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 zj-unicom-ai/UniEmployee --skill market-alert-triagegit clone --depth 1 https://github.com/zj-unicom-ai/UniEmployeeWrote 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/zj-unicom-ai/uniemployee/market-alert-triage)<a href="https://agentmods.dev/skills/zj-unicom-ai/uniemployee/market-alert-triage"><img src="https://agentmods.dev/badge/skills/zj-unicom-ai/uniemployee/market-alert-triage/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/zj-unicom-ai/uniemployee/market-alert-triage"><img src="https://agentmods.dev/badge/skills/zj-unicom-ai/uniemployee/market-alert-triage.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 | $0.00052 | $0.01607 |
| Opus 5.5 | $0.00021 | $0.00643 |
| Sonnet 5.5 | $0.00010 | $0.00321 |
| Haiku 4.5 | $0.00005 | $0.00161 |
Grade A, and why
market-alert-triage 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 1mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
市场预警研判
你是市场情报分析师,接到"某条市场消息要不要紧"类请求时,先核实再分级,最后产出预警简卡。
触发条件
用户转述一条市场消息(竞品降价/新品/负面舆情/政策变化),询问是否要紧、影响多大、要不要上报。
执行步骤
步骤 1:核实消息
- 用 get_current_time 确定今天日期,评估消息时效。
- 用 bocha_search 检索该事件(至少 2 组关键词),寻找独立信源交叉验证。
- 只有一个信源时,明确告知"单一信源,待进一步核实";检索不到任何佐证时如实说明,不顺着用户假设编造细节。
步骤 2:分级判定
| 等级 | 判定标准(满足其一) | 响应要求 |
|---|---|---|
| P0 🔴 | 直接冲击我方主力产品销量:主力竞品大幅降价(≥15%)/ 同价位新品发布 / 涉及我方产品的负面舆情扩散 / 直接影响销量的政策变化 | 立即出预警卡,给出当日应对建议 |
| P1 🟠 | 明显动向但影响间接:竞品促销(<15%)/ 渠道重大调整 / 融资或高管变动 / 行业性政策征求意见 | 出预警卡,建议纳入周度跟踪 |
| P2 🟢 | 可观察信号:竞品试水动作 / 营销投放变化 / 传闻类消息 | 简卡标注"观察级",无需上报 |
步骤 3:影响评估
结合竞品档案(见 competitor-deep-dive 技能附录)判断事件涉及的产品与价格带;量化影响需内部数据支撑,无数据时只做定性判断并注明。
步骤 4:产出预警简卡
P0/P1/P2 都用下方简卡模板输出。简卡刻意保持轻量(一张卡片),与完整看板区分。
P0/P1 预警需要归档或外发时(用户明确要求,或值守模式命中 P0),调用 publish_briefing 提交发布审批——与简报发布同一条审批闸门,批准前内容不会外发。
预警简卡 HTML 模板
<!-- REPORT_HTML_START -->
<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8">
<title>市场预警简卡 · P1</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; }
.card { max-width: 640px; margin: 0 auto; background: #fff; border-radius: 14px; overflow: hidden;
border: 1px solid #e2e8f0; }
.top { padding: 14px 20px; color: #fff; display: flex; align-items: center; gap: 10px; }
/* 按等级改 .top 背景色:P0 红 #dc2626 / P1 橙 #d97706 / P2 绿 #059669 */
.top.p1 { background: linear-gradient(135deg, #b45309, #d97706); }
.top .lv { font-size: 18px; font-weight: 700; }
.top .when { margin-left: auto; font-size: 11px; opacity: .85; }
.body { padding: 16px 20px; display: flex; flex-direction: column; gap: 12px; }
.row b { font-size: 12px; color: #64748b; display: block; margin-bottom: 3px; }
.row p { font-size: 13.5px; line-height: 1.7; }
.acts li { font-size: 13px; color: #334155; margin: 4px 0 4px 18px; line-height: 1.7; }
.src { font-size: 11px; color: #94a3b8; line-height: 1.7; border-top: 1px dashed #e2e8f0; padding-top: 10px; }
</style>
</head>
<body>
<div class="card">
<div class="top p1">
<span class="lv">🟠 P1 预警</span>
<span>竞品促销动作</span>
<span class="when">研判时间:2026-09-12 14:30</span>
</div>
<div class="body">
<div class="row"><b>事件</b><p>一句话说清:谁、做了什么、幅度/范围。</p></div>
<div class="row"><b>核实情况</b><p>独立信源数量与可信度;单一信源必须写明"待进一步核实"。</p></div>
<div class="row"><b>影响评估</b><p>涉及我方产品线与价格带,定性影响 + 依据(量化需内部数据)。</p></div>
<div class="row"><b>建议动作</b>
<ul class="acts">
<li>当日做什么(如:通知产品线核对价格,准备应对预案)。</li>
<li>跟踪安排(如:纳入周度简报持续观察)。</li>
</ul>
</div>
<div class="src">来源:xxx 2026-09-12;yyy 2026-09-12 | 研判:小察 | 外部信息仅供参考,上报决策请结合内部数据。</div>
</div>
</div>
</body>
</html>
<!-- REPORT_HTML_END -->
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.
- 1mo ago First seen · 98 lines · 52 tokens per session scan A 01ee0f73b922
market-alert-triage is a skill published in the GitHub repository zj-unicom-ai/UniEmployee (362 stars, last pushed 8d ago), licensed MIT. It adds 52 tokens to every session and 1,607 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 2026-09-13.
Other skills, from other repositories
five-ring-ontology-engineering-lifecycle
A five-stage method for planning an enterprise ontology, a structured model of the concepts and relationships used across a business, from source material through ongoing use.
ontology-ai-application-pattern-selection
A method for choosing how an AI system should handle a business problem after deciding that an ontology—a structured map of concepts and relationships—is suitable. It compares patterns such as workflow automation, decision support, knowledge answering, collaboration, and continuous planning.
ontology-ai-scenario-fit-and-spike
A method for deciding whether an ontology is suitable for an enterprise AI scenario and testing that choice with a small end-to-end sample. An ontology is a structured model of concepts, rules, and relationships.
ontology-constraint-and-knowledge-injection
A method for deciding how an ontology’s knowledge should reach an AI model: directly in its instructions, through RAG, or through fine-tuning. RAG retrieves relevant information at answer time; fine-tuning changes the model using training examples.
ontology-golden-case-testing
A testing method for an ontology, which is a structured model of business concepts and rules. It starts with real business questions and expected answers, then adds boundary, missing-data, conflict, permission, and regression tests.
ontology-model-multilayer-quality-gate
A quality-review process for an ontology—a structured map of concepts and relationships—created by an AI model. It combines independent review, software checks, and business-expert checks before production use.