Week 5 — Office Hours

Turn Prompts Into Systems

How to build skills for AI — reusable, portable instruction sets that produce consistent results every time, without you in the room.

~60 minOffice HoursSkills + Systems
Recording Coming Soon
The Week 5 office hours recording will be available here after the session.

Where we've been — and why this week changes everything.

You have the tools. Now it's time to turn them into systems.

The Story So Far

01Week 1 — Built your AI Coach. Learned prompting fundamentals and how to give Claude context that makes it genuinely useful.
02Week 2 — Became a Claude power user. Models, features, Dispatch, Schedule — the toolkit most people never discover.
03Week 3 — Connected Claude to the real world. APIs, MCPs, n8n, and automation that actually runs without you.
04Week 4 — Learned the doctrine: skills as operating instructions, repeatability over drift, and keeping systems simple.

This week we go hands-on. You'll learn how to actually build skills — the structured, reusable instruction sets that turn one-off prompts into systems other people can run. The difference between "I use AI" and "I built something with AI" is a skill.

"A prompt is something you type. A skill is something you ship. This week, you learn to ship."

The fundamental distinction that separates casual AI use from real systems.

A prompt is a one-off instruction. You type it, get a response, and it's done. A skill is a reusable operating instruction: it includes the context, constraints, prerequisites, and output format so the AI produces consistent results every time — whether you run it or someone else does.

❌ Prompt (one-off)

Write me a marketing email for our new product launch.

✅ Skill (reusable)

You are a B2B SaaS copywriter. The product is [X], targeting [Y]. Use the AIDA framework. Keep it under 200 words. Include one CTA. Tone: professional but warm. Output: subject line + body.

Why the Distinction Matters

🔁

Consistency

A skill produces the same quality output on run 1 and run 100. A prompt depends on context and luck.

👥

Portability

A skill can be handed to a colleague, a scheduled agent, or an n8n workflow. A prompt lives in your head.

📈

Scalability

Skills compose into systems. Prompts are isolated events that don't build on each other.

🔎

Debuggability

When a skill produces bad output, you can inspect which layer failed. With a prompt, you just try again.

The Prompt-to-Skill Spectrum

Not everything needs to be a full skill. Think of it as a spectrum: on one end, a raw question you type into chat. On the other, a fully specified instruction set with role, context, prerequisites, constraints, and output format. Most people live at the prompt end. The goal is to move your repeating tasks toward the skill end.

01Raw prompt — "Help me write an email." Zero structure. Output depends entirely on what Claude infers from context.
02Guided prompt — "Write a follow-up email to [client] about [topic], keep it professional, under 150 words." Some structure, still needs you to fill in context each time.
03Template — A saved prompt with placeholders. Reusable, but missing prerequisite gathering and output specs.
04Skill — Complete instruction set. Role, context, prerequisites (the AI asks before starting), constraints, output format. Anyone can run it.

"If you find yourself typing the same kind of request more than three times, it's time to turn it into a skill."

A five-layer framework for building skills that work every time.

Every reliable skill follows the same five-layer structure. This isn't theory — it's the pattern behind every skill that actually ships. Master these five layers and you can turn any repeating task into a system.

The Five Layers of a Skill
1. Role — Who is the AI in this task?
2. Context — What background does it need every time?
3. Prerequisites — What inputs must it gather before starting?
4. Constraints — What rules and boundaries apply?
5. Output Format — What should the result look like?

Layer by Layer

01Role — Define the persona. "You are a senior financial analyst" produces different output than "You are a marketing intern." The role sets the expertise level, vocabulary, and judgment criteria.
02Context — Provide the background that doesn't change between runs. Company info, industry standards, team preferences. This is the "world" the skill operates in.
03Prerequisites — Tell the AI to ask for what it needs before producing output. This is the most overlooked layer. A skill that gathers prerequisites before starting outperforms one that guesses.
04Constraints — Set the boundaries: word count, tone, format restrictions, things to avoid. Without constraints, the AI defaults to generic, verbose output.
05Output Format — Specify exactly what the result should look like. Headers, sections, bullet points, tables. The more precise the output spec, the less time you spend reformatting.
Skill Template — Copy and Customize
# [Skill Name]

## Role
You are a [specific role with expertise level]. You [key behavior or perspective].

## Context
- [Company/team/project background]
- [Industry or domain context]
- [Any standards or references to follow]

## Prerequisites
Before producing any output, ask the user for:
1. [Required input #1]
2. [Required input #2]
3. [Required input #3]
If any prerequisite is unclear, ask for clarification. Do not guess.

## Constraints
- [Word count / length limit]
- [Tone and voice]
- [Things to avoid]
- [Format restrictions]

## Output Format
Produce the result as:
- [Section 1: description]
- [Section 2: description]
- [Section 3: description]

Use [formatting style]. Do not include [excluded elements].

Example: Meeting Prep Skill

Complete Skill Example
# Meeting Prep Brief

## Role
You are an executive assistant who prepares concise, actionable meeting briefs.

## Context
- Company: [Your company name]
- Meeting briefs should enable the attendee to walk in prepared in under 2 minutes of reading.
- Prioritize decisions needed and open questions over background summary.

## Prerequisites
Before producing the brief, ask for:
1. Who is the meeting with? (names and roles)
2. What is the meeting about? (agenda or topic)
3. What is our goal? (decide, inform, explore, or close)
4. Any relevant history? (past meetings, open items, blockers)

## Constraints
- Maximum 250 words
- No filler or pleasantries
- Use bullet points, not paragraphs
- Flag any risks or sensitivities

## Output Format
1. **Meeting**: [who + when]
2. **Our Goal**: [one sentence]
3. **Key Context**: [3-5 bullets]
4. **Decisions Needed**: [numbered list]
5. **Open Questions**: [numbered list]
6. **Watch Out For**: [risks or sensitivities, if any]

"A skill that doesn't need you in the room is a skill that's finished. If someone else can't run it and get the same quality output, keep refining."

Three ways to run your skills — and how to pick the right one for each task.

A skill is interface-agnostic — it works whether you run it in chat, through an integration, or via code. The question isn't which interface is "best." It's which interface matches the frequency, complexity, and autonomy level of the task.

💬

Chat

Interactive

Exploration, brainstorming, one-off runs, testing new skills. You're in the loop for every step.

🔗

Integrations

Automated

Recurring tasks, scheduled workflows, MCP connections, Dispatch. Runs without you once configured.

Code

Programmable

Complex logic, custom data transforms, high-volume processing, API integrations. Maximum control.

The Escalation Ladder

01Start in chat — Prove the skill works interactively. Refine the five layers until output is consistent. This is your testing ground.
02Move to integrations — When you've run the skill 3+ times manually. Set it up in Dispatch, Schedule, or n8n. Let it run on autopilot.
03Graduate to code — Only when integrations can't handle the logic. Complex branching, custom transforms, scale requirements, or multi-step pipelines.
❌ Over-engineering

I need to analyze customer feedback, so let me build a Python script with the Anthropic API, set up a database, and deploy it to AWS.

✅ Right-sizing

I need to analyze customer feedback, so let me write a skill in chat, test it on 10 examples, then schedule it in Dispatch to run weekly on my inbox.

Most people jump straight to code because it feels more "real." Don't. The sweet spot for 90% of business tasks is chat to prove the concept, then integrations to automate it. Code is the exception, not the rule.

"The best interface is the simplest one that does the job. If you're writing code to do something Dispatch can handle, you've over-engineered it."

A step-by-step walkthrough of turning your most common tasks into production-ready skills.

Theory is done. Let's build. The process is always the same: identify a repeating task, extract the five layers, test until consistent, then deploy to the right interface.

Step 1: Pick Your Task

Start with the task you do most often with AI. Not the most complex — the most frequent. Frequency is what makes a skill valuable. A skill you use daily returns 10x more value than a brilliant skill you use once a month.

