Agent skill

Market Daily Brief

by zj-unicom-ai in zj-unicom-ai/UniEmployee

市场情报每日简报技能。当用户需要市场简报/早报/日报/周报/行业动态汇总,或问"最近有什么值得关注的"时使用。产出 HTML 在线看板。

MITAuto-check passed

Install Market Daily Brief

skills CLI
$ npx skills add zj-unicom-ai/UniEmployee --skill market-daily-brief -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install zj-unicom-ai/UniEmployee market-daily-brief --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/zj-unicom-ai/UniEmployee.git skills-src && mkdir -p .claude/skills && cp -r skills-src/backend/skills/market-daily-brief .claude/skills/market-daily-brief && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
market-daily-brief
GitHub stars
360
Token cost
~1.6k tokens
SKILL.md length
97 words
Files
1
Skills in repo
22
Repo updated
First seen
Licence
MIT

At a glance

市场情报每日简报技能。当用户需要市场简报/早报/日报/周报/行业动态汇总,或问"最近有什么值得关注的"时使用。产出 HTML 在线看板。

  • Works in 2 steps: 委派 intel-scouter… → 如配置了竞品档案知识库,先用 kb_search 调档案,再联网补最新动态。
  • SKILL.md covers 触发条件, 值守模式(无人值守场景), 执行步骤 and 看板 HTML 模板, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Market Daily Brief is an agent skill from zj-unicom-ai/UniEmployee. 市场情报每日简报技能。当用户需要市场简报/早报/日报/周报/行业动态汇总,或问"最近有什么值得关注的"时使用。产出 HTML 在线看板。

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 面向企业的数字员工构建与运行平台:把专业员工的经验、流程与判断标准,固化为可随时上岗、可配置、可审批、可观测的 AI 数字员工。 The licence is MIT.

Example prompts

  • “最近有什么值得关注的”
  • “/market-daily-brief”

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. 委派 intel-scouter 子代理执行定向搜索(不委派时自己搜),覆盖四组关键词,每组 1-2 次检索
  2. 如配置了竞品档案知识库,先用 kb_search 调档案,再联网补最新动态。

What it can do on your machine

Read from SKILL.md and the folder at commit c38a00a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are html).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Market Daily Brief loads about 1.6k tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 97 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~22
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from zj-unicom-ai/UniEmployee at commit c38a00a, republished under its MIT licence (© zj-unicom-ai). 97 words, ~1,567 tokens.

Download SKILL.mdSave it as .claude/skills/market-daily-brief/SKILL.md (or your agent's skills folder).
name
market-daily-brief
description
市场情报每日简报技能。当用户需要市场简报/早报/日报/周报/行业动态汇总,或问"最近有什么值得关注的"时使用。产出 HTML 在线看板。

市场情报每日简报

你是市场情报分析师,接到简报类请求时执行以下流程,最终产出一份 HTML 在线看板。

触发条件

用户要市场简报/早报/日报/周报/行业动态汇总;或问"今天/最近有什么值得关注的行业动态";或自动化值守任务触发(提示词带【自动化值守】标记的简报指令)。

值守模式(无人值守场景)

提示词带【自动化值守】标记时没有用户可交互:

  • 直接按默认监测范围执行全量采集,不要反问澄清(没有谁会回答);
  • 某数据源不可用时跳过并在看板"来源汇总"注明,不阻塞流程;
  • 简报完成后必须调用 publish_briefing 提交发布审批,这是值守简报的收尾动作——发布需人工批准,批准前内容不会外发。

执行步骤

步骤 1:确定日期与期号

用 get_current_time 获取今天日期,简报期号与所有时效判断以此为准。

步骤 2:多源采集
  1. 委派 intel-scouter 子代理执行定向搜索(不委派时自己搜),覆盖四组关键词,每组 1-2 次检索:
    • 行业大盘:「智能硬件 行业 动态 2026」「消费电子 市场趋势」
    • 竞品动作:「声湃科技 新品/降价」「光屿智能」「极映科技」等竞品名 + 动态词
    • 政策法规:「智能硬件/消费电子 政策 补贴 认证」
    • 突发热点:newsnow 连接器拉取各平台热榜,筛出与行业相关的条目
  2. 如配置了竞品档案知识库,先用 kb_search 调档案,再联网补最新动态。
步骤 3:筛选与核实
  • 去重:同一事件多源报道合并为一条,来源取最早/最权威。
  • 剔除:与行业无关的热点、超过 30 天的旧闻(若确需保留,标注"历史信息")。
  • 评估:每条按「高/中/低」标注对我司业务的影响等级。
  • 拿不准真伪的消息不进看板正文,可在"建议关注"里提示待核实。
步骤 4:按模板产出看板

严格按下方 HTML 模板填充,字段不够时该区块输出"本期无"而不是删除区块。

步骤 5:提交发布审批
  • 交互会话:把看板作为消息文本输出(按下方分隔符规范)后,询问用户是否需要归档发布;用户确认后调用 publish_briefing(title=简报标题,content_html=完整看板 HTML,不含分隔符标记本身)。
  • 值守模式:直接调用 publish_briefing,然后把审批状态告知性输出(markdown 导读里注明"已提交发布审批")。
  • publish_briefing 会挂起等待人工审批:批准后简报归档为 HTML 文件并按配置外发;被拒绝时向用户说明"发布已取消,看板仍保留在对话中"。

看板 HTML 模板

用 <!-- REPORT_HTML_START --> 和 <!-- REPORT_HTML_END --> 独占行包裹以下完整 HTML 后作为消息文本输出。纯 CSS 实现,不引入任何外部 JS/图表库(简报以信息卡片为主,不需要图表库)。

html
<!-- REPORT_HTML_START -->
<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8">
<title>市场情报每日简报 · 2026-09-12</title>
<style>
  * { margin: 0; padding: 0; box-sizing: border-box; }
  body { font-family: -apple-system, "PingFang SC", "Microsoft YaHei", sans-serif;
         background: #f1f5f9; color: #0f172a; padding: 20px; }
  .board { max-width: 960px; margin: 0 auto; display: flex; flex-direction: column; gap: 14px; }
  /* 头部 */
  .head { background: linear-gradient(135deg, #1e3a8a, #3b82f6); color: #fff;
          border-radius: 14px; padding: 18px 22px; }
  .head h1 { font-size: 20px; margin-bottom: 6px; }
  .head .meta { font-size: 12px; opacity: .85; display: flex; gap: 14px; flex-wrap: wrap; }
  .badge { background: rgba(255,255,255,.18); border-radius: 10px; padding: 1px 9px; font-size: 11px; }
  /* 预警横幅(本期有 P0/P1 预警才保留此区块) */
  .alert { background: #fef2f2; border: 1px solid #fecaca; border-left: 4px solid #dc2626;
           border-radius: 10px; padding: 10px 14px; font-size: 13px; color: #991b1b; }
  .alert.orange { background: #fffbeb; border-color: #fcd34d; border-left-color: #d97706; color: #92400e; }
  /* 区块卡片 */
  .sec { background: #fff; border-radius: 14px; padding: 16px 20px; }
  .sec h2 { font-size: 15px; margin-bottom: 10px; display: flex; align-items: center; gap: 8px; }
  .sec h2 .cnt { font-size: 11px; color: #94a3b8; font-weight: 400; }
  /* 头条列表 */
  .news-item { padding: 9px 0; border-top: 1px dashed #e2e8f0; }
  .news-item:first-of-type { border-top: 0; }
  .news-title { font-size: 14px; font-weight: 600; }
  .news-sum { font-size: 12.5px; color: #475569; margin-top: 3px; line-height: 1.6; }
  /* 标签 */
  .tag { display: inline-block; border-radius: 8px; padding: 0 7px; font-size: 11px; margin-right: 6px; vertical-align: 1px; }
  .tag.src { background: #f1f5f9; color: #64748b; }
  .tag.high { background: #fee2e2; color: #b91c1c; }
  .tag.mid  { background: #fef3c7; color: #b45309; }
  .tag.low  { background: #ecfdf5; color: #047857; }
  /* 竞品动态卡片墙 */
  .cards { display: grid; grid-template-columns: repeat(auto-fill, minmax(270px, 1fr)); gap: 10px; }
  .card { border: 1px solid #e2e8f0; border-radius: 10px; padding: 11px 13px; }
  .card .co { font-weight: 700; font-size: 13px; }
  .card .ev { border-radius: 8px; padding: 0 7px; font-size: 11px; margin-left: 6px; }
  .ev.price { background: #fee2e2; color: #b91c1c; }
  .ev.launch { background: #dbeafe; color: #1d4ed8; }
  .ev.channel { background: #fef3c7; color: #b45309; }
  .ev.funding { background: #ede9fe; color: #6d28d9; }
  .card p { font-size: 12.5px; color: #475569; margin-top: 5px; line-height: 1.6; }
  .card .foot { font-size: 11px; color: #94a3b8; margin-top: 6px; }
  /* 政策/建议列表 */
  .plain li { font-size: 13px; color: #334155; margin: 6px 0 6px 18px; line-height: 1.6; }
  /* 尾部 */
  .foot-note { font-size: 11px; color: #94a3b8; line-height: 1.7; }
</style>
</head>
<body>
<div class="board">
  <div class="head">
    <h1>📊 市场情报每日简报</h1>
    <div class="meta">
      <span>期号:2026-09-12(第 XX 期)</span>
      <span>生成时间:YYYY-MM-DD HH:MM</span>
      <span><span class="badge">newsnow</span><span class="badge">bocha_search</span><span class="badge">竞品档案</span></span>
    </div>
  </div>

