.build/claude/skills/knowledge-architecture/SKILL.md
Design knowledge systems using ontological principles—organizing by what things ARE rather than arbitrary hierarchies. Use when structuring personal knowledge bases, designing documentation systems, creating cross-domain linking patterns, building the {OS.me} ecosystem, or architecting information that reveals rather than obscures essential nature. Triggers on knowledge management, documentation architecture, information ontology, or systematic organization of complex domains.
npx skillsauth add organvm-iv-taxis/a-i--skills knowledge-architectureInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Organize knowledge by being, not bureaucracy.
Most knowledge systems fail because they organize by:
Result: Knowledge fragments. Connections hide. Understanding atrophies.
Organize by asking: What is this thing, essentially?
Not "where should this file go?" but "what is the nature of this entity, and what does it relate to by that nature?"
Things that exist in themselves, not as properties of other things.
| Category | Examples | Identifying Question | |----------|----------|---------------------| | Persons | You, collaborators, mentors | Who acts? | | Projects | in-midst-my-life, AI Council | What is being built? | | Tools | Claude, Figma, modular synth | What enables action? | | Works | Essays, code, art pieces | What has been created? | | Concepts | Ideas, theories, frameworks | What is understood? |
Exist only as aspects of substances.
| Category | Examples | Identifying Question | |----------|----------|---------------------| | States | In-progress, complete, abandoned | What phase? | | Qualities | Elegant, experimental, stable | What character? | | Relations | Depends-on, extends, contradicts | How connected? | | Measures | Size, duration, complexity | What quantity? |
Things that happen, with beginning and end.
| Category | Examples | Identifying Question | |----------|----------|---------------------| | Actions | Decisions, commits, publications | What was done? | | Processes | Learning, building, evolving | What unfolds? | | Occasions | Meetings, deadlines, milestones | What marks time? |
Essential: What makes the thing that thing. Remove it, and it's something else. Accidental: Could be otherwise without changing identity.
Example: A "portfolio website"
Organizing principle: Group by essential properties. Tag/filter by accidental.
Classical definition structure: "A is a B that C"
Project
├── Software Project (produces code)
│ ├── Library (produces reusable code)
│ ├── Application (produces usable program)
│ └── Infrastructure (produces enabling system)
├── Creative Project (produces art/writing)
│ ├── Visual Work (produces images)
│ ├── Written Work (produces text)
│ └── Interactive Work (produces experience)
└── Research Project (produces knowledge)
├── Academic (produces citable work)
└── Applied (produces practical insight)
Don't bury relations in properties. Make them navigable.
| Relation Type | Meaning | Inverse | |---------------|---------|---------| | depends-on | Cannot exist without | enables | | extends | Builds upon foundation | is-extended-by | | contradicts | In tension with | is-contradicted-by | | implements | Realizes abstraction | is-implemented-by | | exemplifies | Is instance of pattern | is-exemplified-by | | supersedes | Replaces previous | is-superseded-by |
Each note captures ONE thing:
Connections emerge from linking atoms, not from cramming compounds into single containers.
Create navigational hubs, not hierarchical folders.
# Project Index
## By Nature
- [[Software Projects]]
- [[Creative Projects]]
- [[Research Projects]]
## By State
- [[Active Work]]
- [[Completed Work]]
- [[Archived Work]]
## By Relation
- [[Dependencies Map]]
- [[Influence Graph]]
Same entity, different contexts:
/entities/project-alpha.md # The thing itself
/contexts/technical/project-alpha.md # Technical view
/contexts/business/project-alpha.md # Business view
/contexts/personal/project-alpha.md # Personal meaning
Knowledge changes. Track it:
/current/concept-x.md # Current understanding
/history/concept-x/ # Evolution
├── 2024-01-understanding.md
├── 2024-06-revision.md
└── changelog.md
[type]-[identifier]
project-in-midst-my-life
concept-modular-synthesis
person-mentor-name
tool-claude-desktop
[source]--[relation]--[target]
project-alpha--depends-on--library-beta
concept-x--contradicts--concept-y
[entity].[state-type]
project-alpha.status = active
project-alpha.phase = development
project-alpha.health = stable
Same concept, different domain vocabularies:
concept: feedback-loop
domains:
synthesis: "output patches to input, creating evolving timbre"
systems: "output affects input, creating dynamic behavior"
learning: "results inform practice, creating improvement"
biology: "effect influences cause, creating homeostasis"
Find structural similarities across domains:
Modular Synthesis ←→ Software Architecture
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Oscillator ←→ Data Source
Filter ←→ Transformer
Patch Cable ←→ API Connection
Mixer ←→ Aggregator
CV ←→ Configuration
Audio Signal ←→ Data Payload
Document what emerges from combination:
Component A + Component B = Emergent Property C
# Example
Note-taking + Linking + Time = Evolving understanding
(None of the parts alone produces this)
knowledge/
├── entities/ # Primary substances
│ ├── projects/
│ ├── concepts/
│ ├── works/
│ └── tools/
├── relations/ # Connection maps
│ ├── dependencies.md
│ ├── influences.md
│ └── contradictions.md
├── contexts/ # Perspective layers
│ ├── technical/
│ ├── personal/
│ └── temporal/
├── indices/ # Navigation hubs
│ ├── by-nature.md
│ ├── by-state.md
│ └── by-domain.md
└── meta/ # About the system itself
├── ontology.md
├── conventions.md
└── changelog.md
---
type: [entity-type]
nature: [essential description]
state: [current state]
created: [date]
modified: [date]
relations:
depends-on: [list]
extends: [list]
relates-to: [list]
contexts: [list of applicable contexts]
tags: [accidental properties for filtering]
---
references/ontological-terms.md - Philosophical vocabularyreferences/implementation-patterns.md - Concrete file/linking patternsdevelopment
Dry-run audit + targeted cleanup for shell command history. Currently wraps atuin (stats today, prune, dedup with dated preview artifacts); extensible to zsh/bash/mcfly backends. Always previews before applying — apply commands are echoed for the human to run, never auto-executed. Triggers on "/shell-history-hygiene", "audit atuin", "audit shell history", "clean shell history", "atuin prune", "atuin dedup", "shell history hygiene", "history cleanup". Replaces ad-hoc one-liners (e.g. `... | tee cmd > file.txt` which wrote two files, swallowed dedup output, and left a junk `cmd` file).
tools
Guided Cowork setup — install role-matched plugins, connect your tools, try a skill.
development
Manage AI agent session lifecycles with structured phases (FRAME, SHAPE, BUILD, PROVE), context preservation across sessions, handoff protocols, and session metadata tracking. Triggers on session management, agent lifecycle, or multi-session workflow requests.
tools
Parse a session transcript into a structured Session Governance Index — an annotated bibliography of every file modified and commit made, internal-energy accounting (tool uses, estimated tokens), shipped-vs-tasked atom tally, and classification of missing items as Gaps or Vacuums. Triggers on "visibility-schema-substrate-sweep", "session cascade audit", "session governance audit", or any request to summarize what a session actually produced versus what it was asked to produce.