Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/taosdata/agent-skills/idmp-sample-data-generatornpx skills add taosdata/agent-skills --skill idmp-sample-data-generatorgit clone --depth 1 https://github.com/taosdata/agent-skillsWrote 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.
[](https://agentmods.dev/skills/taosdata/agent-skills/idmp-sample-data-generator)<a href="https://agentmods.dev/skills/taosdata/agent-skills/idmp-sample-data-generator"><img src="https://agentmods.dev/badge/skills/taosdata/agent-skills/idmp-sample-data-generator.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00064 | $0.03623 |
| Opus 5 | $0.00032 | $0.01811 |
| Sonnet 5 | $0.00013 | $0.00725 |
| Haiku 4.5 | $0.00006 | $0.00362 |
Grade A, and why
idmp-sample-data-generator scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> 所有接口调用默认使用 `curl` 命令在 bash 环境中执行。 How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IDMP 示例数据生成与自动执行工具
根据业务场景描述，自动完成资产建模、JSON 配置生成、单位校验和 API 推送，将模拟数据加载到 IDMP 系统。
输入要求
| 参数 | 场景 Demo 生成 (类别 1) | 业务数据接入 (类别 2) | 说明 |
|---|---|---|---|
| 项目根目录路径 | ✅ 必传 | ✅ 必传 | 本次任务的绝对路径，所有产物需存入其 outputs/ |
| 行业调研路径 | ✅ 必传 | — | outputs/industry_research.md 的绝对路径 |
| 原始数据/结构文件 | — | ✅ 必传 | 用户提供的 CSV、Excel 或 Markdown 格式的结构定义 |
目录规范要求：
- 过程中生成的 Python 脚本必须存放在项目根目录下的
scripts/。 - 最终产物（
sample_data.json等）必须存放在项目根目录下的outputs/。
常见陷阱（Gotchas）
以下规则是 Agent 在没有明确提示时最容易出错的地方，执行前必须阅读。
超级表设计
- 严格遵循"同类设备一张超级表"原则。不同采集指标的设备必须拆分为独立超级表，切勿合并，否则会产生大量 NULL 值。
namingPattern 固定值
- 所有
templates中的namingPattern固定为${KEYWORD1}，不得修改。
资产命名与子表名唯一性
- 严禁在不同的行政层级或工艺段下使用重复的名称（例如：禁止在“A 线”和“B 线”中同时出现名称为“冲压机-1”的设备）。
- 强制规范：如果不同块中使用相同的设备模板，必须通过添加父级上下文前缀（如
"values": ["灌装线1-泵-1", "灌装线1-泵-2"]）或使用全局递增序列来确保名称不重复。
树状结构与 Tag 映射
tree_root中的tag_name必须设为对应超级表tags数组的第一个 tag 名称。children节点中必须为超级表中**所有 tag（包括第一个 tag）**进行显式赋值。- Tag 赋值数组长度必须与
child_table_names展开后的设备数量完全一致，即使值相同也必须逐一列出（如"vendor": ["东方泵业", "东方泵业"]）。
模拟函数（fun）
fun字段仅允许使用sin(x)、cos(x)、random(n)三种函数。- 禁止使用
floor、ceil、abs、sqrt、pow、exp、log等任何其他函数。 - 示例：
"fun": "2.0 * sin(x) + random(0.5) + 5.0"
单位（uom）规范
uom字段必须使用国际标准符号或系统已定义缩写（如m、m³、°C），不得使用全称（如"米"、"摄氏度"）。自定义单位使用不超过 5 个字符的英文缩写。- 如果没有单位，确保
uom和uomClass都为 - 同一
uomClass中的单位必须物理上可互相转化。物理意义不同的单位（如"频率"和"生产频率"）必须分配不同的uomClass。
数值类型
- 数值型指标尽量使用浮点型（
Float或Double），除非业务明确要求整数。
历史数据量
- 无 CSV 文件时，默认生成过去 7 天历史数据。
insert_rows计算公式：insert_rows = 7 * 24 * 60 * 60 * 1000 / time_step - 若提供了 CSV 数据文件，
insert_rows固定设为0。
文件写入
- 严禁用单次
Write工具写入完整 JSON，必须执行分段写入（见第二步）。
执行流程
Telemetry (MUST)
调用
skill-telemetry，传入name=idmp-sample-data-generator version=0.3.0 author=Wang Zhe。 失败不阻塞，但必须尝试。详见skill-telemetry。
What ships with it
9 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.
- README.md 2.9 KB
- scripts/duplicate_check.py 7.7 KB runs code
- scripts/extract_tables.py 5.6 KB runs code
- scripts/uom_check.py 17 KB runs code
- scripts/upload_sample.py 13 KB runs code
- scripts/validate_sample_data.py 12 KB runs code
- templates/idmp_sample_data_v1.json 6.6 KB
- templates/uom_template.json 871 B
- templates/uomclass_template.json 626 B
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.
- 6d ago First seen · 247 lines · 64 tokens per session scan A 763e138f92b4
idmp-sample-data-generator is a skill published in the GitHub repository taosdata/agent-skills (3 stars, last pushed 22d ago), licensed MIT. It adds 64 tokens to every session and 3,623 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pinecone
Managed vector DB for production RAG and search.
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
cognee-community
Use when the user needs something that ships outside cognee core — community database adapters (Qdrant, Milvus, Weaviate, Redis, Pinecone, FalkorDB, Memgraph, DuckDB, NetworkX, …), data-source connectors (Slack, Gmail, Notion, Confluence, Google Drive), custom tasks/pipelines/retrievers (Exa, ScrapeGraph, codify)…
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
ingesting-into-data-lake
Import data into the AWS data lake from S3 files, local uploads, JDBC databases (Oracle, SQL Server, PostgreSQL, MySQL, RDS, Aurora), Amazon Redshift, Snowflake, BigQuery, DynamoDB, or existing Glue catalog tables (migration). Default target is S3 Tables; standard Iceberg on a general purpose bucket is supported where…