vault

Living knowledge base management. Actions: search (query vault), save (store learning), index (update indices), compile (raw->wiki->rules graduation), init (create vault structure). Follows Karpathy pipeline: ingest->compile->query. Use when: (1) searching accumulated knowledge, (2) saving learnings, (3) compiling raw notes into wiki, (4) initializing a new vault. Triggers: /vault, 'vault search', 'knowledge base', 'save learning'.

108 stars

Best use case

vault is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Living knowledge base management. Actions: search (query vault), save (store learning), index (update indices), compile (raw->wiki->rules graduation), init (create vault structure). Follows Karpathy pipeline: ingest->compile->query. Use when: (1) searching accumulated knowledge, (2) saving learnings, (3) compiling raw notes into wiki, (4) initializing a new vault. Triggers: /vault, 'vault search', 'knowledge base', 'save learning'.

Teams using vault should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/vault/SKILL.md --create-dirs "https://raw.githubusercontent.com/alfredolopez80/multi-agent-ralph-loop/main/.claude/skills/vault/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/vault/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How vault Compares

Feature / AgentvaultStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Living knowledge base management. Actions: search (query vault), save (store learning), index (update indices), compile (raw->wiki->rules graduation), init (create vault structure). Follows Karpathy pipeline: ingest->compile->query. Use when: (1) searching accumulated knowledge, (2) saving learnings, (3) compiling raw notes into wiki, (4) initializing a new vault. Triggers: /vault, 'vault search', 'knowledge base', 'save learning'.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Vault — Living Knowledge Base v3.0

Karpathy-inspired knowledge pipeline: Ingest -> Compile -> Query.

## Architecture

The vault is a PRIVATE directory OUTSIDE the public repo:
- Location: `$HOME/Documents/Obsidian/MiVault/` (configurable)
- Backup: private git repo (user creates their own)
- Viewer: Obsidian (optional, vault works as plain markdown + git)

**This skill teaches HOW to use the vault (framework). It does NOT contain vault data.**

## Actions

### `/vault init`

Create vault structure:

```bash
VAULT_DIR="${VAULT_DIR:-$HOME/Documents/Obsidian/MiVault}"

# 3-layer structure
mkdir -p "$VAULT_DIR"/{global/{raw/articles,raw/papers,raw/images,wiki,output,decisions},projects,_templates}

# Create vault index
echo "# Vault Index" > "$VAULT_DIR/_vault-index.md"
echo "# Project Index" > "$VAULT_DIR/projects/_project-index.md"
```

Or run: `scripts/setup-obsidian-vault.sh`

### `/vault save <classification> <content>`

Save a learning to the vault:

| Classification | Destination | Example |
|---|---|---|
| GREEN | `$VAULT_DIR/global/wiki/{category}/` | Generic patterns (TypeScript, React) |
| YELLOW | `$VAULT_DIR/projects/{project}/wiki/` | Project-specific knowledge |
| RED | DISCARDED (never saved) | Contains secrets or sensitive info |

### `/vault search <query>`

Search vault for relevant knowledge:

1. Search in: `global/wiki/` + `projects/{current-project}/`
2. NEVER search in: `projects/{other-project}/` (isolation)
3. Return: matching articles with relevance score

### `/vault index`

Update all `_index.md` files in the vault:

1. Scan all `.md` files in `global/wiki/` and `projects/*/wiki/`
2. Regenerate `_vault-index.md` and `projects/_project-index.md`
3. Update backlinks between articles

### `/vault compile`

Compile raw notes into wiki articles (Karpathy pipeline):

1. Read `raw/` and `lessons/` directories
2. LLM compiles new articles in `wiki/`
3. Update backlinks between articles
4. Update `_index.md`
5. **Knowledge Graduation**: promote high-confidence learnings to `.claude/rules/learned/`

Graduation criteria:
- Confidence >= 0.7
- Confirmed in >= 3 sessions
- Format: rule text + source + confidence + last confirmed date

### `/vault demote <rule>`

Revert a graduated rule back to vault if incorrect:

