Globales Ranking · von 601 Skills
turso AI Agent Skill
Quellcode ansehen: oakoss/agent-skills
SafeInstallation
npx skills add oakoss/agent-skills --skill turso 34
Installationen
Turso
Overview
Turso is an edge-hosted SQLite platform built on libSQL, an open-source fork of SQLite. It provides globally distributed databases with embedded replicas for local-first reads, a platform API for programmatic database management, and native vector search. Use Turso for edge-deployed applications needing low-latency reads, per-tenant database isolation, or offline-capable embedded replicas. Avoid when you need a traditional relational database with complex joins across tenants or require PostgreSQL-specific features.
Quick Reference
| Pattern | API / Command | Key Points |
|---|---|---|
| Remote client | createClient({ url, authToken }) |
Connect to Turso cloud database |
| Local file client | createClient({ url: 'file:local.db' }) |
Pure local SQLite via libSQL |
| Embedded replica | createClient({ url, syncUrl, authToken }) |
Local reads, remote sync |
| Manual sync | client.sync() |
Pull latest changes from remote |
| Periodic sync | syncInterval: 60 in client config |
Auto-sync interval in seconds |
| Execute query | client.execute({ sql, args }) |
Positional ? or named $param args |
| Batch operations | client.batch([...statements], mode) |
Atomic multi-statement execution |
| Interactive transaction | client.transaction('write') |
Multi-step logic with commit/rollback |
| Encryption at rest | encryptionKey in client config |
Encrypts local database file |
| Vector insert | vector32('[0.1, 0.2, ...]') |
Store embeddings as F32_BLOB columns |
| Vector search | vector_distance_cos(col, vector32(...)) |
Cosine similarity, ORDER BY distance ASC |
| Vector index | libsql_vector_idx(col, 'type=diskann') |
DiskANN index for efficient nearest-neighbor |
| Create database (CLI) | turso db create <name> |
Provision new database |
| Create database (API) | POST /v1/organizations/{org}/databases |
Programmatic provisioning for multi-tenant |
| Generate token (CLI) | turso db tokens create <name> |
Auth tokens with optional read-only and expiration |
| Drizzle integration | drizzle(createClient({ url, authToken })) |
Use drizzle-orm/libsql driver |
| In-memory database | createClient({ url: ':memory:' }) |
Ephemeral database for testing |
Common Mistakes
| Mistake | Correct Pattern |
|---|---|
Using syncUrl without authToken |
Embedded replicas require both syncUrl and authToken |
Forgetting client.sync() before reads |
Call sync() or set syncInterval to keep replica current |
Using vector_distance_cos without a vector index |
Create a libsql_vector_idx index for efficient similarity search |
| Hardcoding auth tokens in source code | Use environment variables for TURSO_DATABASE_URL and TURSO_AUTH_TOKEN |
| Using interactive transactions for simple batches | Use client.batch() for atomic multi-statement operations |
| Not closing transactions on error | Always call transaction.close() in a finally block |
| Creating one database for all tenants | Use multi-database per-tenant isolation for SaaS workloads |
| Passing raw arrays as vector values | Wrap vectors with vector32() SQL function or pass as Float32Array |
Using ORDER BY distance DESC for nearest neighbor |
Cosine distance: smaller is closer, use ORDER BY distance ASC |
Delegation
If the
drizzle-ormskill is available, delegate ORM schema definition, query building, relations, and migration patterns to it.
Otherwise, recommend:pnpm dlx skills add oakoss/agent-skills -s drizzle-orm -a claude-code -yIf the
local-firstskill is available, delegate architecture decisions, sync engine comparisons, and conflict resolution strategies to it.
Otherwise, recommend:pnpm dlx skills add oakoss/agent-skills -s local-first -a claude-code -yIf the
pgliteskill is available, delegate PGlite-specific patterns for comparison with Turso embedded replicas.
- Database provisioning: Use
Taskagent for multi-tenant setup automation - Vector search tuning: Use
Exploreagent to research embedding models and dimensions - Code review: Delegate to
code-revieweragent
References
- Client SDK setup, connection modes, and configuration
- Embedded replicas, sync strategies, and offline mode
- Batch operations and interactive transactions
- Vector search, embeddings, and similarity queries
- Multi-database per-tenant architecture and platform API
- CLI commands and database management
- Drizzle ORM integration with libSQL driver
- Schema migrations and database operations
Installationen
Sicherheitsprüfung
Quellcode ansehen
oakoss/agent-skills
Mehr aus dieser Quelle
Power your AI Agents with
the best open-source models.
Drop-in OpenAI-compatible API. No data leaves Europe.
Explore Inference APIGLM
GLM 5
$1.00 / $3.20
per M tokens
Kimi
Kimi K2.5
$0.60 / $2.80
per M tokens
MiniMax
MiniMax M2.5
$0.30 / $1.20
per M tokens
Qwen
Qwen3.5 122B
$0.40 / $3.00
per M tokens
So verwenden Sie diesen Skill
Install turso by running npx skills add oakoss/agent-skills --skill turso in your project directory. Führen Sie den obigen Installationsbefehl in Ihrem Projektverzeichnis aus. Die Skill-Datei wird von GitHub heruntergeladen und in Ihrem Projekt platziert.
Keine Konfiguration erforderlich. Ihr KI-Agent (Claude Code, Cursor, Windsurf usw.) erkennt installierte Skills automatisch und nutzt sie als Kontext bei der Code-Generierung.
Der Skill verbessert das Verständnis Ihres Agenten für turso, und hilft ihm, etablierte Muster zu befolgen, häufige Fehler zu vermeiden und produktionsreifen Code zu erzeugen.
Was Sie erhalten
Skills sind Klartext-Anweisungsdateien — kein ausführbarer Code. Sie kodieren Expertenwissen über Frameworks, Sprachen oder Tools, das Ihr KI-Agent liest, um seine Ausgabe zu verbessern. Das bedeutet null Laufzeit-Overhead, keine Abhängigkeitskonflikte und volle Transparenz: Sie können jede Anweisung vor der Installation lesen und prüfen.
Kompatibilität
Dieser Skill funktioniert mit jedem KI-Coding-Agenten, der das skills.sh-Format unterstützt, einschließlich Claude Code (Anthropic), Cursor, Windsurf, Cline, Aider und anderen Tools, die projektbezogene Kontextdateien lesen. Skills sind auf Transportebene framework-agnostisch — der Inhalt bestimmt, für welche Sprache oder welches Framework er gilt.
Chat with 100+ AI Models in one App.
Use Claude, ChatGPT, Gemini alongside with EU-Hosted Models like Deepseek, GLM-5, Kimi K2.5 and many more.