Agent skill
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'.
Install this agent skill to your Project
npx add-skill https://github.com/alfredolopez80/multi-agent-ralph-loop/tree/main/.claude/skills/vault
SKILL.md
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:
$HOME/Documents/Obsidian/MiVault/(configurable) - Backup: private git repo (user creates their own)
- Viewer: Obsidian (optional, vault works as plain markdown + git)
This skill teaches HOW to use the vault (framework). It does NOT contain vault data.
Actions
/vault init
Create vault structure:
VAULT_DIR="${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:
- Search in:
global/wiki/+projects/{current-project}/ - NEVER search in:
projects/{other-project}/(isolation) - Return: matching articles with relevance score
/vault index
Update all _index.md files in the vault:
- Scan all
.mdfiles inglobal/wiki/andprojects/*/wiki/ - Regenerate
_vault-index.mdandprojects/_project-index.md - Update backlinks between articles
/vault compile
Compile raw notes into wiki articles (Karpathy pipeline):
- Read
raw/andlessons/directories - LLM compiles new articles in
wiki/ - Update backlinks between articles
- Update
_index.md - 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:
- Remove from
.claude/rules/learned/{category}.md - 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
- A project ONLY reads:
global/wiki/+projects/{its-own-name}/ - NEVER reads
projects/{other-project}/directly - GREEN learnings from any project can be promoted to
global/wiki/ - 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. |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
browser-test
Browser testing using Chrome DevTools MCP and Playwright for visual verification. Start dev server, navigate, screenshot, Lighthouse audit, console errors, network check. Use when: (1) verifying frontend changes, (2) accessibility auditing, (3) performance testing, (4) visual regression. Triggers: /browser-test, 'test in browser', 'visual test', 'lighthouse audit'.
crafting-effective-readmes
Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.
stop-slop
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'.
bugs
Bug hunting with Codex CLI Use when: (1) /bugs is invoked, (2) task relates to bugs functionality.
adversarial
Multi-Agent Adversarial Analysis System for code security
senior-software-engineer
Global skill enforcing senior software engineering best practices
Didn't find tool you were looking for?