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 qingkongzhiqian/groundapi --skill groundapi-web-researchergit clone --depth 1 https://github.com/qingkongzhiqian/groundapiWrote 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/qingkongzhiqian/groundapi/groundapi-web-researcher)<a href="https://agentmods.dev/skills/qingkongzhiqian/groundapi/groundapi-web-researcher"><img src="https://agentmods.dev/badge/skills/qingkongzhiqian/groundapi/groundapi-web-researcher/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/qingkongzhiqian/groundapi/groundapi-web-researcher"><img src="https://agentmods.dev/badge/skills/qingkongzhiqian/groundapi/groundapi-web-researcher.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 | $0.00044 | $0.01068 |
| Opus 5.5 | $0.00018 | $0.00427 |
| Sonnet 5.5 | $0.00009 | $0.00214 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
groundapi-web-researcher 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 2mo 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.
What it actually says
网络调研助手
当用户需要对某个话题做深入了解,或类似以下表达时自动触发:
- "帮我调研一下 XXX"、"查一下 XXX 的情况"
- "XXX 的最新进展是什么"、"帮我了解一下 XXX"
- "对比一下 A 和 B"、"总结一下这个话题"
- "帮我搜一下..."、"研究一下..."
- "现在什么最火"、"今天有什么热点"
前置条件
本 Skill 依赖 GroundAPI MCP Server 提供的工具。确保已配置 GroundAPI MCP 连接:
{
"mcpServers": {
"groundapi": {
"url": "https://mcp.groundapi.net/mcp",
"headers": {
"X-API-Key": "sk_gapi_xxxxx"
}
}
}
}
执行流程
Step 1 — 拆解调研问题
将用户的调研需求拆解为 1-3 个搜索查询,覆盖不同角度。
示例:用户说"帮我调研一下固态电池的发展现状"
- 查询 1:
固态电池 技术进展 2026(技术角度) - 查询 2:
固态电池 产业链 公司 量产(产业角度) - 查询 3:
固态电池 市场规模 预测(市场角度)
Step 1.5 — 热度预判(可选)
调用 info_trending() 查看该话题是否在全网热搜中,了解当前舆论热度。
调用 info_bulletin() 获取每日新闻简报,看该话题是否在今日重点事件中。
如果话题正在热搜,优先使用 recency="oneDay" 获取最新信息。
Step 2 — 搜索
对每个查询调用 info_search(query="...", count=10, recency="oneMonth")。
如果话题有时效性或正在热搜中,使用更短的 recency(oneWeek 或 oneDay)。
Step 3 — 筛选与综合
从搜索结果中挑选最相关、最权威的 3-5 个条目(优先选择:官方来源 > 权威媒体 > 行业报告 > 博客),基于 snippet 摘要进行综合。
由于摘要长度有限,建议针对同一话题用不同关键词组合多搜几轮,以获得更全面的信息。
Step 4 — 综合输出
## 🌐 调研报告:{话题}
### 概述
(2-3 句话的核心结论)
### 关键发现
**1. {角度一标题}**
- 要点 A(来源:XXX)
- 要点 B(来源:XXX)
**2. {角度二标题}**
- 要点 A(来源:XXX)
- 要点 B(来源:XXX)
**3. {角度三标题}**
- 要点 A(来源:XXX)
- 要点 B(来源:XXX)
### 总结与观点
(基于多源信息的综合判断,标注哪些是事实、哪些是推测)
### 信息来源
1. [标题](URL) — 简要说明
2. [标题](URL) — 简要说明
3. ...
对比调研模式
当用户要求对比两个或多个事物时(如"对比 React 和 Vue"),调整流程:
- 对每个对比对象分别搜索
- 抓取各自最相关的 2-3 篇内容
- 按统一维度做对比表格输出:
### 对比:A vs B
| 维度 | A | B |
|------|---|---|
| 维度1 | ... | ... |
| 维度2 | ... | ... |
| ... |
### 结论
(根据使用场景给出建议)
注意事项
- 始终标注信息来源,不要把不同来源的信息混在一起而不注明
- 区分"事实"(有明确数据支撑)和"观点"(来自分析/预测)
- 如果搜索结果质量不佳或信息过少,如实告知用户,不要编造内容
- 抓取网页时尊重内容:不要抓取明显需要付费阅读的内容
- 输出语言跟随用户
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.
- 2mo ago First seen · 128 lines · 44 tokens per session scan A c81b3eb37c46
groundapi-web-researcher is a skill published in the GitHub repository qingkongzhiqian/groundapi (0 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 1,068 once invoked, about $0.0002 per session on Opus 5.5. 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
fli
Guidance for installing and using Fli correctly as a CLI and MCP server. Use when: setting up Fli with pipx, running fli flight searches, configuring Claude Desktop with fli-mcp, using the HTTP MCP server, or troubleshooting Fli command availability and common usage mistakes.
apitap
ApiTap gives AI agents cheap access to web data through three layers.
pipefy-api-fallback
Use this skill when a toolkit operation fails AND the introspection skill could not resolve the problem. This is the last-resort fallback (Tier 3): call the Pipefy GraphQL API directly using curl or httpx, authenticating with the Service Account (OAuth2) or a Personal Access Token (PAT) available as env var. Follow…
gitlab-merge-request-review
Review and merge GitLab merge requests via the gitlab-api MCP server — by default the MRs assigned to you or where you are a reviewer, optionally scoped to a project, group, or the whole instance. Read an MR, gate it on a green pipeline (pipeline → jobs → job log), then approve, accept/merge, or set…
gitlab-api-development
Develop, test, gate, and release the GitLab REST and GraphQL connector. Use this skill when changing API mappings, governed MCP tools, authentication, tenant selection, KG ingestion, packaged content, or repository gates.
gitlab-pipelines
CI/CD pipeline review on GitLab via the gitlab-api MCP server — review pipeline results for a project, a group, or the whole instance, drill into the CI jobs of a pipeline, and read a job's log; also trigger a pipeline on a ref. Use when the agent must review CI results across a project/group/organization, check…