  <!-- 本期命中预警时保留,否则删除本区块 -->
  <div class="alert">🚨 P0预警|声湃科技官宣 Mini3 直降 100 元(399→299),正面冲击我司 X1 价格带,建议今日内评估应对。来源:xxx 2026-09-12</div>

  <div class="sec">
    <h2>📌 今日头条 <span class="cnt">3-5 条,按影响排序</span></h2>
    <div class="news-item">
      <div class="news-title"><span class="tag high">高影响</span>头条标题一句话</div>
      <div class="news-sum">两句话摘要:事件 + 对我司的潜在影响。<span class="tag src">来源站点 · 2026-09-11</span></div>
    </div>
    <!-- 更多头条按同样结构复制 -->
  </div>

  <div class="sec">
    <h2>🏢 竞品动态 <span class="cnt">事件类型标签:价格/新品/渠道/融资</span></h2>
    <div class="cards">
      <div class="card">
        <div class="co">声湃科技<span class="ev price">价格</span></div>
        <p>动态一句话描述(做了什么、幅度多大)。</p>
        <div class="foot">影响:高|来源:xxx · 2026-09-12</div>
      </div>
      <!-- 更多竞品卡按同样结构复制 -->
    </div>
  </div>

  <div class="sec">
    <h2>🏛 政策法规</h2>
    <ul class="plain">
      <li>政策一句话 + 对业务的影响判断。<span class="tag src">来源 · 日期</span></li>
    </ul>
  </div>

  <div class="sec">
    <h2>💡 今日建议关注</h2>
    <ul class="plain">
      <li><b>建议动作:</b>面向业务方的 1-3 条可执行建议(每条注明依据哪条情报)。</li>
      <li><b>待核实:</b>拿不准真伪的线索放这里,注明核实建议。</li>
    </ul>
  </div>

  <div class="sec">
    <h2>📎 来源汇总</h2>
    <div class="foot-note">本期共采集 N 条信息,采用 M 条。数据来源:newsnow 热点聚合、bocha_search 联网检索、竞品档案库。所有外部信息仅供参考,重大决策请与内部经营数据交叉验证。</div>
  </div>
</div>
</body>
</html>
<!-- REPORT_HTML_END -->

约束

  • 看板 HTML 只填数据、不改动模板的 CSS 类名与结构;某区块无内容时保留区块并写"本期无"。
  • 头条/竞品卡里的每条信息都必须带来源与日期标签,缺失来源的条目不得进入看板。
  • 分隔符外的 markdown 只写 2-3 行导读(本期要点 + 预警提示),不要重复看板全文。
  • 禁止把 HTML 写入磁盘(write_file/execute),禁止谎称"已保存到文件"。

© zj-unicom-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in backend/skills/market-daily-brief of zj-unicom-ai/UniEmployee.

Open the folder on GitHubat commit c38a00a

Compare with similar skills

Market Daily Brief next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Market Daily Brief compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Market Daily Brief this skillzj-unicom-ai/UniEmployee360—~1.6kAutomated safety check: PassMIT
Daily Briefamd/gaia1.6k—~680Automated safety check: PassMIT
Daily Briefhuytieu/COG-second-brain1.3k—~4.1kAutomated safety check: PassMIT
Daily Briefleiting-eric/DailyBrief367—~3kAutomated safety check: NotesMIT
Briefalirezarezvani/claude-skills28k—~967Automated safety check: PassMIT
Daily Briefingvellum-ai/vellum-assistant1.4k—~806Automated safety check: PassMIT

Similar skills

  • Daily Brief

    amd/gaia

    Compose a short briefing from several sources at once — headlines, tracked topics, and the user's own open items — as one digest instead of separate answers.

    1.6k GitHub stars~680 tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Daily Brief

    huytieu/COG-second-brain

    Generate personalized news intelligence with verified sources (7-day freshness requirement)

    1.3k GitHub stars~4.1k tokensUpdated 9 days ago
    Auto-check passed
  • Daily Brief

    leiting-eric/DailyBrief

    Operational knowledge for the daily-brief digest pipeline (this project).

