lark-base

lark-base is a skill for Claude Code, Codex from EthanYoQ/Skill-hub. It costs 116 tokens per session (10,451 once invoked), scanned A, a copy of lark-base, MIT.

A Feishu Base assistant for working with shared tables, sometimes called multi-dimensional spreadsheets. It manages tables, fields, records, views, formulas, relationships, permissions, forms, dashboards, and workflows.

In plain words
What is it for?
It helps create and change tables and fields, read and update records, filter and sort data, calculate derived values, link tables, analyse data, and manage related views, forms, dashboards, roles, and workflows.
Why use it?
It removes the need to manage structured business data through scattered manual edits or separate API calls.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **前置条件:** 先阅读 [`../lark-shared/SKILL.md`](../lark-shared/SKILL.md)。.

Good fit It helps create and change tables and fields, read and update records, filter and sort data, calculate derived values, link tables, analyse data, and manage related views, forms, dashboards, roles, and workflows.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/EthanYoQ/Skill-hub
agentmods
npx agentmods add skills/ethanyoq/skill-hub/lark-base

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for lark-base

README.md
[![agentmods](https://agentmods.dev/badge/skills/ethanyoq/skill-hub/lark-base/github.svg)](https://agentmods.dev/skills/ethanyoq/skill-hub/lark-base)
Your own site
<a href="https://agentmods.dev/skills/ethanyoq/skill-hub/lark-base"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/lark-base/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for lark-base

Your own site · 80×15
<a href="https://agentmods.dev/skills/ethanyoq/skill-hub/lark-base"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/lark-base.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,451 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 94% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00116 $0.10451
Opus 5.5 $0.00046 $0.04180
Sonnet 5.5 $0.00023 $0.02090
Haiku 4.5 $0.00012 $0.01045

Measured 1mo ago against content hash 002ebc361d7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lark-base scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

94% identical to lark-base — 45 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

archives/user-installed-skills/lark-base/61a9ddfd289f4978/lark-base/SKILL.md · 362 lines

How it starts

The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.

base

前置条件: 先阅读 ../lark-shared/SKILL.md。 执行前必做: 执行任何 base 命令前,必须先阅读对应命令的 reference 文档,再调用命令。 查询类任务必做: 涉及筛选、排序、Top/Bottom N、聚合、多表关联、查询后写入或判断全局结论时,必须先阅读 references/lark-base-data-analysis-sop.md,再选择 record / view / data-query 路径。 命名约定: Base 业务命令仅使用 lark-cli base +... 形式;解析 Wiki 链接使用 lark-cli wiki +node-get。 分流规则: 如果用户要“把本地文件导入成 Base / 多维表格 / bitable”,第一步不是 base,而是 lark-cli drive +import --type bitable;导入完成后再回到 lark-cli base +... 做表内操作。

1. 何时使用本 Skill

1.1 触发条件

以下场景应使用本 skill:

  • 用户明确要操作飞书多维表格 / Base。
  • 用户要建表、改表、查表、删表,或管理字段、记录、视图。
  • 用户要做公式字段、lookup 字段、派生指标、跨表计算。
  • 用户要做临时统计、聚合分析、比较排序、求最值。
  • 用户要管理 workflow、dashboard、表单、角色权限。
  • 用户给出 /base/{token} 链接。
  • 用户给出 /wiki/{token} 链接,且最终解析为 bitable。
  • 用户要把旧的 Base 聚合式写法改成当前原子命令写法,例如把旧 +table / +field / +record / +view / +history / +workspace 改写成当前命令。

以下场景不应使用本 skill:

  • 用户只是做认证、初始化配置、切换 --as user/bot、处理 scope。此时先读 ../lark-shared/SKILL.md。
  • 用户只是泛化地讨论“数据分析 / 字段设计”,但并不在 Base 场景中。不要因为提到“统计 / 公式 / lookup”就误触发。

