Skip to main content
View .mdOpen in ClaudeOpen in ChatGPT

Reading docs

Three machine-readable surfaces let agents read these docs without scraping HTML or rendering JS.

/llms.txt, the index​

https://docs.funnelfizz.com/llms.txt

A sparse structured index of every docs page, title and one-line summary per entry. ~3–5 KB. Use when your agent needs to know what pages exist before deciding what to fetch ("which page covers splits?").

Follows the llms.txt convention proposed by Jeremy Howard / Answer.AI.

/llms-full.txt, the corpus​

https://docs.funnelfizz.com/llms-full.txt

Every page concatenated into one markdown file. Use when your agent needs the whole knowledge base in context to answer general questions or write code against FunnelFizz.

Both files regenerate on every docs build, so they're always current.

Per-page .md routes​

Append .md to any docs URL to get the raw markdown source minus navigation chrome:

https://docs.funnelfizz.com/concepts/stages       ← rendered HTML
https://docs.funnelfizz.com/concepts/stages.md    ← clean markdown

Use when the agent only needs one specific page, cheaper than fetching the full corpus.

Context7​

Context7 is an indexed MCP-based docs search service by Upstash. Agents that have Context7 enabled can run:

use context7 funnelfizz

…and Context7 returns relevant doc excerpts. Complementary to our own MCP server: Context7 serves docs, the FunnelFizz MCP serves your live workspace.

Our context7.json (in this repo at docs/context7.json) gives Context7 a few canonical rules to surface alongside excerpts:

{
  "$schema": "https://context7.com/schema/context7.json",
  "projectTitle": "FunnelFizz",
  "description": "Marketing funnel builder for solo founders and small SaaS teams.",
  "rules": [
    "Plans are FREE, HOBBY, PRO only. There is no TEAM plan.",
    "Domain is funnelfizz.com (not .app).",
    "Brand is FunnelFizz (PascalCase) in user-facing copy.",
    "The 4 stages are AWARENESS → CONSIDERATION → TRIAL → CUSTOMER in fixed order.",
    "Stripe connection uses restricted keys (rk_live_...) with exactly 7 read scopes."
  ]
}

When to use which​

TaskUse
"Which page covers splits?"llms.txt
"Tell me everything about FunnelFizz"llms-full.txt
"Walk me through stages"/concepts/stages.md (single page)
Inside an MCP-aware agent with Context7use context7 funnelfizz
Doing actual setup or reading live dataMCP, not docs