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 chengkj99/kj-skills --skill ai-daily-websearchgit clone --depth 1 https://github.com/chengkj99/kj-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/chengkj99/kj-skills/ai-daily-websearch)<a href="https://agentmods.dev/skills/chengkj99/kj-skills/ai-daily-websearch"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/ai-daily-websearch/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/chengkj99/kj-skills/ai-daily-websearch"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/ai-daily-websearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00147 | $0.01578 |
| Opus 5 | $0.00073 | $0.00789 |
| Sonnet 5 | $0.00029 | $0.00316 |
| Haiku 4.5 | $0.00015 | $0.00158 |
Grade A, and why
ai-daily-websearch 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 前沿日报技能（ai-daily-websearch）
实现细节：references/scoring-rubric.md
输出格式规范：references/compose-format.md
部署集成说明：references/deployment.md
目标
把「今日值得程序员关注的 AI 动态」压缩为可执行、可复盘、可分享的一页中文日报，自动写入网站，最大化信噪比，零模板空话。
技能执行总则
激活本技能后，默认交付物：
| 产物 | 说明 |
|---|---|
content/daily/YYYY-MM-DD.md |
完整可读日报，写入网站仓库 |
| 网站数据更新 | 自动调用 update-daily-digest.mjs |
| 部署提示 | 告知一条命令完成网站上线 |
| 用户意图 | 你要做的 |
|---|---|
| 「出日报」「AI 日报」（未限定） | 阶段 1（采集）→ 阶段 2（定稿）→ 阶段 3（写入+更新） |
| 「根据已有内容写日报」「定稿」 | 仅阶段 2+3（前提：已有原始内容） |
| 「只采集」「给我今日 AI 原始信息」 | 仅阶段 1，明确告知用户这是草稿 |
执行流程
阶段 1：信息采集（5-8 次 WebSearch）
搜索过去 24 小时内的最新动态，覆盖以下维度：
| 搜索方向 | 示例关键词 |
|---|---|
| 机构公告 | "OpenAI announcement today", "Anthropic news today" |
| 模型/产品 | "new AI model released today", "LLM release [month year]" |
| 工具更新 | "Claude update", "Gemini update", "ChatGPT update today" |
| 大 V 动态 | "Karpathy twitter today", "Ethan Mollick post today" |
| 研究突破 | "AI research paper today", "DeepMind announcement" |
| 行业新闻 | "AI funding news", "AI company news today" |
重点追踪来源：
- 机构：OpenAI / Anthropic / Google DeepMind / Meta AI / Mistral / xAI / Hugging Face
- 大 V：@karpathy @ylecun @emollick @demishassabis @drjimfan @rohanpaul_ai
阶段 2：价值评分与筛选（内化于判断）
按 references/scoring-rubric.md 评分，分级：
- 🔥 P0（头条）：重大发布/突破，建议当天行动
- 📦 P1（重要）：产品/工具/模型更新，本周评估
- 📌 P2（简讯）：趋势性信息，简要记录
去重：同一事件只保留最高质量一条（优先官方来源）。
阶段 3：生成定稿
按 references/compose-format.md 格式输出。
质量门禁（交付前自检）：
- 不编造 URL、发布时间、数字、账号
- 无「补充性动态，可作为趋势参考」等空话
- 无「加入日报追踪，等待更多上下文」
- 每条「建议下一步」具体可执行（不写「持续关注」）
- 同一事件只出现一次
阶段 4：写入项目并更新网站数据
适用于集成了
ai-daily-websearch管线的项目（见references/deployment.md）。
- 版本化检测：写入前用 Bash 检查
YYYY-MM-DD.md是否已存在：- 不存在 → 直接写入
YYYY-MM-DD.md - 已存在 → 依次尝试
YYYY-MM-DD-2.md、YYYY-MM-DD-3.md……直到找到空槽，写入该版本文件，并在回复中注明「今日第 N 篇」
- 不存在 → 直接写入
- Write 工具：保存日报到确定的路径（
<APP_DIR>/content/daily/<文件名>） - Bash 工具：执行数据更新（全量扫描模式，更健壮）：
APP_DIR="<项目根目录>" node "$APP_DIR/scripts/update-daily-digest.mjs" - 一键部署：
该命令已内置完整流程（cd <APP_DIR> && pnpm daily:deployscripts/daily-deploy.sh）：- Step 1：全量扫描
content/daily/更新网站数据 - Step 2：
git add今日 md + generated.js →git commit→git push origin main - Step 3：
vite build生产包 - Step 4：
rsync上传阿里云 ECS - Step 5：微信发布（默认跳过）
- Step 1：全量扫描
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.
- 12d ago First seen · 125 lines · 147 tokens per session scan A 07afa0a503e8
ai-daily-websearch is a skill published in the GitHub repository chengkj99/kj-skills (14 stars, last pushed 11d ago), licensed MIT. It adds 147 tokens to every session and 1,578 once invoked, about $0.0007 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…