feishu-bitable-creator_skill

This skill creates clean Feishu bitable tables from scratch and populates them with fields and records, auto-cleaning placeholders.
  • Python

2.6k

GitHub Stars

2

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill openclaw/skills --skill feishu-bitable-creator

  • _meta.json484 B
  • SKILL.md17.0 KB

Overview

This skill creates clean, ready-to-use Feishu (Lark) Bitable tables and populates them with data while removing default clutter. It automates cleanup of placeholder rows and unused default columns, renames the primary field intelligently, and supports batch field and record creation. The result is a clean table URL and a summary of the created structure and record counts.

How this skill works

When you request a new table, the skill creates the Bitable, removes the default placeholder rows and unnecessary default columns, and renames the primary field based on the table name. You can then batch-add custom fields and records; the skill returns the dynamic primary field name to ensure records include the required key. It also handles value formatting for common field types and batches large inserts to avoid timeouts.

When to use it

  • Create a new Bitable with no placeholder rows or unused default columns
  • Batch-create fields and records from structured data
  • Convert CSV, JSON, or other structured data into a Bitable table
  • Build research, comparison, or tracking tables quickly and consistently
  • Prepare a clean table template for team collaboration or reporting

Best practices

  • Name tables descriptively so the primary field becomes meaningful (e.g., “Project List”, “Research Summary”)
  • Create all custom fields first, then insert records to preserve field order
  • Always use the returned primary_field_name when adding records
  • Batch record inserts (20–30 per batch) for large datasets to avoid timeouts
  • Format values according to field type: arrays for multi-select, ISO/timestamps for dates, numbers for numeric fields

Example use cases

  • Create a research comparison table, add fields like Framework, Stars, and Use Cases, then bulk import findings
  • Set up a project tracking table where the primary field becomes “Project Name” and add status and assignee fields
  • Convert a CSV of customer follow-ups into a clean Bitable with fields for priority, next contact date, and notes
  • Build a product feature list with tags as multi-select and import feature rows in batches

FAQ

It returns the table URL, app token, table ID, the computed primary_field_name, and a brief summary of created fields and record count.

How is the primary field name chosen?

The skill renames the primary field based on table name patterns (e.g., names containing “project” become “Project Name”); otherwise it uses the table name or truncates long names for readability.

How should I send multi-select or date values?

Provide multi-select values as arrays (e.g., ["tagA","tagB"]) and dates as ISO strings or timestamps. Number fields accept integers or decimals.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational