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 skills add taosdata/agent-skills --skill tdgpt-model-deploygit 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/tdgpt-model-deploy)<a href="https://agentmods.dev/skills/taosdata/agent-skills/tdgpt-model-deploy"><img src="https://agentmods.dev/badge/skills/taosdata/agent-skills/tdgpt-model-deploy/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.
<a href="https://agentmods.dev/skills/taosdata/agent-skills/tdgpt-model-deploy"><img src="https://agentmods.dev/badge/skills/taosdata/agent-skills/tdgpt-model-deploy.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00054 | $0.02935 |
| Opus 5 | $0.00027 | $0.01468 |
| Sonnet 5 | $0.00011 | $0.00587 |
| Haiku 4.5 | $0.00005 | $0.00294 |
Grade A, and why
tdgpt-model-deploy 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 9d 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.
curl -sk --max-time 3 -X POST \ How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TDGPT 模型部署辅助 (tdgpt-model-deploy)
何时使用 (When to use)
当用户需要部署、升级或配置 TDGPT 大模型服务(或对接 TDengine 的大语言模型服务)时,触发此技能。
触发关键词:部署 tdgpt、部署 TDengine GPT、部署大模型、tdgpt 部署。
输入 (Input)
- 核心输入:
- 目标部署环境的硬件规格(如 GPU 型号、显存大小、CPU 核心数、内存容量等)。
- TDGPT 模型文件的存储路径(如本地磁盘路径、S3 桶地址或 Hugging Face 模型 ID )。
- 需要连接的 TDengine 实例配置(主机名/IP、端口、数据库名等)。
- 运行依赖项(如 Python 版本、CUDA 版本、Web 框架偏好如 FastAPI/Flask )。
- 澄清策略:
- 如果未指定 GPU 规格,需向用户确认是否使用 CPU 运行(仅限测试)或者提供推荐的 GPU 显存大小(例如 7B 模型推荐 16GB+ VRAM)。
- 如果 user 没有指明部署方式,默认生成基于 Docker Compose 的容器化部署方案。
输出 (Output)
- 容器化配置文件 (Docker Compose):
- 提供一份完整的
docker-compose.yml,定义模型服务容器(如 vLLM、TGI、Ollama 等)、与 TDengine 容器的网络连通配置,以及显卡挂载配置(如deploy.resources.reservations.devices)。
- 提供一份完整的
- 依赖包描述文件 (Requirements):
- 若用户偏好原生部署,提供
requirements.txt(包含torch、transformers、taospy等核心包及兼容的版本范围)。
- 若用户偏好原生部署,提供
- 服务启动与验证脚本:
- 提供模型服务的启动指令。
- 提供一段轻量的 Python 或 Bash 验证脚本,向部署完成的 TDGPT 模型服务发送基础 Prompt,校验其是否能正常生成响应以及是否可连通 TDengine。
特殊业务模型部署默认约定 (Special Business Model Deployment Conventions)
为了降低前端展示和快速演示时的提示词要求,针对烘丝机出口水分时序预测服务模型的部署,若用户指令中仅指定部署该模型而未提供其他部署参数,默认使用以下部署配置约定:
- 默认时序预测服务类文件:
_moisture_forecast_Service.py - 默认配置文件:
tdgpt_moisture_rule.json - 部署目标:一键部署到正在运行中的 Docker 开发容器中。
- 自动加载与刷新:拷贝文件并重启
taosanode服务后,必须自动在 TDengine 客户端执行update all anodes;命令刷新算法列表缓存,保证模型即时生效,并运行基础的 FORECAST SQL 查询进行连通性与结果验证。
安全 (Safety)
- 凭证安全 (No Secrets):
- 严禁在生成的配置文件或脚本中硬编码任何真实的 API 密钥、数据库密码或敏感 Token。
- 应使用环境变量(如
TAOS_PASSWORD=${TAOS_PASSWORD})进行占位,并提醒用户在外部.env文件或系统环境中配置。
- 环境安全:
- 在执行诸如端口映射开放(如暴露 11434 / 8000 端口至公网)或拉取未经安全扫描的外部镜像前,必须向用户进行风险警示并获得确认。
实战部署案例与常见避坑指南 (Real-world Case & Troubleshooting)
在运行中的开发容器中一键部署与验证 TDgpt 自定义时序预测服务类时,必须注意以下几点以避免联调失败:
1. 算法列表缓存刷新 (Analysis algorithm/model not loaded [0x80000443])
- 痛点:将新算法(如
_moisture_forecast_Service.py)拷贝至容器内部,且重启taosanode服务后,直接执行预测 SQL 仍报错Analysis algorithm/model not loaded。 - 原因:TDengine TSDB 进程缓存了 ANODE 数据分析节点的算法列表,新算法注册后无法被 TSDB 自动探知。
- 解决:算法拷贝且容器重启就绪后,必须在 TDengine 命令行端执行
update all anodes;或者update anode <anode_id>;命令刷新算法列表缓存,直到执行show anodes full;能在列表中看到新算法状态为READY。
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.
- 9d ago First seen · 157 lines · 54 tokens per session scan A 58536f15c0ff
tdgpt-model-deploy is a skill published in the GitHub repository taosdata/agent-skills (3 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 2,935 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
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…