1.2 前置约束

  1. 先阅读 ../lark-shared/SKILL.md。
  2. Base 业务命令仅使用 lark-cli base +... 形式的 shortcut 命令。
  3. 如果输入是 Wiki 链接或 Wiki token,并且用户想读取/操作其中的 Base,先执行 lark-cli wiki +node-get --node-token <wiki_url_or_token>;当返回 data.obj_type=bitable 时,把 data.obj_token 当作 --base-token。不要把 URL 里的 /wiki/{token} 当成 Base token。(旧的 --token flag 仍可用,但已 deprecated,会在 stderr 打印迁移提示。)
  4. 定位到命令后,先读该命令对应的 reference,再执行命令。
  5. 如果用户要把本地 Excel / CSV / .base 快照导入成 Base / 多维表格 / bitable,第一步不是 base,而是 lark-cli drive +import --type bitable;导入完成后再回到 lark-cli base +... 做表内操作。
  6. 不要在 Base 场景改走 lark-cli api /open-apis/bitable/v1/...。
  7. 如果用户只给 Base 名称、关键词,或说“帮我找一个多维表格”,先通过 lark-cli drive +search --query <keyword> --doc-types bitable 搜索 Base / 多维表格资源;拿到 Base URL 后再使用本 skill 的 base +... 命令。复杂搜索再读 ../lark-drive/references/lark-drive-search.md:标题精确匹配、限定 owner(--mine / --creator-ids,owner 语义非"最初创建人")/群/文件夹/时间范围、只搜标题/评论、分页/全量搜索。

Read the full file on GitHub · 362 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 362 lines · 116 tokens per session scan A 002ebc361d7b

Subscribe to this mod's changes

lark-base is a skill published in the GitHub repository EthanYoQ/Skill-hub (11 stars, last pushed 5d ago), licensed MIT. It adds 116 tokens to every session and 10,451 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to lark-base, differing in 45 lines, and is treated as a copy.

Related

Other skills, from other repositories

dba-designer

Database Architect / DBA role skill. Use when you need to design database schemas, performance strategies, security design, or data model reviews. Keywords: database design, schema design, table structure, index design, performance optimisation, data security, data integrity, ER diagram, database standards.

nelson820125/iforgeai · 0 tokens

DataWarehouseArchitect

Complete modern data stack intelligence — data warehouse design (Snowflake/BigQuery/Redshift), dbt transformation layer, ingestion pipelines, data catalog, data quality, and building a data platform that the whole company can use.

vignesh2027/Claude-Agentic-Skills2.0-version · 48 tokens

database-genius

Activates DatabaseGenius for database design, optimization, and migration. Use when you need ERD and schema design with normalization decisions, composite/partial/covering index strategy, EXPLAIN plan analysis and query rewriting, zero-downtime migration planning with rollback strategy, or pgvector setup for AI…

vignesh2027/Claude-Agentic-Skills2.0-version · 68 tokens

knowledge-graph-builder

Activates KnowledgeGraph — an expert in building, querying, and reasoning over knowledge graphs. Use when you need entity extraction, relationship mapping, ontology design, Neo4j/RDF graph construction, graph-RAG pipelines, or complex multi-hop reasoning over structured knowledge.

vignesh2027/Claude-Agentic-Skills2.0-version · 58 tokens

sql-analyzer

Activates SQLAnalyzer for advanced SQL optimization, query analysis, and database performance tuning. Use when you need to optimize a slow query using EXPLAIN plans, rewrite subqueries as CTEs or window functions, design complex analytical queries, identify missing indexes, eliminate N+1 patterns, or write advanced…

vignesh2027/Claude-Agentic-Skills2.0-version · 79 tokens

business-intelligence-pro

Activates BusinessIntelligence-Pro for KPI design, dashboard strategy, and SQL optimization. Use when you need north star metric and metric tree design, LookML or Looker explore architecture, complex SQL with window functions and CTEs, threshold-based and ML-powered alerting design, or data storytelling for executive…

vignesh2027/Claude-Agentic-Skills2.0-version · 68 tokens