Awesome-omni-skill catalyzed

Help with Catalyzed API - datasets, tables, pipelines, queries, vector search. Use when building Catalyzed integrations.

install
source · Clone the upstream repo
git clone https://github.com/diegosouzapw/awesome-omni-skill
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/diegosouzapw/awesome-omni-skill "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data-ai/catalyzed" ~/.claude/skills/diegosouzapw-awesome-omni-skill-catalyzed && rm -rf "$T"
manifest: skills/data-ai/catalyzed/SKILL.md
source content

Catalyzed API Assistant

You are helping a developer integrate with the Catalyzed data platform.

Live Documentation (fetched at load time)

!

curl -sf https://docs.catalyzed.ai/llms.txt 2>/dev/null

Quick Reference (fallback if above is empty)

Base URL:

https://api.catalyzed.ai
Docs:
https://docs.catalyzed.ai
Auth:
Authorization: Bearer <API_TOKEN>

Core Endpoints

ResourceMethodEndpointDescription
TeamsGET/teamsList user's teams
TeamsGET/teams/:teamIdGet team by ID
DatasetsGET/datasetsList datasets
DatasetsPOST/datasetsCreate dataset
DatasetsGET/datasets/:datasetIdGet dataset by ID
DatasetsPUT/datasets/:datasetIdUpdate dataset
DatasetsDELETE/datasets/:datasetIdDelete dataset
TablesGET/dataset-tablesList tables
TablesPOST/dataset-tablesCreate table with schema
TablesGET/dataset-tables/:tableIdGet table by ID
TablesPUT/dataset-tables/:tableIdUpdate table metadata
TablesDELETE/dataset-tables/:tableIdDelete table
RowsPOST/dataset-tables/:tableId/rows?mode=appendInsert rows
RowsPOST/dataset-tables/:tableId/rows?mode=upsertUpsert rows
RowsPOST/dataset-tables/:tableId/rows?mode=deleteDelete rows by PK
QueriesPOST/dataset-tables/:tableId/queryExecute SQL query
SchemaGET/dataset-tables/:tableId/schemaGet table schema
PipelinesGET/pipelinesList pipelines
PipelinesPOST/pipelinesCreate pipeline
PipelinesGET/pipelines/:pipelineIdGet pipeline by ID
PipelinesPUT/pipelines/:pipelineIdUpdate pipeline
PipelinesPOST/pipelines/:pipelineId/triggerTrigger pipeline execution
ExecutionsGET/pipeline-executionsList executions
ExecutionsGET/pipeline-executions/:executionIdGet execution status
Knowledge BasesGET/knowledge-basesList knowledge bases
Knowledge BasesPOST/knowledge-basesCreate knowledge base
Knowledge BasesGET/knowledge-bases/:kbIdGet knowledge base
Knowledge BasesPOST/knowledge-bases/:kbId/sourcesAdd source (file or table)
Knowledge BasesPOST/knowledge-bases/:kbId/queryVector search query
FilesPOST/filesUpload file
FilesGET/files/:fileIdGet file metadata
API TokensGET/api-tokensList API tokens
API TokensPOST/api-tokensCreate API token

Authentication

All API requests require a Bearer token in the Authorization header:

curl -H "Authorization: Bearer cat_YOUR_API_TOKEN" \
  https://api.catalyzed.ai/teams

API tokens are created via the Catalyzed dashboard or API. Tokens have a

cat_
prefix.

Common Patterns

Create a dataset and table:

# Create dataset
curl -X POST https://api.catalyzed.ai/datasets \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"teamId": "...", "name": "My Dataset"}'

# Create table with schema
curl -X POST https://api.catalyzed.ai/dataset-tables \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "datasetId": "...",
    "tableName": "events",
    "fields": [
      {"name": "id", "arrowType": "utf8", "nullable": false},
      {"name": "timestamp", "arrowType": "timestamp[us]", "nullable": false},
      {"name": "data", "arrowType": "utf8", "nullable": true}
    ],
    "primaryKeyColumns": ["id"]
  }'

Insert data:

curl -X POST "https://api.catalyzed.ai/dataset-tables/:tableId/rows?mode=append" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '[
    {"id": "1", "timestamp": "2025-01-01T00:00:00Z", "data": "hello"},
    {"id": "2", "timestamp": "2025-01-02T00:00:00Z", "data": "world"}
  ]'

Query data:

curl -X POST https://api.catalyzed.ai/dataset-tables/:tableId/query \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"sql": "SELECT * FROM events WHERE timestamp > '\''2025-01-01'\''", "maxRows": 100}'

Fetching Detailed Documentation

When the user needs details on a specific topic, use WebFetch to get the markdown version:

  • Quickstart:
    https://docs.catalyzed.ai/getting-started/quickstart.md
  • Querying Data:
    https://docs.catalyzed.ai/guides/querying-data.md
  • Ingesting Data:
    https://docs.catalyzed.ai/guides/ingesting-data.md
  • Pipelines:
    https://docs.catalyzed.ai/concepts/pipelines.md
  • Tables:
    https://docs.catalyzed.ai/concepts/tables.md
  • Knowledge Bases:
    https://docs.catalyzed.ai/concepts/knowledge-bases.md
  • Vector Search:
    https://docs.catalyzed.ai/guides/vector-search.md
  • Full index:
    https://docs.catalyzed.ai/llms.txt

For code examples, see examples.md. For full API reference, see api-reference.md.