Personal Knowledge Wiki

Based on the wiki skill from hermes-agent by Nous Research. Modified and extended.

Quick Start

/wiki init              # Set up project (clone repo, install deps)
/wiki ingest            # Interactive: choose data source, import entries
/wiki absorb all        # Compile entries into wiki articles
/wiki query <q>         # Ask questions about the wiki
/wiki serve             # Launch Wikipedia-style web UI

Command:

/wiki init

1. Check if the current directory is empty (or nearly empty). If not, warn the user before proceeding.
2. Clone the project repository:
   bash

   git clone https://github.com/cylqwe7855-alt/personal-wiki.git .

3. Install Python dependencies:
   bash

   python3 -m venv .venv && source .venv/bin/activate
   pip install -r requirements.txt

4. Install Node.js dependencies for the web UI:
   bash

   cd ui && npm install && cd ..

5. Create the initial wiki structure:
   bash

   mkdir -p raw wiki

6. Create

   wiki/index.md

   with just the header:
   markdown

   # Wiki Index

7. Create

   wiki/log.md

   with a bootstrap entry:

   | Date | Action | Details |
   |------|--------|---------|
   | {today's date} | init | Project initialized. |

8. Tell the user: "Project ready. Run

   /wiki ingest

   to import your data."

Command:

/wiki ingest

1. Ask the user: "What data source do you want to import?" and present options:
   • Obsidian vault — a folder of .md files
   • Apple Notes — macOS Notes app (requires macOS)
   • Documents — .docx and .pdf files from a folder
   • Other — any text files, CSV, JSON, Day One, etc.
2. Based on their choice:
   Obsidian:
   • Ask for the vault path (e.g.,

     ~/Documents/MyVault/

     )
   • Run:

     python scripts/ingest_obsidian.py <path>

   • Update

     CLAUDE.md

     sources config with the path
   Apple Notes:
   • Confirm they are on macOS
   • Run:

     python scripts/ingest_apple_notes.py

   • Update

     CLAUDE.md

     sources config
   Documents:
   • Ask for the folder path
   • Run:

     python scripts/ingest_documents.py <path>

   • Update

     CLAUDE.md

     sources config with the path
   Other:
   • Ask the user to describe the data format and location
   • Write a custom

     scripts/ingest_<source>.py

     script following the standard output format
   • Run the script
3. After ingestion completes, report: "{N} entries created in raw/{source}/. Run

   /wiki absorb all

   to compile them into wiki articles."

Output Format (for custom ingest scripts)

{date}_{id}.md

---
id: <unique identifier>
date: YYYY-MM-DD
source_type: <obsidian|apple-notes|documents|custom>
tags: []
---

<entry text content>

Command:

/wiki serve

1. Check if

   ui/node_modules/

   exists. If not, run

   cd ui && npm install

   .
2. Start the dev server:
   bash

   cd ui && npm run dev

3. Tell the user: "Wiki is live at http://localhost:3000"

Command:

/wiki absorb [date-range]

last 30 days

2026-03

2026-03-22

2024

all

raw/

/wiki ingest

The Absorption Loop

wiki/index.md

1. Read the entry. Text, frontmatter, metadata. View any attached photos. Actually look at them and understand what they show.
2. Understand what it means. Not "what facts does this contain" but "what does this tell me?" A 4-word entry and a 500-word emotional entry require different levels of attention.
3. Match against the index. What existing articles does this entry touch? What doesn't match anything and suggests a new article?
4. Update and create articles. Re-read every article before updating. Ask: what new dimension does this entry add? Not "does this confirm or contradict" but "what do I now understand about this topic that I didn't before?"
   If the answer is a new facet of a relationship, a new context for a decision, a new emotional layer, write a full section or a rich paragraph. Not a sentence. Every page you touch should get meaningfully better. Never just append to the bottom. Integrate so the article reads as a coherent whole.
5. Connect to patterns. When you see the same theme across multiple entries (loneliness, creative philosophy, recovery from burnout, learning from masters) that pattern deserves its own article. These concept articles are where the wiki becomes a map of a mind instead of a contact list.

What Becomes an Article

Anti-Cramming

Anti-Thinning

Every 15 Entries: Checkpoint

1. Rebuild

   wiki/index.md

   with all articles and

   also:

   aliases
2. New article audit: How many new articles in the last 15? If zero, you're cramming.
3. Quality audit: Pick your 3 most-updated articles. Re-read each as a whole piece. Ask:
   • Does it tell a coherent story, or is it a chronological dump?
   • Does it have sections organized by theme, not date?
   • Does it use direct quotes to carry emotional weight?
   • Does it connect to other articles in revealing ways?
   • Would a reader learn something non-obvious? If any article reads like an event log, rewrite it.
4. Check if any articles exceed 150 lines and should be split.
5. Check directory structure. Create new directories when needed.
6. Log the checkpoint to

   wiki/log.md

   .

Command:

/wiki query <question>

How to Answer

1. Read

   wiki/index.md

   . Scan for articles relevant to the query. Each entry has an

   also:

   field with aliases.
2. Read 3-8 relevant articles. Follow

   [[wikilinks]]

   and

   related:

   entries 2-3 links deep when relevant.
3. Synthesize. Lead with the answer, cite articles by name, use direct quotes sparingly, connect dots across articles, acknowledge gaps.

Query Patterns

people/

decisions/

transitions/

patterns/

philosophies/

tensions/

life/

eras/

places/

projects/

Rules

• Never read raw diary entries (

  raw/

  ). The wiki is the knowledge base.
• Don't guess. If the wiki doesn't cover it, say so.
• Don't read the entire wiki. Be surgical.
• Don't modify any wiki files. Query is read-only.

Command:

/wiki cleanup

Phase 1: Build Context

wiki/index.md

Phase 2: Per-Article Subagents

• Structure: theme-driven or diary-driven (individual events as section headings)?
• Line count: bloated (>120 lines) or stub (<15 lines)?
• Tone: flat/factual/encyclopedic or AI editorial voice?
• Quote density: more than 2 direct quotes? More than a third quotes?
• Narrative coherence: unified story or list of random events?
• Wikilinks: broken links? Missing links to existing articles?

## The March Meeting
## The April Pivot
## The June Launch

## Origins
## The Pivot to Institutional Sales
## Becoming the Product

Phase 3: Integration

wiki/index.md

Command:

/wiki breakdown

Phase 1: Survey

wiki/index.md

Phase 2: Mining

• Named people, places, companies, organizations, institutions
• Named events or turning points with dates
• Books, films, music, games referenced
• Tools, platforms used significantly
• Projects with names

Phase 3: Planning

Phase 4: Creation

Command:

/wiki rebuild-index

wiki/index.md

also:

Command:

/wiki status

What This Wiki IS

Directory Taxonomy

people/

projects/

places/

events/

companies/

institutions/

books/

tools/

platforms/

philosophies/

patterns/

tensions/

life/

eras/

transitions/

decisions/

experiments/

relationships/

ideas/

artifacts/

Writing Standards

The Golden Rule

Tone: Wikipedia, Not AI

• Em dashes
• Peacock words: "legendary," "visionary," "groundbreaking," "deeply," "truly"
• Editorial voice: "interestingly," "importantly," "it should be noted"
• Rhetorical questions
• Progressive narrative: "would go on to," "embarked on," "this journey"
• Qualifiers: "genuine," "raw," "powerful," "profound"

• Lead with the subject, state facts plainly
• One claim per sentence. Short sentences.
• Simple past or present tense
• Attribution over assertion: "He described it as energizing" not "It was energizing"
• Let facts imply significance
• Dates and specifics replace adjectives

Article Format

---
title: Article Title
type: person | project | place | era | decision | ...
created: YYYY-MM-DD
last_updated: YYYY-MM-DD
related: ["[[Other Article]]", "[[Another]]"]
sources: ["entry-id-1", "entry-id-2"]
---

# Article Title

{Content organized by theme, not chronology}

## Sections as needed

Linking

[[wikilinks]]

Quote Discipline

Length Targets

Principles

1. You are a writer. Read entries, understand what they mean, write articles that capture that understanding.
2. Every entry ends up somewhere. Woven into the fabric of understanding, not mechanically filed.
3. Articles are knowledge, not diary entries. Synthesize, don't summarize.
4. Concept articles are essential. Patterns, themes, arcs. These are where the wiki becomes a map of a mind.
5. Revise your work. Re-read articles. Rewrite the ones that read like event logs.
6. Breadth and depth. Create pages aggressively, but every page must gain real substance.
7. The structure is alive. Merge, split, rename, restructure freely.
8. Connect, don't just record. Find the web of meaning between entities.
9. Cite sources. Every claim traces back to a raw entry ID.

Concurrency Rules

• Never delete or overwrite a file without reading it first.
• Re-read any article immediately before editing it.
• Rebuild

  wiki/index.md

  only at the very end of a command.
• One writer per article when using parallel subagents.