← 返回 Skills 市场
antonygiomarxdev

Livestock Assistant

作者 antonygiomarxdev · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ⚠ suspicious
211
总下载
1
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install livestock-assistant
功能描述
AI-powered livestock management assistant for Spanish-speaking farmers. Provides expert advice on herd management, animal health, reproduction, genetics, nut...
使用说明 (SKILL.md)

OpenClaw Livestock Assistant

Expert livestock management assistant for Spanish-speaking farmers. Responds always in Spanish. Combines AI chat with a REST API for herd record-keeping.

Capabilities

  • Herd management — register and track animals (bovine, ovine, caprine, porcine, equine, poultry)
  • Animal health — vaccination schedules, disease identification, treatment guidance
  • Reproduction — heat detection, pregnancy tracking, birth records, genetics
  • Nutrition — ration formulation, forage selection, supplementation
  • Breed advice — selection by aptitude (meat / milk / wool / dual-purpose)
  • REST API — persistent record-keeping via Express server on http://localhost:3000

Starting the API Server

Before using any REST API endpoint, start the server:

bash scripts/start.sh

The server exposes /health, /api/animals, and /api/assistant — see references/api.md for the full endpoint reference.

AI Provider Configuration

The assistant supports OpenAI, Anthropic (Claude), and Google (Gemini). Set at least one API key; the assistant auto-selects the provider.

Provider API key env var Default model
OpenAI OPENAI_API_KEY gpt-5
Anthropic ANTHROPIC_API_KEY claude-opus-4-6
Google GOOGLE_GENERATIVE_AI_API_KEY gemini-2.5-pro

Override explicitly via:

  • AI_PROVIDER=openai|anthropic|google — force a specific provider
  • AI_MODEL=\x3Cmodel-id> — override the model ID for the chosen provider

AI Chat

Every interaction should be in Spanish. Use the system prompt embedded in src/assistant/systemPrompt.ts as the agent's knowledge baseline.

Create a session before sending messages:

curl -X POST http://localhost:3000/api/assistant/sessions
# → { "sessionId": "...", "welcome": "¡Hola! Soy el Asistente de Ganadería..." }

curl -X POST http://localhost:3000/api/assistant/sessions/\x3CsessionId>/messages \
  -H "Content-Type: application/json" \
  -d '{"message": "¿Cómo prevenir la mastitis en vacas lecheras?"}'

Domain References

Load these files when you need detailed reference data:

Reference When to read
references/breeds.md User asks about breeds, selection, or characteristics
references/diseases.md User reports symptoms, asks about prevention or treatment
references/nutrition.md User asks about feeding, rations, forages, or supplementation
references/api.md User wants to register animals or retrieve herd data

Animal Status Reference

Field Allowed values
species bovine ovine caprine porcine equine poultry
sex male female
status active sold dead quarantine
healthStatus healthy sick in_treatment recovered
reproductiveStatus open pregnant lactating in_heat served not_applicable

Safety Guidelines

  • Never diagnose diseases definitively — always recommend a veterinarian for emergencies.
  • Zoonotic diseases (e.g., Brucelosis) must be flagged immediately.
  • Urgency levels: lowmediumhighemergency. Escalate accordingly.
安全使用建议
This package appears incomplete or mispackaged. Before installing or providing API keys: 1) Confirm whether the repository actually includes the Node/Express code and the scripts referenced in SKILL.md (scripts/start.sh, src/assistant/systemPrompt.ts). 2) Don't supply all three AI provider keys unless you trust the author — provide only the single provider key you intend to use. 3) Ask the maintainer to fix the manifest so requires.env matches the documented 'at least one' requirement, or include the missing code. 4) If you plan to run the server locally, review the server code and startup script for network endpoints, data collection, and any external calls. 5) If you cannot validate the code/repository, avoid installing or granting credentials; treat this as an untrusted, incomplete skill.
功能分析
Type: OpenClaw Skill Name: livestock-assistant Version: 0.1.0 The skill bundle requests high-risk capabilities including local shell execution (via scripts/start.sh) and the operation of a local REST API server (port 3000), which are classified as suspicious under the provided criteria even when plausibly required for the stated purpose. Furthermore, the metadata contains significant anomalies, such as a future publication date (March 2026) and references to non-existent AI models (e.g., 'gpt-5' and 'claude-opus-4-6'), suggesting the content may be synthetic or unreliable. While the livestock reference data in references/ appears legitimate and no clear evidence of intentional malice was found, the combination of shell/network access and hallucinated technical details warrants caution.
能力评估
Purpose & Capability
The skill claims to provide a Node.js REST API and references runtime files (scripts/start.sh, src/assistant/systemPrompt.ts), but the bundle contains no code or scripts—only docs. Requiring the node binary and installing ts-node would make sense if code were present, but as packaged the install/requirements are disproportionate to an instruction-only skill.
Instruction Scope
Runtime instructions tell the agent to start a local Express server and to load a system prompt from src/assistant/systemPrompt.ts; those files are not present in the manifest. The SKILL.md also lists reading domain reference files (which are present) — that part is fine — but the missing start script and source files are a clear mismatch.
Install Mechanism
Install spec requests the ts-node npm package (creates ts-node binary). Installing ts-node from npm is a moderate-risk action but is unnecessary here because no TypeScript code is provided. No external download URLs or extract steps are present.
Credentials
requires.env lists OPENAI_API_KEY, ANTHROPIC_API_KEY, and GOOGLE_GENERATIVE_AI_API_KEY, but SKILL.md states 'Set at least one API key' and marks OPENAI_API_KEY as primaryEnv. Requiring all three credentials is disproportionate and inconsistent with the stated 'at least one' policy. Supplying multiple model provider keys increases blast radius if the skill acts autonomously.
Persistence & Privilege
The skill does not request always:true, does not declare config paths, and is user-invocable only. Autonomous invocation is allowed by default (disable-model-invocation: false), which is normal, but combined with the multi-provider credential requirement this raises caution (see guidance).
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install livestock-assistant
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /livestock-assistant 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v0.1.0
Initial release of OpenClaw Livestock Assistant: expert AI-powered livestock management for Spanish-speaking farmers. - Provides expert advice on herd management, animal health, reproduction, genetics, nutrition, and breed selection across major livestock species. - Includes a Node.js REST API for persistent herd record-keeping (animal registration, health records, reproduction events). - Supports OpenAI, Anthropic, and Google AI providers—auto-selects or allows override through environment variables. - All chat responses are always in Spanish, tailored for effective communication with Spanish-speaking users. - Loads domain-specific references for breeds, diseases, nutrition, and animal record management when requested. - Implements safety protocols: flags zoonotic diseases, always advises veterinary intervention for emergencies, and escalates urgent cases appropriately.
元数据
Slug livestock-assistant
版本 0.1.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Livestock Assistant 是什么?

AI-powered livestock management assistant for Spanish-speaking farmers. Provides expert advice on herd management, animal health, reproduction, genetics, nut... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 211 次。

如何安装 Livestock Assistant?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install livestock-assistant」即可一键安装,无需额外配置。

Livestock Assistant 是免费的吗?

是的,Livestock Assistant 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Livestock Assistant 支持哪些平台?

Livestock Assistant 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Livestock Assistant?

由 antonygiomarxdev(@antonygiomarxdev)开发并维护,当前版本 v0.1.0。

💬 留言讨论