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 AgenticAIPlan/AgenticAISkills --skill wuhan-ai-dailygit clone --depth 1 https://github.com/AgenticAIPlan/AgenticAISkillsWrote 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/agenticaiplan/agenticaiskills/wuhan-ai-daily)<a href="https://agentmods.dev/skills/agenticaiplan/agenticaiskills/wuhan-ai-daily"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/wuhan-ai-daily/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/agenticaiplan/agenticaiskills/wuhan-ai-daily"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/wuhan-ai-daily.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 | $0.00078 | $0.01270 |
| Opus 5 | $0.00039 | $0.00635 |
| Sonnet 5 | $0.00016 | $0.00254 |
| Haiku 4.5 | $0.00008 | $0.00127 |
Grade A, and why
wuhan-ai-daily 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 12d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
武汉 AI 信息每日采集 SKILL
配置参数
使用前需在环境变量中配置以下参数（请勿将实际值提交至代码仓库）：
FEISHU_APP_TOKEN = <你的飞书多维表格 App Token>
FEISHU_TABLE_ID = <你的飞书多维表格 Table ID>
配置方式：在 claude_desktop_config.json 的 lark-mcp 启动参数中，或通过系统环境变量注入；也可在本地项目的 .env 文件中设置（.env 需加入 .gitignore）。
飞书写入通过 lark-mcp 工具完成，无需手动鉴权。
飞书表格字段结构
| 字段名 | 字段类型 | 说明 |
|---|---|---|
| 发布日期 | 日期 | Unix 毫秒时间戳，取内容发布当日 00:00:00 |
| 信息摘要 | 文本 | 100 字以内，用自己语言概括，不引用原文 |
| 信息源链接 | 文本 | 原始页面完整 URL |
| 类型 | 单选 | 政策 / 新闻 / 活动 / 其他 |
注意：表格第一列「时间」是系统自动生成的创建时间字段（带锁），无法写入，忽略即可。
执行流程
Step 1：构建搜索关键词
每次执行使用以下关键词矩阵，覆盖三类信息：
| 类型 | 关键词 |
|---|---|
| 政策 | 武汉 人工智能 政策 最新、武汉 AI 扶持 补贴 |
| 新闻 | 武汉 人工智能 最新动态、武汉 AI 产业 新闻 |
| 活动 | 武汉 人工智能 峰会 论坛、武汉 AI 活动 展会 |
| 大模型 | 武汉 大模型 最新 |
Step 2：执行全网搜索
- 调用
web_search执行各关键词组，每组取前 5 条 - 对标题模糊或摘要不足的条目，调用
web_fetch精读原文
Step 3：去重与相关性过滤
丢弃以下内容：
- 相关性不足：必须同时满足「武汉/湖北」+「人工智能/AI/大模型/智能化」两个维度
- 重复内容：URL 相同或标题高度相似，仅保留一条
Step 4：生成结构化字段
对每条通过过滤的内容，生成以下字段：
- 发布日期：从原文提取发布时间，转为 Unix 毫秒时间戳（当日 00:00:00 北京时间）；无法识别则用执行当日
- 信息摘要：100 字以内，用自己语言描述核心信息
- 信息源链接：原始页面完整 URL
- 类型：从「政策、新闻、活动」三选一；无法归类标「其他」
Step 5：写入飞书多维表格
调用 lark-mcp:bitable_v1_appTableRecord_create 逐条写入：
path:
app_token: $FEISHU_APP_TOKEN
table_id: $FEISHU_TABLE_ID
data.fields:
发布日期: <Unix毫秒时间戳>
信息摘要: "<100字以内摘要>"
信息源链接: "<完整URL>"
类型: "<政策|新闻|活动|其他>"
时间戳动态计算规则：
- Unix 毫秒时间戳 = 自 1970-01-01 00:00:00 UTC 起的毫秒数
- 北京时间（UTC+8）某日 00:00:00 的时间戳，可用以下方式动态计算：
- JavaScript：
new Date('YYYY-MM-DDT00:00:00+08:00').getTime() - Python：
int(datetime(YYYY, MM, DD, 0, 0, tzinfo=timezone(timedelta(hours=8))).timestamp() * 1000)
- JavaScript：
- 每天固定偏移 86,400,000 毫秒，禁止使用硬编码的静态年份查找表
Step 6：输出执行摘要
执行完成后输出：
本次采集完成 ✅
- 搜索关键词组：X 组
- 候选条目：X 条
- 过滤后写入：X 条
- 写入成功：X 条 / 失败：X 条
- 执行时间：YYYY-MM-DD
若写入条目为 0，输出告警：「今日未采集到相关信息，请人工核查」
异常处理
| 异常情况 | 处理方式 |
|---|---|
| lark-mcp 返回 91403 Forbidden | 检查多维表格是否已添加「claude助手」文档应用（路径：表格右上角「···」→「更多」→「添加文档应用」） |
| 字段写入失败 | 检查字段名是否与表格完全一致（区分全角/半角） |
| 单条写入失败 | 记录失败原因，继续写入其余条目，最终汇总报告 |
| 搜索无结果 | 尝试备用关键词，仍无结果则输出告警 |
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.
- 12d ago First seen · 117 lines · 78 tokens per session scan A fc5d9a065cdb
wuhan-ai-daily is a skill published in the GitHub repository AgenticAIPlan/AgenticAISkills (11 stars, last pushed 3mo ago), licensed MIT. It adds 78 tokens to every session and 1,270 once invoked, about $0.0004 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 2026-08-30.
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…