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 zrtch/awesome-skills --skill ag-earthgit clone --depth 1 https://github.com/zrtch/awesome-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/zrtch/awesome-skills/ag-earth)<a href="https://agentmods.dev/skills/zrtch/awesome-skills/ag-earth"><img src="https://agentmods.dev/badge/skills/zrtch/awesome-skills/ag-earth/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/zrtch/awesome-skills/ag-earth"><img src="https://agentmods.dev/badge/skills/zrtch/awesome-skills/ag-earth.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 | $0.00202 | $0.02275 |
| Opus 5 | $0.00101 | $0.01137 |
| Sonnet 5 | $0.00040 | $0.00455 |
| Haiku 4.5 | $0.00020 | $0.00228 |
Grade A, and why
Ag-earth scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
技能概述
这个技能用于自动化完成工具查找和执行的全流程,后端由 Agent Earth 提供,基础地址为 https://dev07.agentearth.ai:
用户自然语言描述 → 调用推荐 API → 语义匹配筛选 → 执行最优工具 → 返回结果
核心价值:
- 主动发现:模型不需要记住所有工具,只需描述意图。
- 上下文感知:能够理解多轮对话中的隐含参数(如“那边的价格”)。
- 决策辅助:不仅是查数据,还能支持“适不适合”、“建议”等决策类问题。
鉴权要求
所有对 https://dev07.agentearth.ai 的 API 请求(包括 recommend 和 execute)都必须包含鉴权头:
- Header Name:
X-Api-Key - Header Value:
<AGENT_EARTH_API_KEY> - 注意:
<AGENT_EARTH_API_KEY>的值来自环境变量$AGENT_EARTH_API_KEY。 - 获取 Key: 用户访问 AgentEarth 官方网站,在个人主页中添加 Key 即可完成注册并获取 API Key。
适用场景
使用这个技能当用户表达以下类型的意图时:
- 时事新闻:"I want to know the latest situation in Iran, please introduce it to me."
- 决策咨询:"I want to go skiing in Hokkaido, is it suitable to go these days?"(隐含查询天气、雪况、旅游建议)
- 具体数据:"I have decided to go skiing in Hokkaido, how are the housing prices there?"(隐含查询酒店/民宿价格,需继承“北海道”上下文)
- 功能调用:"Find me a tool that can translate documents."
- 任何暗示需要外部信息的场景
执行流程
Step 1: 调用推荐 API
向 POST https://dev07.agentearth.ai/agent-api/v1/tool/recommend 发送 JSON 请求:
Headers:
Content-Type: application/jsonX-Api-Key: $AGENT_EARTH_API_KEY
Body:
{
"query": "<结合上下文的完整自然语言描述>",
"task_context": "可选,任务上下文信息"
}
关键技巧(Context Injection):
如果用户的请求依赖上下文(例如“那边的房价”),必须在 query 中显式补全信息,或通过 task_context 字段传递。
- 用户输入:"那边的住房价格怎么样?"
- 历史上下文:"我想去北海道滑雪"
- 发送的 Query:"查询北海道的滑雪住房价格"(推荐这样做,让 Embedding 更准确)
Step 2: 语义匹配筛选
分析推荐结果(tools 列表),优先选择:
- 直接匹配:工具描述与任务高度重合。
- 组合能力:如果一个任务需要多个步骤(如“是否合适去”可能需要“天气”+“资讯”),优先选择能提供综合信息的工具,或准备多次调用。
Step 2.5: 参数检查与交互(关键)
在调用执行接口前,必须对照选中工具的 input_schema 进行参数完整性检查:
- 检查必填项:确认所有
required: true的参数是否都能从当前输入或对话历史中提取。 - 缺失处理:
- 如果缺失必填参数,不要调用 execute 接口。
- 直接向用户发起追问。
- 示例:"查询住房价格需要指定具体城市或区域,请问您是指'北海道'的哪个具体城市(如札幌、二世谷)?"
Step 3: 执行工具
调用 POST https://dev07.agentearth.ai/agent-api/v1/tool/execute 执行最优工具:
What ships with it
4 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.
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.
- 10d ago First seen · 207 lines · 202 tokens per session scan A 2a9f55fb5240
Ag-earth is a skill published in the GitHub repository zrtch/awesome-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 202 tokens to every session and 2,275 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…