← 返回 Skills 市场

Ai Product Monitor

Name: Ai Product Monitor
Author: terrycarter1985

作者 terrycarter1985 · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

总下载

当前安装

版本数

在 OpenClaw 中安装

/install ai-product-monitor

功能描述

One-click AI product launch monitoring pipeline — RSS monitoring, product info search, screenshot capture, and trend analysis. Run the full workflow or indiv...

使用说明 (SKILL.md)

AI Product Monitor

One-click pipeline that runs four stages sequentially:

RSS Monitor — Fetch configured RSS feeds, extract AI product launch posts
Product Search — Enrich each launch with web search details
Screenshot Capture — Take screenshots of product landing pages
Trend Analysis — Analyze launch trends and generate a summary report

Quick Start (Full Pipeline)

python3 scripts/pipeline.py

Individual Stages

# Stage 1 only — RSS monitoring
python3 scripts/pipeline.py --stage rss

# Stage 2 only — Product info search
python3 scripts/pipeline.py --stage search

# Stage 3 only — Screenshot capture
python3 scripts/pipeline.py --stage screenshot

# Stage 4 only — Trend analysis
python3 scripts/pipeline.py --stage trends

Configuration

Edit references/feeds.yaml to customize RSS sources. Default feeds include OpenAI, Google AI, Anthropic, Meta AI, and Hugging Face blogs.

Output

File	Description
`data/raw_launches.json`	Raw RSS items from stage 1
`data/enriched_launches.json`	Launches with search-enriched info
`data/screenshots/`	Landing page screenshots (PNG)
`data/trend_report.md`	Final trend analysis report

Pipeline Flow

RSS Feeds → raw_launches.json → enriched_launches.json → screenshots/ → trend_report.md

Each stage reads the previous stage's output, so stages can be re-run independently after editing earlier results.

安全使用建议

Install/run only if you are comfortable with it fetching configured RSS feeds, sending product-launch titles to web search, visiting launch URLs to capture screenshots, and storing results under the skill’s `data/` directory. Review `references/feeds.yaml` first and consider running stages individually for more control.

功能分析

Type: OpenClaw Skill Name: ai-product-monitor Version: 1.0.0 The skill implements a legitimate pipeline for monitoring AI product launches by fetching RSS feeds, performing web searches, and capturing screenshots. It uses standard Python libraries and integrates with OpenClaw's internal CLI tools via subprocess.run in a safe manner (using argument lists rather than shell strings). No evidence of data exfiltration, malicious execution, or prompt injection was found in scripts/pipeline.py or SKILL.md.

能力评估

ℹ Purpose & Capability

Coherent with the stated purpose: SKILL.md describes RSS monitoring, product search, screenshot capture, and trend analysis, and scripts/pipeline.py visibly implements RSS fetching, web search, screenshot output, and local report files. Users should notice that this necessarily contacts external sites.

ℹ Instruction Scope

The workflow is user-invoked via commands such as `python3 scripts/pipeline.py`; no background or automatic startup is shown. Once run, the full pipeline follows feed-derived URLs for search and screenshots.

ℹ Install Mechanism

The registry says there is no install spec and no required binaries, while SKILL.md declares `requires_bins: [python3]` and the visible code invokes `openclaw` helper commands. This is an under-declared runtime expectation, not evidence of malicious installation.

ℹ Credentials

Network access to configured RSS feeds and product URLs is proportionate to the monitoring purpose. The script writes outputs under `data/`, including JSON files, screenshots, and a report; no credentials or private local file reads are shown.

ℹ Persistence & Privilege

The skill persists monitoring outputs such as `data/raw_launches.json`, `data/enriched_launches.json`, `data/screenshots/`, and `data/trend_report.md`. No elevated privileges, long-running worker, or self-persistence are shown.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install ai-product-monitor
安装完成后，直接呼叫该 Skill 的名称或使用 /ai-product-monitor 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release: full 4-stage pipeline (RSS→Search→Screenshot→Trends)

元数据

Slug ai-product-monitor

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题