Sentiment Monitor

Public opinion monitoring and structured report generation. Collects publicly available web information about celebrities, TV shows, or brands, performs sent...

This skill is coherent and uses only built-in web search/fetch and file-write capabilities; it does not request credentials or install code. Before installing, confirm your platform provides the WebSearch and WebFetch tools the skill needs — otherwise it cannot operate. Understand that: (1) exact social-media metrics often require platform APIs or authenticated access and will frequently be reported as “Data Unavailable”; the skill explicitly forbids fabricating numbers; (2) the agent will fetch public internet content (network traffic) — verify this behavior is acceptable in your environment and that fetching abides by target sites' terms of service; (3) the optional deliver_attachments/preview_url features may cause the platform to transmit the generated HTML via its channels — review how your platform handles attachments and previews. If you want to limit scope, test with non-sensitive public targets and review the first generated report to confirm it behaves as you expect.

Type: OpenClaw Skill Name: sentiment-monitor Version: 0.4.0 The sentiment-monitor skill bundle provides a structured framework for an AI agent to perform public opinion analysis and generate HTML reports. It utilizes standard built-in tools (WebSearch, WebFetch, Write) for its stated purpose and includes explicit instructions to avoid data fabrication and respect privacy by only accessing public information. No evidence of malicious intent, data exfiltration, or harmful prompt injection was found in SKILL.md or _meta.json.