Agentbay Monitor Skills
舆情监控技能,最终产出舆情报告。当用户问「某事件/话题舆情如何」「舆论怎么样」「做舆情分析」「运行舆情分析」或按关键词/平台爬取并生成舆情报告时,使用本技能。约定:凡舆情相关意图即执行全流程(爬取→情感分析→生成报告)。爬取由本技能完成;情感分析由主 Agent 按提示词自主判断;报告由 generate_report 生成。
Install
npx skills add agentbay-ai/agentbay-skills --skill agentbay-monitor-skillsgit clone --depth 1 https://github.com/agentbay-ai/agentbay-skills.git /tmp/agentbay-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agentbay-skills/agentbay-monitor-skills ~/.claude/skills/agentbay-monitor-skillsPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# AgentBay 舆情监控 Skill ## ⚠️ 舆情分析 = 全流程(必读) **用户说「运行舆情分析」「做舆情分析」「舆情分析 主题是 XXX」时,必须执行完整三步,不能只跑爬取就结束。** | 步骤 | 动作 | 说明 | |------|------|------| | 1. 爬取 | `crawl.py` 或 `crawl_for_sentiment(...)` | 得到 `raw_output_path`(爬取结果 JSON) | | 2. 情感分析 | 读 `scripts/sentiment/sentiment_instruction.md` → 对爬取 JSON 逐条判定 → 写情感结果小 JSON → 运行 `write_processed.py` | 得到 processed JSON(如 `output/processed.json`) | | 3. 生成报告 | `report.py --input <processed 路径>` 或 `generate_report(...)` | 得到 Markdown/JSON(及可选 PDF) | **禁止行为**:只运行 `crawl.py` 后就说「爬取完成,情感分析由主 Agent 完成」并结束。这是错误用法——主 Agent 就是你自己,你必须继续完成步骤 2 和 3,直到产出最终报告文件。 ## 何时使用 用户出现以下任一意图时,**必须**使用本技能并执行全流程(爬取→情感分析→生成报告): - 问「**某事件/话题舆情如何**」「XX 舆论怎么样」「想了解 XX 的舆情」 - 「运行舆情分析」「做舆情分析」「舆情分析 主题是 XXX」 - 舆情监控、情感分析、舆情报告、按关键词/平台爬取并生成报告(中英文场景均可) **意图为舆情相关即默认使用本技能**,不可仅用联网搜索代替。 **重要约定**:凡提到「舆情分析」(或「运行舆情分析」「做舆情分析」等等价表述),即视为执行**全流程**——爬取 → 情感分析 → 生成报告。必须按该完整流程执行,不可只做爬取;最终产出须包含 Markdown/JSON(及可选 PDF)报告。 ## 前置条件 工作目录为技能目录(本 SKILL 所在目录);已安装依赖;已配置 `AGENTBAY_API_KEY`。 ## 依赖 ```bash pip install wuying-agentbay-sdk pandas numpy pyyaml markdown ``` 可选(PDF 报告):`brew install cairo pango gdk-pixbuf` 后 `pip install weasyprint`。不装则仅无 PDF,.md/.json 正常。 ## API Key 仅需配置 `AGENTBAY_API_KEY`。环境变量:`export AGENTBAY_API_KEY=你的key`(Windows PowerShell:`$env:AGENTBAY_API_KEY="你的key"`)。或直接写文件:`mkdir -p ~/.config/agentbay && echo -n '你的key' > ~/.config/agentbay/api_key`。获取:https://agentbay.console.aliyun.com/service-management 。未配置时运行脚本会报错。其余参数由主 Agent 传参/命令行传入。 ## 整体流程
Details
- Skill name
agentbay-monitor-skills- Repository
- agentbay-ai/agentbay-skills
- Path
agentbay-monitor-skills/SKILL.md- Repo updated
- 12 February 2026
- Listed in
- BehiSecc/awesome-claude-skills
FAQ
What does the Agentbay Monitor Skills skill do?
舆情监控技能,最终产出舆情报告。当用户问「某事件/话题舆情如何」「舆论怎么样」「做舆情分析」「运行舆情分析」或按关键词/平台爬取并生成舆情报告时,使用本技能。约定:凡舆情相关意图即执行全流程(爬取→情感分析→生成报告)。爬取由本技能完成;情感分析由主 Agent 按提示词自主判断;报告由 generate_report 生成。
How do I install the Agentbay Monitor Skills skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add agentbay-ai/agentbay-skills --skill agentbay-monitor-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Agentbay Monitor Skills popular?
It lives in agentbay-ai/agentbay-skills, which has 51 GitHub stars and 5 forks, and is included in 1 curated skill list.
Related skills
Agentbay Aio Skills
51agentbay-ai/agentbay-skills
用于任何「运行/执行/评估代码」的请求(如 run this code、execute script、用 Python 画图、跑代码/画图/执行脚本)。通过 AgentBay SDK 创建 code_latest 沙箱,调用 run_code 执行并返回结果。支持 Python、JavaScript、R、Java。
Amap Traffic
51agentbay-ai/agentbay-skills
高德地图实时路况查询与最优自驾路线规划技能。基于高德交通态势API和路径规划API,提供实时拥堵信息和最快路线建议。
Boss Job Search
51agentbay-ai/agentbay-skills
查询Boss直聘职位信息。当用户想要搜索Boss直聘上的职位、筛选特定公司规模的岗位时使用此skill。
Alterlab AI Use Disclosure
87AlterLab-IEU/AlterLab-Academic-Skills
Helps faculty and researchers disclose generative-AI use and comply with the rules for manuscripts, grant proposals, peer review, theses and figures. Walks a venue → policy → placement decision tree over policies verified on 2026-09-23 (ICMJE, Springer Nature/Nature, Elsevier, Wiley, Taylor & Francis, Sage, IEEE, PLOS, arXiv; NIH NOT-OD-25-132 and NOT-OD-23-149, NSF, UKRI, ERC, TÜBİTAK; YÖK's 2024 ethics guide; EU AI Act Article 50), drafts English and Turkish statements, and ships scripts/disclosure_builder.py to emit a statement plus warnings where a policy forbids the use. Use when the requ
Alterlab Alphafold Db
87AlterLab-IEU/AlterLab-Academic-Skills
Access the AlphaFold DB of 240M+ AI-PREDICTED protein structures (v6, plus precomputed homodimer/heterodimer complexes) — retrieve models by UniProt accession, download PDB/mmCIF files, and analyze prediction confidence metrics (pLDDT, PAE). Use when a UniProt ID needs a computationally predicted 3D structure or when no experimental structure exists, for homology modeling, protein engineering, or structure-based drug discovery; for EXPERIMENTALLY determined structures (X-ray, cryo-EM, NMR) prefer alterlab-pdb, to fold a NEW sequence or complex yourself prefer alterlab-alphafold, and for protei
Olore Tensorzero Latest
119olorehq/olore
Local TensorZero documentation reference (latest). TensorZero documentation. Use for LLM gateway configuration, inference API, model provider integrations, optimization (fine-tuning, DICL), experimentation, evaluations, deployment, and observability.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.