1. Remove from `.claude/rules/learned/{category}.md`
2. Mark source article with `status: demoted`

## Integration Points

| Component | Integration |
|---|---|
| `session-accumulator.sh` | PostToolUse hook captures learnings during session |
| `vault-graduation.sh` | SessionStart hook promotes high-confidence learnings to rules |
| `/exit-review` | End-of-session GREEN/YELLOW/RED classification |
| `smart-memory-search.sh` | Adds vault as 5th search source (parallel) |
| `pre-compact-handoff.sh` | Saves vault context before compaction |

## Project Isolation

1. A project ONLY reads: `global/wiki/` + `projects/{its-own-name}/`
2. NEVER reads `projects/{other-project}/` directly
3. GREEN learnings from any project can be promoted to `global/wiki/`
4. SHA-256 deduplication prevents duplicate entries

## Anti-Rationalization

| Excuse | Rebuttal |
|---|---|
| "The vault is just another notes system" | The vault graduates to rules. Notes don't change behavior. |
| "I'll save it to memory instead" | Memory is ephemeral (25KB). Vault is curated knowledge. |
| "Classification is overhead" | 3 seconds to classify saves hours of future searching. |
| "RED content is useful for context" | RED = secrets. Never store. Period. |

Related Skills

worktree-pr

108
from alfredolopez80/multi-agent-ralph-loop

Manage git worktrees with PR workflow and multi-agent review (Claude + Codex). Use when developing features in isolation with easy rollback.

vercel-react-best-practices

108
from alfredolopez80/multi-agent-ralph-loop

React and Next.js performance optimization guidelines from Vercel Engineering. Use when writing, reviewing, or refactoring React/Next.js code. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

testing-anti-patterns

108
from alfredolopez80/multi-agent-ralph-loop

Custom skill for testing-anti-patterns

task-visualizer

108
from alfredolopez80/multi-agent-ralph-loop

Visualize task dependencies and progress (Gastown-style)

task-classifier

108
from alfredolopez80/multi-agent-ralph-loop

Classifies task complexity (1-10) for model and agent routing

task-batch

108
from alfredolopez80/multi-agent-ralph-loop

Autonomous batch task execution with PRD parsing, task decomposition, and continuous execution until all tasks complete. Uses /orchestrator internally. Stops only for major failures (no internet, token limit, system crash). Use when: (1) processing task lists autonomously, (2) PRD-driven development, (3) batch feature implementation. Triggers: /task-batch, 'batch tasks', 'process PRD', 'run task queue'.

tap-explorer

108
from alfredolopez80/multi-agent-ralph-loop

Tree of Attacks with Pruning for systematic code analysis

stop-slop

108
from alfredolopez80/multi-agent-ralph-loop

A skill for removing AI-generated writing patterns ('slop') from prose. Eliminates telltale signs of AI writing like filler phrases, excessive hedging, overly formal language, and mechanical sentence structures. Use when: writing content that should sound human and natural, editing AI-generated drafts, cleaning up prose for publication, or any content that needs to sound authentic rather than AI-generated. Triggers: 'stop-slop', 'remove AI tells', 'clean up prose', 'make it sound human', 'edit AI writing'.

spec

108
from alfredolopez80/multi-agent-ralph-loop

Produce a verifiable technical specification before coding. 6 mandatory sections: Interfaces, Behaviors, Invariants (from Aristotle Phase 2), File Plan, Test Plan, Exit Criteria (executable bash commands + expected results). Use when: (1) before implementing features with complexity > 4, (2) as Step 1.5 in orchestrator workflow, (3) when requirements need formalization. Triggers: /spec, 'create spec', 'write specification', 'technical spec'.

smart-fork

108
from alfredolopez80/multi-agent-ralph-loop

Smart Forking - Find and fork from relevant historical sessions using parallel memory search across vault, memvid, handoffs, and ledgers

ship

108
from alfredolopez80/multi-agent-ralph-loop

Pre-launch shipping checklist orchestrating /gates, /security, /browser-test, /perf. Ensures nothing ships without passing all quality checks. Use when: (1) before deploying, (2) before merging to main, (3) before release. Triggers: /ship, 'ship it', 'ready to deploy', 'pre-launch check'.

senior-software-engineer

108
from alfredolopez80/multi-agent-ralph-loop

Global skill enforcing senior software engineering best practices