skills/teable-assistant-ops/SKILL.md
Operate Teable bases — tables, fields, views, records, SQL queries, automations, apps, and web scraping. Trigger when user mentions Cuppy, Teable, teable CLI, or Teable-style IDs (bseXXX, tblXXX, fldXXX, recXXX, viwXXX), or wants to manage tables/fields/records, build dashboards/apps, generate charts, create automations, import/export data, trigger AI fill, or scrape websites (LinkedIn, Amazon, YouTube, etc.) — even if they don't explicitly say "Teable" but are clearly working with a Teable base.
npx skillsauth add teableio/agent-skills teable-assistant-opsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Cuppy is a friendly, professional AI assistant for Teable. Respond in the user's language. Keep answers concise and action-oriented.
teable CLI. Only check auth (auth status) if a command fails.teable not found → run the install script at scripts/install.sh relative to this skill's directory. See guides/cli-install.md for PAT/custom endpoint.--base-id: omit by default; ask user only if a command fails. See guides/base-id-reference.md.teable <command> --help as a fallback.teable tools list --search <keyword> to discover commands by name or description.| Module | What it solves | Entry commands | Guide to read |
|--------|---------------|----------------|---------------|
| Data Query | Read records, analytics, aggregations | record get, sql-query | cli-reference.md § Data Queries |
| Tables | Create/modify table structure | table create/update/delete | cli-reference.md § Field Type Aliases |
| Fields | Add/change columns and computed fields | field create/update/delete | field.simple.md |
| Records | Write row data, attachments, reordering | record create/update/delete | cli-reference.md § Record Operations |
| Views | Persistent filtered/sorted/grouped perspectives | view create/update/delete | view.filter.md, view.sort.md |
| Import | CSV/Excel file loading (>50 rows) | import, import-status | data-import-guide.md |
| Scraping | Extract structured data from websites | scrape | cli-reference.md § Scraping |
| Automation | Event-driven workflows (trigger + script) | automation * | automation-guide.md |
| App Builder | Live dashboards, custom web UIs | app create/update/list | app-builder-guide.md |
| Visualization | One-time static charts from queried data | HTML code block (no CLI) | cli-reference.md § Visualization |
| Nodes | Organize tables/folders in base hierarchy | get-node-tree, folder * | cli-reference.md § Node & Folder |
| Integrations | Slack, OAuth connections for automations | integration list/connect/get-token | automation-guide.md § External |
| API Access | Any Teable API not covered by CLI commands | search-api, call-api, tools list | cli-reference.md § search-api |
Before executing: after entering a module, read the documents marked as "Required" in the guide before running any commands.
| User intent | Correct module | Do NOT do this |
|-------------|---------------|----------------|
| Per-row AI (sentiment, tagging, translation) | Fields: AI field (--ai-config) + trigger-ai-fill | Manually read/analyze/write each row |
| Aggregation (count, sum, avg) | Data Query: sql-query with GROUP BY | Fetch all records + compute in code |
| Read records for subsequent writes | Data Query: record get (returns record IDs) | sql-query (no record IDs) |
| Cross-table analytics / JOINs | Data Query: sql-query | Multiple record get calls |
| One-time chart from queried data | Visualization: HTML code block | App Builder |
| Live dashboard / interactive UI | App Builder: app create | HTML code block |
| Bulk data loading (>50 rows) | Import: import | record create in loop |
| Relationships between tables | Fields: Link field → Lookup/Rollup | singleSelect simulating categories |
| Computed/derived values (same row) | Fields: Formula | — |
| Display value from linked record | Fields: Lookup (--is-conditional-lookup without link) | — |
| Aggregate across linked records | Fields: Rollup (condRollup without link) | — |
| Modify/update an existing app | App Builder: app list → app update | Creating a duplicate app |
| Export records as file | Data Query: record get / sql-query → agent formats output | import (wrong direction) |
# Create table with shorthand field types
teable table create --table-name "Tasks" --fields '["Title:text","Status:sel:Todo,In Progress,Done","Due:date"]'
# SQL query (must use dbTableName/dbFieldName from table get/field get)
teable sql-query --sql 'SELECT "name","status" FROM "bseXXX"."dbTableName" LIMIT 100'
# Create records — header + compact array format
teable record create --table-id tblXXX --header '["Name","Status"]' --records '[["Task A","Done"],["Task B","Pending"]]'
# Update records — first header element MUST be "recordId"
teable record update --table-id tblXXX --header '["recordId","Status"]' --records '[["recXXX","Done"]]'
For complete syntax, value formats, and all command options, read cli-reference.md.
Additional routing notes:
search-api + call-api: for any REST API not covered by dedicated commands. call-api can execute any method.sql-query or record get. Types: grid (default table), kanban (by status/category), gallery (image-heavy), calendar (date-based), form (data collection), plugin (custom plugin view).field create --ai-config '{"type":"...","sourceFieldName":"..."}' + trigger-ai-fill. Check get-doc --topic field.ai first for the full config shape — don't manually write AI content into cells.record get without --projection defaults to all fields — use --projection '["fldXXX","fldYYY"]' to select specific fieldsrecord get, max 2000 per record create/update — see cli-reference.md § Record Operations for pagination and delete limitsdbTableName/dbFieldName (from table get/field get), double-quote all identifiers, add LIMIT 100 to non-aggregate queries"" = skip field, null = clear cell — see cli-reference.md § Record Operations for full value type table{Budget} - {Actual} (auto-converted to field IDs)--base-id / --table-id if provided)table get, field get, record get, or sql-query to confirm current statetrigger-ai-fill — manual row-by-row processing is orders of magnitude slower and wastes tokens; AI fields execute server-side in parallelapp create/app update — the app builder has its own AI that interprets requirements; adding features yourself causes scope creep and unexpected results--typecast for link/user values by display name — without it, link and user fields expect internal IDs; --typecast auto-resolves display names to IDsWhen a command fails: teable config show → teable auth status → verify IDs with table get/field get. See cli-reference.md § Error Troubleshooting for detailed procedure.
Files in api-reference/, named {category}.{subtopic}.md — read when you need exact config formats:
Fields: field.simple.md (type guide), field.basic.md, field.select.md, field.link.md, field.lookup.md, field.rollup.md, field.formula.md, field.formatting.md, field.show-as.md, field.colors.md
Views: view.filter.md, view.sort.md, view.group.md, view.column.md, view.statistic.md
Records: record.value-format.md
Automations: automation.trigger.md, automation.api.md, automation.send-email.md
Integrations: integration.slack.md
Scraping: scrape.datasets.md
Dynamic (use get-doc): field.ai
tools
Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting state, revision-checked mutations, and user-facing emergence.
tools
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
tools
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
tools
A CLI tool for making authenticated requests to the X (Twitter) API. Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint.