ai-launch-pipeline

by terrycarter1985

Install this Skill

curl -fsSL -o ai-launch-pipeline.zip https://skill.seembox.com/api/v1/skills/ai-launch-pipeline/download && unzip ai-launch-pipeline.zip

Download ai-launch-pipeline.zip

SKILL.md About

---
name: ai-launch-pipeline
description: One-click automated pipeline for AI product launch monitoring. Integrates RSS feed monitoring, product info search, page screenshot/snapshot capture, and trend analysis into a single script. Use when running a full AI launch monitoring cycle, generating a trend report from RSS feeds, or executing the blogwatcher workflow end-to-end without manual step-by-step orchestration.
---

# AI Launch Pipeline

Run the full AI product launch monitoring workflow in one command.

## Quick Start

```bash
bash scripts/ai_launch_pipeline.sh
```

Output lands in `$AI_PIPELINE_WORKSPACE/runs/<timestamp>/` (default: `~/.openclaw/workspace/data/ai-launch-pipeline/runs/`).

## Pipeline Stages

| # | Stage | Output |
|---|-------|--------|
| 1 | RSS monitoring | `rss/rss_hits.json` — AI launch hits from OpenAI, Anthropic, Google, HuggingFace, DeepSeek feeds |
| 2 | Product search | `search/search_results.json` — supplementary search results |
| 3 | Screenshot capture | `screenshots/` — text snapshots of hit pages + manifest |
| 4 | Trend analysis | `trends/summary.md` + `trends/trend_report.json` — model/org frequency, top signals |

## Configuration

- `AI_PIPELINE_WORKSPACE` — override output root directory
- Edit the `feeds` list in Stage 1 to add/remove RSS sources
- AI keyword filter is in the `ai_keywords` regex (Stage 1)

## Requirements

- Python 3 (stdlib only — no pip packages needed)
- Optional: `duckduckgo-search` CLI for enhanced Stage 2

_meta.json Metadata

{
  "ownerId": "kn72jmd20ws94jr0p8b3p24wyn82abgj",
  "publishedAt": 1777863618405,
  "slug": "ai-launch-pipeline",
  "version": "1.0.0"
}