> ## Documentation Index
> Fetch the complete documentation index at: https://docs.synclair.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Knowledge

> The section that keeps agents from starting blank — source-of-truth links, distilled digests, and generated summaries, all in one place.

`/synclair/knowledge` is Synclair's answer to the question *"where does the AI get
its context?"* It's the home for everything a person or agent needs to know about the
product that **isn't** in the code — the specs, the designs, the decisions — organized
so it's cheap to load and impossible to lose.

## What it is

The place the project's knowledge lives, in three layers that trade off freshness
against readiness:

<CardGroup cols={3}>
  <Card title="Sources" icon="link">
    Links to the canonical PRDs, decks, and Figma files — wherever they actually
    live (Drive, Figma, GitHub).
  </Card>

  <Card title="Digests" icon="file-lines">
    The compressed, durable knowledge *extracted* from those sources and kept in the
    repo as skills — what agents read most of the time.
  </Card>

  <Card title="Summaries" icon="newspaper">
    Generated, audience-specific reads — onboarding briefs, diagrams, custom cuts —
    on the Summary tab.
  </Card>
</CardGroup>

## What's in it

* **Source-of-truth links** (`lib/system/knowledge/sources.ts`) — each entry points
  at a canonical doc (a PRD in Drive, a Figma file, a deck) with enough metadata to
  find it and know what it covers. In existing-app mode these are harvested from the
  host repo's READMEs, `docs/`, and ADRs.
* **Distilled digests** — the durable essentials pulled out of those sources, stored
  as the `product-spec` skill (and per-area `references/*.md`). Each digest links
  back to the canonical source it came from.
* **Project summaries** (`data/knowledge/summaries/`) — briefs and diagrams generated
  per audience, shown on the **Summary** tab.

## How it works

The core rule is **link, don't copy** — and it's not a style preference, it's what
keeps the knowledge from rotting.

<Note>
  A pasted 40-page PRD goes stale the day someone edits the real Doc, and it blows an
  agent's context window when read raw. So raw sources stay **canonical** in Drive /
  Figma / GitHub and are *linked*; the repo holds the **distilled digest**, not the dump.
</Note>

Two mechanisms make rich context cheap:

<Steps>
  <Step title="Progressive disclosure">
    A digest's one-line description is always in context; its body loads only when a
    task touches that area. A large knowledge base costs almost nothing until it's
    relevant.
  </Step>

  <Step title="Digger agents">
    A retrieval agent (like `prd-retriever` or `figma-frame-reader`) reads the heavy
    source in its own throwaway context and hands back a tight brief — so the main
    conversation never loads the 40-page doc.
  </Step>
</Steps>

And it compounds. When a dig surfaces something durable, the agent **writes it back**
into the digest — so the next agent loads it cheaply instead of re-reading the source.
This is the flywheel: the knowledge base converges on "what a builder routinely needs."

## How to act on it

<AccordionGroup>
  <Accordion title="Add a source" icon="plus">
    Add an entry to `lib/system/knowledge/sources.ts` (or, in existing-app mode, let
    the `knowledge-harvester` digger propose entries from the host repo). It appears
    on `/synclair/knowledge` immediately — a link, not a copy.
  </Accordion>

  <Accordion title="Distill a source into agent-ready knowledge" icon="filter">
    Use the `product-spec` skill (for docs/PRDs) or `figma-distiller` (for Figma) to
    pull the durable essentials into a digest. Dig into the raw source with a digger
    only when the digest is insufficient — then write the durable part back.
  </Accordion>

  <Accordion title="Generate a summary" icon="newspaper">
    Queue a summary from the Summary tab (or run the `product-summary` skill) — a
    brief, a diagram, or a custom cut for a specific audience. The button queues it;
    an agent drains the queue and writes it to `data/knowledge/summaries/`.
  </Accordion>

  <Accordion title="Onboard someone (or an agent)" icon="user-plus">
    Point them at `/synclair/knowledge` — the Summary tab's brief is the fastest way
    in, and the source links are there when they need the canonical detail.
  </Accordion>
</AccordionGroup>

<Card title="Related: References" icon="bookmark" href="/references">
  Knowledge is the *inputs* (specs, designs). References is the project's *findings* —
  prior art and recommendations agents accumulate as they research.
</Card>