You can’t locate the mistake. A smaller task produces an assessable artifact and gives faster feedback before connecting important systems.

Key concepts

Frequencyhow many times it repeats.
Cost of errorwhat a failure causes.
Observabilityhow to recognize a correct result.
Scope where the task ends.
COMMENTED EXAMPLE · 1.1.3
Candidate A: review a paragraph → easy to compare.
Candidate B: prepare a local report → verifiable numbers.
Candidate C: operate the whole company → too broad a scope.

✓ Do it like this

Start with a local output that can be reviewed.

✗ Avoid this mistake

Link the first version directly to external sends or changes.

Practice before revealing

Compare two tasks using frequency, output clarity, and the cost of error.

View commented response

Prefer the one that combines repetition, clear output, and cheap review. A less frequent task can win if rework is high; justify the criterion instead of using a score without context.

4

Draw the input and output contract

Received CSV Valid fields? Calculations Report + QA
Validation comes before writing: writing well doesn’t fix a column that doesn’t exist.

What it is

The contract describes what needs to be delivered, what will be produced, and what happens when information is missing. In our lab, the CSV contains date, channel, and value. The output includes observed period, total, totals by channel, and pending items.

Why learn

Missing data should not turn into silent assumptions. If “value” doesn’t exist, the skill can’t calculate revenue. A useful response identifies the missing field, stops only the dependent step, and preserves the original material.

Key concepts

Pre-condition minimum required data.
Post-condition mandatory content.
Invariant something that cannot change.
Predicted failure a useful response without making things up.
COMMENTED EXAMPLE · 1.1.4
Input: UTF-8, date,canal,valor columns.
Value: decimal with dot; BRL currency defined by the exercise.
Output: relatorio.md + qa.json.
If there is no mandatory column: report the error and do not generate a report.

✓ Do it like this

Define the date format and currency unit.

✗ Avoid this mistake

Add values from different currencies without an explicit rule.

Practice before revealing

Add a stopping condition and a limitation to the contract.

View commented response

Stop if there is an invalid date; limit the analysis to descriptive totals, without inferring causes of sales changes. The contract should say what to do, not just list prohibitions.

5

Read the video’s promise critically

Author’s account Hypothesis Local test Limited decision
Use the reference to form hypotheses; use your cases to decide.

What it is

The six steps are the author’s practical proposal: start from the result, define the task, calibrate freedom, verify, compare configurations, and incorporate feedback. “Better than 99%” is the promotional title of the reference, not a measured result in this course.

Why learn

The video shows different outputs across models in a visual task. This is a useful case study, but it doesn’t establish a universal ranking. Observed times from that one run also don’t guarantee duration, price, or quality for your account.

Key concepts

An author’s account does not equal a benchmark.
Repeatability requires multiple cases.
Tools depend on real access.
Self-assessment requires evidence.
COMMENTED EXAMPLE · 1.1.5
Hypothesis: “A cheaper configuration is enough for summaries.”
Test: same cases, same rubric, more than one run.
Valid conclusion: “In this sample, it met the criteria.”

From concept to action

  1. Author’s account: identify the initial condition.
  2. Hypothesis: apply the described decision.
  3. Local test: check the effect in the example.
  4. Limited decision: record the output evidence.

✓ Do it like this

Identify which conclusions depend on the context.

✗ Avoid this mistake

Repeat quality percentages without an experiment.

Practice before revealing

Turn “the expensive model is always better” into a testable hypothesis.

View commented response

“In our image selection cases, configuration A has fewer images out of context than B, using the same evaluation criterion.” Now there is a bounded comparison.

6

Prepare your learning lab

Prepare Execute Inspect Record
The lab produces artifacts you can open and verify without relying solely on the agent’s report.

What it is

You’ll work with synthetic data and local files. Download the kit from the homepage, open the folder in Codex, and keep input, output, and evidence separate. The exercise doesn’t require a paid API or a connected CRM account.

Why learn

Separating folders makes it possible to redo an execution without replacing the original. With each change, you can compare the previous report with the new one and verify whether the fix had any unintended effect.

Key concepts

dados/ immutable inputs.
saidas/ execution results.
evidencias/ tests and observations.
SKILL.md versionable procedure.
COMMENTED EXAMPLE · 1.1.6
laboratorio/
  dados/vendas.csv
  saidas/
  evidencias/
  .agents/skills/relatorio-semanal/SKILL.md

✓ Do it like this

Save a copy of the input used in each comparison.

✗ Avoid this mistake

Change data, model, and instruction at the same time.

Practice before revealing

Open the kit CSV and manually calculate the total of the four lines.

View commented response

The values 120,50 + 80,00 + 199,50 + 100,00 add up to R$ 500,00. This standalone calculation will be a reference to verify the first report.

CHECK WITHOUT BLOCKING

Check your understanding

A skill needs to access a CRM. What provides that access?

What you take from this module

Choose a repeatable task and explain where the skill fits in.

  • Separate the recipe from the cook.
  • Differentiate prompt, skill, rule, and tool.
  • Find tasks that deserve a skill.
  • Draw the input and output contract.
  • Read the video’s promise critically.
  • Prepare your learning lab.

Next action: save the exercise in your learning lab and record what still needs review.

Module reference: the provided transcript and course sources and technical notes.