    367 GitHub stars~3k tokensUpdated yesterday
    Productivity & AutomationAuto-check: notes
  • Brief

    alirezarezvani/claude-skills

    /cs:brief <topic — Generate a one-page strategy brief from an office-hours intake.

    28k GitHub stars~967 tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed
  • Daily Briefing

    vellum-ai/vellum-assistant

    Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to…

    1.4k GitHub stars~806 tokensUpdated 2 days ago
    Productivity & AutomationAuto-check passed
  • Daily

    sickn33/agentic-awesome-skills

    Documentation and capabilities reference for Daily. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 3 repos~3.6k tokens
    AI & LLM EngineeringAuto-check passed

More from zj-unicom-ai/UniEmployee

All 22 skills in this repo
  • Enterprise Customer Visit Playbook

    zj-unicom-ai/UniEmployee

    Prepares account managers for visits to government and enterprise customers: looks up the customer file, matches products, builds a Word solution document and files visit minutes.

    360 GitHub stars~458 tokensUpdated 3 days ago
    Auto-check passed
  • Tencent ima Knowledge Base Reader

    zj-unicom-ai/UniEmployee

    Exports the article list and original article text from a Tencent ima knowledge base through a logged-in Chrome session, using browser automation.

    360 GitHub stars~1k tokensUpdated 3 days ago
    Auto-check passed
  • Business Overview Analysis

    zj-unicom-ai/UniEmployee

    Produces a full business health analysis from sales, finance, inventory and customer CSV files: core KPIs, monthly trends, drill-downs and recommendations.

    360 GitHub stars~662 tokensUpdated 3 days ago
    Auto-check passed
  • Competitor Deep-Dive Dashboard

    zj-unicom-ai/UniEmployee

    Produces a competitor benchmarking dashboard as an HTML page with an ECharts price comparison, from built-in profile cards plus fresh web research.

    360 GitHub stars~1.7k tokensUpdated 3 days ago
    Auto-check passed
  • Insurance Operations Analysis

    zj-unicom-ai/UniEmployee

    Analyzes insurance operating data such as premium, loss ratio, renewal rate and expense ratio by branch, product and channel, flags anomalies and builds an HTML dashboard.

    360 GitHub stars~646 tokensUpdated 3 days ago
    Auto-check passed
  • Market Alert Triage

    zj-unicom-ai/UniEmployee

    Assesses a reported market event such as a competitor price cut, new launch or negative press, verifies it, grades urgency from P0 to P2 and produces a short alert card.

    360 GitHub stars~778 tokensUpdated 3 days ago
    Auto-check passed

Questions about Market Daily Brief

What does Market Daily Brief do?

市场情报每日简报技能。当用户需要市场简报/早报/日报/周报/行业动态汇总,或问"最近有什么值得关注的"时使用。产出 HTML 在线看板。. Market Daily Brief is an agent skill from zj-unicom-ai/UniEmployee.

How do I install Market Daily Brief in Claude Code?

Run `npx skills add zj-unicom-ai/UniEmployee --skill market-daily-brief -a claude-code`. Or copy the skill folder (backend/skills/market-daily-brief in zj-unicom-ai/UniEmployee) into .claude/skills/market-daily-brief in your project. Claude Code loads it when a task matches its description.

How do I install Market Daily Brief in Codex?

Run `npx skills add zj-unicom-ai/UniEmployee --skill market-daily-brief -a codex`. Or copy the skill folder (backend/skills/market-daily-brief in zj-unicom-ai/UniEmployee) into .agents/skills/market-daily-brief in your project. Codex loads it when a task matches its description.

Can I use Market Daily Brief in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zj-unicom-ai/UniEmployee --skill market-daily-brief -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/market-daily-brief, .gemini/skills/market-daily-brief, .github/skills/market-daily-brief and .opencode/skills/market-daily-brief in your project.

What does Market Daily Brief need to run?

SKILL.md names no scripts, command-line tools or credentials: Market Daily Brief is instructions for the agent only.

Does Market Daily Brief access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Market Daily Brief safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Market Daily Brief use?

Market Daily Brief is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Market Daily Brief use?

About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Market Daily Brief?

Skills that share tags, products or a category with Market Daily Brief: Daily Brief (amd/gaia, 1.6k stars), Daily Brief (huytieu/COG-second-brain, 1.3k stars), Daily Brief (leiting-eric/DailyBrief, 367 stars) and Brief (alirezarezvani/claude-skills, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Market Daily Brief?

zj-unicom-ai (a GitHub organization) maintains it in zj-unicom-ai/UniEmployee, which has 360 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 8, 2026.

Source: zj-unicom-ai/UniEmployee on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.