# Agent Brief. build in the style of skillselion.com

> Machine-extracted from a live on-demand funnel teardown (2026-08-05). 100% facts —
> measured tokens, detected patterns, harvested proof strings. No LLM interpretation.
> Measured from a 1-page capture: the walk did not go past the entry page, so nothing deeper in the funnel was evaluated.
> Tokens: `tokens.json` / `tailwind.css`.

**Funnel:** Homepage / Lander

## Palette (area-weighted from live CSS)
| Hex | Usage | Likely role |
|-----|------:|-------------|
| `#efebe0` | 69.9% | background |
| `#f7f5ef` | 15.6% | background |
| `#fbfaf6` | 13.6% | background |
| `#0891b2` | 0.3% | accent/brand |
| `#9a9a93` | 0.2% | support |
| `#5b554c` | 0.2% | support |
| `#ffffff` | 0.2% | background |

Curated roles: `primary=#efebe0` · `accent=#efebe0` · `bg=#efebe0` · `surface=#f7f5ef` · `text=#948b7d`

## Type
- Display: `ui-sans-serif`
- Body: `JetBrains Mono`
- Size scale (px): 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 21
- Radius (px): 4, 8, 14, 50

## Patterns detected (fact-based). 5/10
- **FAQ / objection handling**. An accordion / FAQ block answering objections. _(home: What is Skillselion? An automatically updated directory of skills, MCP servers and marketp)_
- **Trusted-by logo wall**. Customer/company logos or a "trusted by / used by" claim. _(home: backed by)_
- **Usage / adoption proof**. A count of developers / teams / companies / stars using the product. _(home: 1K+ installs)_
- **Ranked "best of" list**. A ranked / numbered comparison of options ("best X for Y", "top 5"). the affiliate roundup pattern. _(home: ranked list)_
- **Press / "as seen in"**. Media logos or an "as seen in / featured in" claim borrowing publication credibility. _(home: featured on)_

## Proof language (harvested strings → templates)
- _(none extracted)_

## Funnel facts
- Depth reached: 1 step(s)
- Proof points: 0 across 0 step(s)
- Discount/anchor pricing: no · Countdown: no · Subscription: no

## To replicate
Match the palette + type tokens above and deploy the detected patterns. Measured from a 1-page capture: the walk did not go past the entry page, so nothing deeper in the funnel was evaluated.
