Skip to content

GEMINI.md

Latest commit

 

History

History
176 lines (132 loc) · 3.72 KB

GEMINI.md

File metadata and controls

176 lines (132 loc) · 3.72 KB

LLM Wiki Agent — Schema & Workflow Instructions

This wiki is maintained entirely by Gemini CLI. No API key or Python scripts needed — just open this repo with gemini and talk to it.

How to Use

Describe what you want in plain English:

  • "Ingest this file: raw/papers/my-paper.md"
  • "What does the wiki say about transformer models?"
  • "Check the wiki for orphan pages and contradictions"
  • "Build the knowledge graph"

Or use shorthand triggers:

  • ingest <file> → runs the Ingest Workflow
  • query: <question> → runs the Query Workflow
  • lint → runs the Lint Workflow
  • build graph → runs the Graph Workflow

Directory Layout

raw/          # Immutable source documents — never modify these
wiki/         # Agent owns this layer entirely
  index.md    # Catalog of all pages — update on every ingest
  log.md      # Append-only chronological record
  overview.md # Living synthesis across all sources
  sources/    # One summary page per source document
  entities/   # People, companies, projects, products
  concepts/   # Ideas, frameworks, methods, theories
  syntheses/  # Saved query answers
graph/        # Auto-generated graph data
tools/        # Optional standalone Python scripts

Page Format

Every wiki page uses this frontmatter:

---
title: "Page Title"
type: source | entity | concept | synthesis
tags: []
sources: []
last_updated: YYYY-MM-DD
---

Use [[PageName]] wikilinks to link to other wiki pages.

Ingest Workflow

Triggered by: "ingest "

  1. Read the source document fully
  2. Read wiki/index.md and wiki/overview.md for current wiki context
  3. Write wiki/sources/<slug>.md (source page format below)
  4. Update wiki/index.md — add entry under Sources
  5. Update wiki/overview.md — revise synthesis if warranted
  6. Update/create entity and concept pages
  7. Flag contradictions with existing wiki content
  8. Append to wiki/log.md: ## [YYYY-MM-DD] ingest | <Title>
  9. Post-ingest validation — check for broken [[wikilinks]], verify all new pages are in index.md, print a change summary

Source Page Format

---
title: "Source Title"
type: source
tags: []
date: YYYY-MM-DD
source_file: raw/...
---

## Summary
2–4 sentence summary.

## Key Claims
- Claim 1

## Key Quotes
> "Quote here"

## Connections
- [[EntityName]] — how they relate

## Contradictions
- Contradicts [[OtherPage]] on: ...

Domain-Specific Templates

If the source falls into a specific domain (e.g., personal diary, meeting notes), the agent should use a specialized template instead of the default generic one above:

Diary / Journal Template

---
title: "YYYY-MM-DD Diary"
type: source
tags: [diary]
date: YYYY-MM-DD
---
## Event Summary
...
## Key Decisions
...
## Energy & Mood
...
## Connections
...
## Shifts & Contradictions
...

Meeting Notes Template

---
title: "Meeting Title"
type: source
tags: [meeting]
date: YYYY-MM-DD
---
## Goal
...
## Key Discussions
...
## Decisions Made
...
## Action Items
...

Query Workflow

Triggered by: "query: "

  1. Read wiki/index.md — identify relevant pages
  2. Read those pages
  3. Synthesize answer with [[PageName]] citations
  4. Offer to save as wiki/syntheses/<slug>.md

Lint Workflow

Triggered by: "lint"

Check for: orphan pages, broken links, contradictions, stale content, missing entity pages, data gaps.

Graph Workflow

Triggered by: "build graph"

Try python tools/build_graph.py --open first. If unavailable, build graph.json and graph.html manually from wikilinks.

Naming Conventions

  • Source slugs: kebab-case
  • Entity/Concept pages: TitleCase.md

Log Format

## [YYYY-MM-DD] <operation> | <title>