bytedance avatar

Byted Data Search

This is a Chinese industry data search tool that plugs into compliant public data sources covering enterprise registration info, supply chain metrics, and A-share stock data. You query it by first calling describe_datasource to see what fields exist, then constructing filters with the right operators for each field type. The workflow is strict: text fields need "like", keywords need "eq", and you'll hit errors if you mix them up. It's built for questions like "show me all specialized and sophisticated enterprises in the semiconductor chain" or "what's the regional distribution of new energy companies." The documentation is thorough about field types and includes a separate script to enumerate possible values before filtering, which saves you from guessing whether a status field uses "存续" or "在业". Requires Volcengine credentials.

skills.sh installs
140
GitHub stars
484
last updated
Aug 21, 2026

Install

$ npx -y skills add bytedance/agentkit-samples --skill byted-data-search --agent claude-code

Installs into .claude/skills of the current project.

Files

数据查询工具

前置要求

需要环境变量(脚本会自动读取,若读取不到需提醒用户设置):

  • VOLCENGINE_ACCESS_KEY(或 VOLC_ACCESS_KEY)
  • VOLCENGINE_SECRET_KEY(或 VOLC_SECRET_KEY)

工作流程(严格按顺序执行)

第一步:查询可用数据源(必须先执行)

在构造任何查询之前,必须先调用此步骤了解有哪些数据源及其字段定义。这一步的作用是:确认用户需要的数据存在于哪个数据源中,以及该数据源有哪些字段和过滤规则。跳过这一步直接去猜字段名几乎一定会出错。

# 列出所有可用数据源摘要(含 datasource_id、名称、描述、维度/过滤字段数量)
python3 scripts/describe_datasource.py --datasource-id all

# 获取某个数据源的完整字段定义(维度 dimensions、字段类型、可用过滤操作符)
python3 scripts/describe_datasource.py --datasource-id <数据源ID>

返回内容包含:

  • datasource_id:数据源唯一标识
  • datasource_name:数据源中文名称
  • description:数据源说明
  • dimensions:所有字段列表,每个字段包含 field(字段名)、label(显示名)、type(类型)、description(描述)、filterable(是否可作为过滤条件字段)
  • notes:使用备注

关键:根据返回的字段信息(尤其是 field 名称和 type 类型),确定需要用到的字段和过滤操作符,再进入第二步。

字段类型与操作符对照表

每种字段类型只支持特定操作符。用错操作符会直接报错,所以在构造 filters 之前请务必对照此表。

字段类型支持的操作符说明
keywordeq, in, not_in精确匹配类字段(如编码、状态、类型)
textlike, keyword文本类字段(如名称、地址、描述),支持模糊搜索
date / datetimebetween, eq日期类字段,范围查询用 between
long / integer / float / doublerange, eq数值类字段,范围查询用 range

Sponsors

Details

Repository
github.com/bytedance/agentkit-samples
First seen
Jun 3, 2026

More from bytedance/agentkit-samples

All 6

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs