← Back to Skills Marketplace
volcengine-skills

Byted Data Label

by volcengine-skills · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
97
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install byted-data-label
Description
Seederive 非结构化数据打标平台,使用 LLM 对文本、语音、图片数据进行批量分析处理。 当用户提到以下任何场景时必须使用此 Skill:数据打标、标注、情感分析、标签分类、 观点提取、翻译、评论分析、水军识别、内容评分、标签库管理、提示词优化。 即使用户没有直接提到「Seederive」,只要涉及对一批...
README (SKILL.md)

Seederive 非结构化打标平台

你是 Seederive 平台的操作助手。所有 Seederive 操作从这里开始。

什么是 Seederive

Seederive 用 LLM 对文本/语音/图片数据做情感分析、标签分类、观点提取等批量处理。

认证配置

使用前需要设置 AK/SK 环境变量:

环境变量 说明 必填
VOLCENGINE_ACCESS_KEY Access Key
VOLCENGINE_SECRET_KEY Secret Key

验证连通性

设置好环境变量后,执行以下命令验证:

python3 ${SKILL_DIR}/scripts/seederive.py task list --page-size 1

如果返回 "code": 0 表示连通成功。如果返回认证错误,请检查 AK/SK 是否正确。

执行命令的方式

python3 ${SKILL_DIR}/scripts/seederive.py \x3C子命令和参数>

第一步:判断用户意图

阅读用户的需求,对照下表确定属于哪个场景:

场景 用户说了什么(示例) 下一步
A. 快速试效果 "帮我分析这几条评论" / "试一下情感分析" / "看看这些文本的标签" → 直接用 quick-preview,见下方「场景 A」
B. 创建批量任务 "帮我对这个数据表做情感分析" / "建一个打标任务" → 读取 ${SKILL_DIR}/references/task.md 获取详细指引
C. 需要标签体系 "按我们的标签分类" / "建一个标签库" / "主体识别" → 读取 ${SKILL_DIR}/references/tag-base.md 获取详细指引
D. 优化效果 "效果不好" / "帮我优化" / "上传错题" / "换个模型" → 读取 ${SKILL_DIR}/references/optimize.md 获取详细指引
E. 不确定 "我有一批数据想处理" / "能做什么" → 先问用户数据是什么、想得到什么结果,再回到本表判断

重要:场景 B/C/D 的具体操作步骤、参数说明、JSON 格式都在对应的参考文件中。你必须用 Read 工具读取对应文件后再执行,本文件不包含这些细节。

场景 A:快速试效果(唯一可以直接执行的场景)

这是最轻量的路径,无需创建任务,传几条文本就能看结果。

支持的分析类型

分析类型 nodeType 值 输出 额外参数
情感分析 EMOTION_DETECTION 正面/负面/中性 + 原因
营销水军识别 SHILL_DETECTION 是/否 + 原因
观点提取 OPINION_SUMMARY 核心观点 + 理由
内容评分 CONTENT_SCORING 质量/原创/有用/合规评分
翻译 TRANSLATION 翻译结果 --target-language
标签分类 TAG_DETECTION 多级标签 --tag-base-id(需要先建标签库,见场景 C)
主体识别 SUBJECT_DETECTION 多级主体 --tag-base-id(需要先建标签库,见场景 C)
自定义分析 CUSTOM_APPLICATION 自定义 --prompt + --output-fields

执行方式

方式一:直接传文本(推荐,最快)

python3 ${SKILL_DIR}/scripts/seederive.py task quick-preview \
  --raw-data '["文本1", "文本2", "文本3"]' \
  --node-type EMOTION_DETECTION \
  --input-column "评论内容"

方式二:上传文件

python3 ${SKILL_DIR}/scripts/seederive.py task quick-preview \
  --file data.csv \
  --node-type EMOTION_DETECTION \
  --input-column "评论内容"

方式三:导出结果为 CSV 文件

python3 ${SKILL_DIR}/scripts/seederive.py task quick-preview \
  --raw-data '["文本1", "文本2"]' \
  --node-type EMOTION_DETECTION \
  --input-column "评论内容" \
  --response-format csv --output result.csv

自定义分析示例

python3 ${SKILL_DIR}/scripts/seederive.py task quick-preview \
  --raw-data '["今天天气真好", "堵车堵了两小时"]' \
  --node-type CUSTOM_APPLICATION \
  --input-column "内容" \
  --prompt "提取关键词和情绪强度" \
  --output-fields '[{"fieldName":"keywords","fieldType":"String"},{"fieldName":"intensity","fieldType":"String"}]'

quick-preview 全部参数

参数 必填 说明
--raw-data 与 file 二选一 JSON 字符串数组或对象数组
--raw-data-file 与上二选一 JSON 文件路径
--file 与 raw-data 二选一 CSV / Excel 文件
--node-type 分析类型,见上表
--input-column 待处理文本的列名
--max-rows 最大处理行数(默认 10,上限 50)
--tag-base-id TAG/SUBJECT 需要 标签库 ID
--prompt CUSTOM 需要 自定义提示词
--output-fields CUSTOM 需要 输出字段 JSON 数组
--target-language TRANSLATION 用 目标语言(默认"中文")
--response-format json(默认)或 csv
--output CSV 输出文件路径

场景之间的流转

场景 A(试效果)
  │
  ├─ 效果满意 + 数据量大 → 场景 B(建正式任务批量跑)
  │                          → 读取 ${SKILL_DIR}/references/task.md
  │
  ├─ 需要标签分类 → 场景 C(先建标签库)→ 回到 A 或 B
  │                  → 读取 ${SKILL_DIR}/references/tag-base.md
  │
  └─ 效果不满意 → 场景 D(优化提示词/换模型)→ 回到 A 验证
                   → 读取 ${SKILL_DIR}/references/optimize.md

关键原则

  1. 先试后建:建议用户先用 quick-preview 试效果,满意后再创建正式任务
  2. 渐进披露:不要一次给用户灌输所有概念,按需引导到对应参考文件
  3. 按需加载:只有需要执行场景 B/C/D 时才去读取对应参考文件
Usage Guidance
This skill is a CLI wrapper for a Seederive/Volcengine labeling API and generally behaves as described, but take these precautions before installing or running it: - The SKILL.md and script require VOLCENGINE_ACCESS_KEY and VOLCENGINE_SECRET_KEY, but the registry metadata does not declare them — don't assume the skill will surface this requirement elsewhere. - The Python script will auto-install the 'requests' package at runtime if missing (it calls pip). Runtime installation of packages can modify your environment; prefer running in a sandbox/virtualenv or install dependencies yourself and inspect the package install commands first. - Verify the default API base URL (sd6qlcofkmfq59riqgli0.apigateway-cn-beijing.volceapi.com) is an expected Seederive/Volcengine endpoint before providing real credentials. If unsure, supply test/limited-permission keys first. - Review the included scripts (scripts/seederive.py) yourself: it performs HTTP requests (including file uploads) to the configured base URL using the AK/SK provided — that is necessary for the skill but also means your data and keys will be sent to that endpoint. - If you cannot verify the publisher or endpoint, consider running the skill only with throwaway credentials or in an isolated environment. If possible, request the skill author to update registry metadata to declare required env vars and list dependencies instead of doing runtime pip installs.
Capability Analysis
Type: OpenClaw Skill Name: byted-data-label Version: 1.0.0 The skill bundle provides a legitimate interface for the Seederive data labeling platform by Volcengine (ByteDance). The core component is a Python CLI script (scripts/seederive.py) that wraps REST API calls to a Volcengine API gateway (volceapi.com) using standard authentication via environment variables. The instructions in SKILL.md and the reference files (task.md, tag-base.md, optimize.md) are detailed and strictly aligned with the stated purpose of managing LLM-based data processing tasks. While the script includes a routine to auto-install the 'requests' library via subprocess if missing, this behavior is common in such agent skills and lacks evidence of malicious intent or unauthorized data exfiltration.
Capability Assessment
Purpose & Capability
The name, description, README (SKILL.md) and the included script all implement a Seederive data-labeling CLI that calls a Volcengine/Seederive OpenAPI — this is coherent with the stated purpose. However, the skill registry metadata declares no required environment variables or primary credential while the SKILL.md and the script clearly require VOLCENGINE_ACCESS_KEY and VOLCENGINE_SECRET_KEY. That metadata mismatch is unexpected and reduces trust.
Instruction Scope
SKILL.md instructs the agent to run the included CLI script and to read the packaged reference files in ${SKILL_DIR} for scenario-specific guidance. It asks the agent to read user-supplied data files (CSV/JSON) and to use two AK/SK environment variables — all these actions are within the described scope (creating/previewing/optimizing labeling tasks). The instructions do not ask the agent to read unrelated system config or to exfiltrate data to arbitrary endpoints beyond the service API.
Install Mechanism
There is no declared install spec, but the included Python script attempts to auto-install the 'requests' package at runtime via subprocess.check_call pip install if it is missing. Runtime package installation is a high-risk behavior (it writes to disk and executes external code) and should be made explicit in the skill metadata or avoided. No other external downloads are present in the files provided.
Credentials
The script and SKILL.md legitimately require VOLCENGINE_ACCESS_KEY and VOLCENGINE_SECRET_KEY to authenticate to the Seederive API, which is proportional to the skill's function. However, the skill registry metadata lists no required env vars or primary credential — an inconsistency that could cause users to unknowingly provide secrets without noticing or verifying. Also the script defaults to a specific API gateway base URL (sd6qlcofkmfq59riqgli0.apigateway-cn-beijing.volceapi.com); users may want to verify that endpoint is expected and trustworthy before supplying real credentials.
Persistence & Privilege
The skill does not request always:true, does not modify other skills or system-wide agent configuration, and only reads/writes files that are part of its documented workflow (user data files, output CSV). It will write downloaded CSV preview results to disk when requested, which is expected for this CLI.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install byted-data-label
  3. After installation, invoke the skill by name or use /byted-data-label
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Seederive 非结构化数据打标平台首发版本: - 新增通过 LLM 处理文本、语音、图片的情感分析、标签分类、观点提取等批量分析能力。 - 支持“快速试效果”模式,无需建任务即可试用多种分析类型。 - 场景分流指引:根据用户需求自动判断并引导至标签库、批量任务、优化等功能细节。 - 明确认证配置流程,提供环境变量和连通性验证说明。 - 增加多种命令参数用法与关键操作原则指导。
Metadata
Slug byted-data-label
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Byted Data Label?

Seederive 非结构化数据打标平台,使用 LLM 对文本、语音、图片数据进行批量分析处理。 当用户提到以下任何场景时必须使用此 Skill:数据打标、标注、情感分析、标签分类、 观点提取、翻译、评论分析、水军识别、内容评分、标签库管理、提示词优化。 即使用户没有直接提到「Seederive」,只要涉及对一批... It is an AI Agent Skill for Claude Code / OpenClaw, with 97 downloads so far.

How do I install Byted Data Label?

Run "/install byted-data-label" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Byted Data Label free?

Yes, Byted Data Label is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Byted Data Label support?

Byted Data Label is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Byted Data Label?

It is built and maintained by volcengine-skills (@volcengine-skills); the current version is v1.0.0.

💬 Comments