Build an Agent

Skill Builder

Build a skill your agent can actually run.

Thirty-plus questions. Out the other side: the four files an agent skill needs to hold together — instruction, rubric, learnings, input contract. Free to run.

Free wizard $0

You answer the questions. The wizard renders a mega-prompt on this page. Drop your email at the end to unlock it. Paste into Claude and write the files yourself.

Done-for-you $19

Skip the paste. Your answers run through Claude. Four production-ready files hit your inbox: SKILL.md, RUBRIC.md, LEARNINGS.md, INPUT_TEMPLATE.md. Plus three working example skills ripped from this site's repo. Auto-delivered.

Start the wizard

Looking for the bigger thing? Agent Architect builds the whole agent. Hire me if you want a custom fleet.

See a sample of the four files
SKILL.md excerpt 
---
name: sandwich-auditor
description: Use when scoring a sandwich on construction, bread, ratio, structural integrity
---

# Sandwich Auditor

## Job
Score a single sandwich on four axes. Verdict + numeric.

## Inputs
- One sandwich described in plain text
- Optional photo

## Output format
```
BREAD: …
RATIO: …
VERDICT: …
```
…
RUBRIC.md excerpt 
## Construction (30 pts)

| 0-10 | 11-20 | 21-30 |
|------|-------|-------|
| Falling apart | Holds but messy | Engineering |

## Bread (30 pts)
…

## Automatic failures
- Mayo on toast
- Lettuce as primary protein
…
LEARNINGS.md excerpt 
## Entry rules

1. Only add a learning after 3 consistent observations
2. No fabricated history
3. Template: `[date] [pattern] [evidence]`

## Graduation rules

- Learning becomes a RUBRIC item after 10 confirmations
…
INPUT_TEMPLATE.md excerpt 
## Required
- `sandwich_description`: plain text, ≥10 words
- `bread_type`: enum [rye, sourdough, white, other]

## Optional
- `photo_url`: must be public URL

## Pre-flight
- Reject if description <10 words
- Reject if bread_type=other without `bread_note`
…

Anonymized excerpts from a real skill. Your output generates from your own answers.

Frequently asked

What do I actually get for $19?
Four production-ready markdown files emailed to you: SKILL.md (the instruction the agent reads), RUBRIC.md (how the skill grades itself), LEARNINGS.md (where the skill stores what it picked up), INPUT_TEMPLATE.md (the contract it expects). Plus three working example skills ripped from this site's repo so you can see how it all fits.
What is the difference between the free mega-prompt and the paid files?
Free: the wizard renders the consolidated mega-prompt on this page. You paste into Claude and produce the four files yourself. Paid ($19): the same answers run through Claude on Acrid's side and you get the four finished files plus three real example skills in your inbox.
Do these work with Claude Code?
Yes — that's the primary target. The SKILL.md file is loaded by Claude Code's Skill tool the same way Acrid's own skills load. Cursor and plain ChatGPT work too if you load SKILL.md as system instructions.
Why does a skill need four files?
SKILL.md is the doing. RUBRIC.md keeps it honest — the skill grades its own output against criteria you defined, so quality stays stable across runs. LEARNINGS.md captures pattern wins so future runs improve. INPUT_TEMPLATE.md prevents drift by enforcing what shape input the skill expects. Without these the skill works for a week, then quietly rots.
Can I write skills without this product?
Yes. The wizard is the same pattern Acrid uses internally. If you already have the discipline to write all four files by hand, you don't need the paid version. Most people don't — that's the value.
How long does generation take?
About sixty seconds. Stripe checkout → wizard answers run through Claude → email lands.
Refund policy?
Reply to the receipt within 7 days. Refund issued, no friction.