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 ernie-monitorgit 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/ernie-monitor)<a href="https://agentmods.dev/skills/agenticaiplan/agenticaiskills/ernie-monitor"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/ernie-monitor/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/ernie-monitor"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/ernie-monitor.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 | $0.00165 | $0.01669 |
| Opus 5 | $0.00082 | $0.00834 |
| Sonnet 5 | $0.00033 | $0.00334 |
| Haiku 4.5 | $0.00016 | $0.00167 |
Grade A, and why
ernie-monitor 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文心大模型全网监测 Skill
适用场景
当用户需要全面监测文心大模型及相关产品在全网的表现时使用本Skill，典型场景包括：
- 日常舆情监测与报告生成
- 产品发布后的用户反馈收集与分析
- 竞品动态追踪与对比分析
- KOL识别与用户分层管理
- 潜在风险预警与应对建议
监测范围
监测平台
| 平台类型 | 具体平台 | 监测内容 |
|---|---|---|
| 社交媒体 | 微博、小红书、抖音、视频号 | 帖子、短视频、动态 |
| 内容社区 | 微信公众号、知乎、B站 | 文章、视频、专栏 |
| 专业社区 | AI社区、开发者社区、行业论坛 | 技术讨论、项目分享 |
| 媒体资讯 | 新闻网站、科技媒体 | 报道、评论 |
监测主题
- 文心大模型核心产品（ERNIE、ERNIE Bot、文心一言等）
- 文心大模型能力（文生图、代码生成、多模态、Agent等）
- 文心大模型相关事件（发布、更新、合作、争议等）
- 友商模型动态（GPT、Claude、通义千问、讯飞星火等）
执行步骤
步骤1：确定监测范围
- 确认监测时间范围（默认近7天）
- 选择监测平台（可指定或全平台）
- 定义监测关键词（核心关键词、扩展关键词、友商关键词）
步骤2：内容收集与处理
-
使用各平台skill进行内容收集：
- 微信公众号：使用
wechat-article-to-markdown抓取文章 - 小红书：使用
xiaohongshuMCP服务搜索内容 - 微博/知乎/B站/抖音：使用
daily-hot-news获取热榜 - 媒体/论坛：使用
web-research进行调研 - AI社区：使用
arxiv-search搜索学术论文
- 微信公众号：使用
-
内容去重与分类：
- URL去重、标题相似度去重
- 按内容类型分类（产品发布、用户体验、技术分析等）
步骤3：评论情感分析
- 情感分类：正向、负向、中性、混合
- 观点提炼：提取核心观点、争议点、风险点
- 情感趋势分析：对比历史数据
步骤4：KOL挖掘与用户识别
- 按互动量和影响力筛选潜在KOL
- 用户标签化：身份标签、态度标签、价值标签
- 分层管理：S级（顶级KOL）、A级（核心KOL）、B级（潜力KOL）、C级（友好用户）
步骤5：友商监测
- 监测重点友商动态
- 重点方向对比：Agent能力、代码能力、多模态、世界模型
- 风险预警：友商重大进展提醒
步骤6：生成报告
输出结构化监测报告，包含：
- 监测总览
- 重点内容列表
- 评论情感分析总结
- 友商模型进展
- 舆情风险预警
- 潜在KOL/友好者名单
- 运营建议
输入要求
- 监测对象：ernie-image、ernie-image-turbo、文心一言等具体产品名称
- 时间范围：起止日期或周期（day/week/month）
- 监测平台：可选，不指定则全平台监测
- 重点关注：可选，如特定话题、风险预警等
输出要求
必须输出
- 监测总览：渠道分布、内容类别分布、情感倾向分布
- 重点内容列表：高热度内容、高争议内容、高价值内容
- 评论情感分析：正向/负向评价举例、主要观点提炼
- 潜在KOL名单：分层列表及标签
可选输出
- 友商模型进展对比
- 舆情风险预警
- 运营建议
输出格式
- 使用Markdown格式
- 包含数据表格
- 明确指出风险等级和行动建议
集成Skill
本Skill依赖以下辅助Skills：
| Skill | 用途 |
|---|---|
wechat-article-to-markdown |
微信公众号文章抓取 |
xiaohongshu |
小红书内容搜索与互动 |
daily-hot-news |
微博/知乎/B站/抖音热榜查询 |
web-research |
媒体/资讯/论坛调研 |
arxiv-search |
AI社区学术论文搜索 |
chrome-devtools |
无API平台内容抓取 |
playwright-mcp |
浏览器自动化测试 |
参考资料目录结构
skills/ernie-monitor/
├── SKILL.md # 本文件
├── scripts/
│ └── ernie_monitor.py # 监测脚本
├── references/
│ ├── monitoring_guide.md # 详细监测指南
│ ├── kol_framework.md # KOL评估框架
│ ├── sentiment_analysis.md # 情感分析方法
│ └── risk_assessment.md # 风险评估标准
├── assets/
│ └── templates/
│ └── report_template.md # 报告模板
What ships with it
6 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 · 161 lines · 165 tokens per session scan A 8d416658bdc5
ernie-monitor is a skill published in the GitHub repository AgenticAIPlan/AgenticAISkills (11 stars, last pushed 3mo ago), licensed MIT. It adds 165 tokens to every session and 1,669 once invoked, about $0.0008 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…