Vai al contenuto
TakoAPI
Torna alle skill

kameleondb

di marcosnataqs

Marketing & Sales
1.4kDownload riportati da clawskills.sh
2Stelle
0Visualizzazioni
0 likeAccedi per mettere like a questa skill
—Non ancora valutato
La tua valutazione

Sintesi

Store and query structured data without planning schemas upfront.

Descrizione

Cosa fa questa skill

KameleonDB is a schema-flexible database for agents that stores and queries structured data without upfront schema design. The schema evolves automatically as new fields are discovered, and old records remain intact. Supports SQLite for local use and PostgreSQL for production.

Unlike traditional relational databases, it removes the need for migration planning, letting agents start storing data immediately and restructure as patterns emerge.

Quando usarla

  • Tracking contacts and companies across agent sessions
  • Building a knowledge base from web scraping or API ingestion
  • Managing tasks where requirements change over time
  • Storing API response data with unknown or variable structure
  • Creating a lightweight CRM to track leads, deals, or tickets

Esempio di workflow

INPUT

User asks: track the people I meet and add new details as I learn them

AGENT
  1. 1

    Run kameleondb --json schema create Contact --field 'name:string:required' --field 'email:string:unique' to create the entity

  2. 2

    Run kameleondb --json data insert Contact '{"name":"Alice","email":"alice@example.com"}' to add a record

  3. 3

    Run kameleondb --json schema alter Contact --add 'linkedin_url:string' --reason 'Found LinkedIn profiles for contacts' when a new field is needed

  4. 4

    Run kameleondb --json data update Contact <id> '{"linkedin_url":"https://linkedin.com/in/alice"}' to fill in the new field

  5. 5

    Run kameleondb --json schema list to review all tracked entities

OUTPUT

Contact records stored and queryable via SQL, with schema updated in place and no existing records broken

Requisiti

  • KAMELEONDB_URL environment variable

Installazione

clawhub install marcosnataqs/kameleondb

Esegui il comando CLI oppure incolla il prompt in Claude Code, Cursor, Codex o nell'agente di coding che usi.

Link