📧

Email Drafting

Client responses, internal updates, follow-ups. High frequency, high variation.

📊

Data Summarization

Meeting notes, report summaries, research briefs. Structured output from unstructured input.

📝

Content Creation

Social posts, blog outlines, internal docs. Repeating format with variable content.

🔍

Review & Analysis

Code reviews, proposal feedback, competitive analysis. Structured critique with criteria.

Step 2: Extract the Five Layers

For your chosen task, answer these questions — they map directly to the skill template:

Prompt: Extract skill layers from a task
I do this task regularly with AI:

[Describe the task in detail — what you ask for, what good output looks like, what mistakes you've had to correct]

Help me extract the five layers of a reusable skill:

1. Role — Who should the AI be? What expertise level and perspective?
2. Context — What background does the AI need every time? What doesn't change between runs?
3. Prerequisites — What information must I provide (or the AI must ask for) before it starts?
4. Constraints — What rules apply? Length, tone, format, things to avoid?
5. Output Format — What should the result look like? Headers, sections, structure?

Write the complete skill using the standard template format. Include [placeholders] for the parts that change each time.

Step 3: Test and Refine

Run the skill five times with different inputs. Each time, evaluate: did the output meet your standards without correction? If not, identify which layer was weak and tighten it. Common failure modes:

Output too generic — Role or context layer is too vague. Add specifics: industry terms, company voice, concrete examples of good output.
Missing information — Prerequisites layer is incomplete. Add the questions the AI should ask before starting.
Wrong format — Output format layer is underspecified. Show an example of the exact structure you want.
Too long or off-tone — Constraints layer needs boundaries. Add word count, tone adjectives, and explicit "do not" rules.

Step 4: Deploy

Once the skill produces consistent results in chat, move it to the right interface. Save it as a Project instruction for daily use, add it to Dispatch for on-demand automation, or schedule it for recurring tasks.

Ready to build your first skill?
Use the AI Coach to walk through the skill-building process step by step.
Open AI Coach

"The first skill takes 20 minutes to build. The second takes 10. By the fifth, you're writing them in 5 minutes because you've internalized the pattern. That's the point."

Key Takeaways

Prompts are one-off; skills are systems — A skill includes role, context, prerequisites, constraints, and output format. It works without you in the room.
The five-layer template is universal — Every reliable skill follows the same structure. Master the template and you can systematize any repeating task.
Chat → Integrations → Code — Start interactive, automate what repeats, code only when integrations can't handle it. Most tasks never need code.
Prerequisite gathering is the highest-leverage layer — A skill that asks the right questions before starting outperforms a skill with a better prompt that guesses.
Test with five runs, not one — A skill that works once might be lucky. A skill that works five times with different inputs is ready to ship.

Homework

01Build 3 skills from scratch — Pick your three most-used AI tasks. Convert each one into a complete skill using the five-layer template. Test each skill 5 times with different inputs.
02Run the portability test — Give one of your skills to a colleague (or paste it into a fresh conversation with no prior context). Does it produce the same quality output? If not, identify which layer needs tightening.
03Deploy one skill to an integration — Take your best-performing skill and move it out of chat. Save it as a Project instruction, set it up in Dispatch, or schedule it as a recurring task.
04Start your skill pack — Collect your working skills into a single document or Project. This is the beginning of your personal operating system for AI — the collection of skills that define how you work.
05Audit one existing workflow — Pick an automation you built in Weeks 2–4. Is it powered by a raw prompt or a proper skill? If it's a prompt, upgrade it using the five-layer template.

"Week 1 you learned to talk to AI. Week 2 you learned to use it. Week 3 you connected it to everything. Week 4 you learned the doctrine. Week 5 you built the systems. That's the complete toolkit."

From the Office Hours

Questions From the Session

Real questions from the live office hours — practical answers you can use today.

Ready to build skills?

Convert your top tasks into reusable skills, test them for consistency, and start your personal skill pack. Everything you need is in the homework above.