agentleFS
sergi-rzsergi-rz/claudia-os/.claude/skills/vault-search/SKILL.md

vault-search

Skill39 starsChanged 7 months agoMITView on GitHub

Busca en el vault de conocimiento (wisdom, research) usando SQLite FTS5 + metadatos estructurados. Queries por texto, autor, topic, quality, stance, etc.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Vault Search — Índice SQLite del vault de conocimiento

Indexa user/vault/ (wisdom, research, weekly-reviews) con SQLite FTS5 para búsqueda full-text y tablas relacionales para queries estructuradas por metadatos del frontmatter.

Uso como librería (desde otras skills)

# Buscar contexto previo antes de crear wisdom/research
python3 .claude/skills/vault-search/vault_search.py --context "tema" --max-tokens 1500

# Reindexar un fichero recién creado
python3 .claude/skills/vault-search/vault_search.py --reindex-file "wisdom/2026-05-01_slug.md"

# Regenerar INDEX.md automáticamente
python3 .claude/skills/vault-search/vault_search.py --generate-index

Uso CLI directo

# Full-text search
python3 vault_search.py "agentes autónomos memoria"

# Filtros estructurados
python3 vault_search.py --author "Miessler"
python3 vault_search.py --topic agentes-ia --quality alta
python3 vault_search.py --type video --depth deep
python3 vault_search.py --stance esceptico --topic scaling
python3 vault_search.py --since 2026-04-01

# Stats y listados
python3 vault_search.py --stats
python3 vault_search.py --list-topics
python3 vault_search.py --list-authors

# Gestión del índice
python3 vault_search.py --rebuild
python3 vault_search.py --status

Arquitectura

  • Source of truth: ficheros .md con frontmatter YAML en user/vault/
  • Índice derivado: user/vault/.index/vault.db (SQLite, gitignored, regenerable)
  • Auto-rebuild: detecta cambios por mtime, reconstruye transparentemente
  • Fallback: grep si FTS5 no disponible

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.