Menu
RSS 피드 모니터링 → SEO 기사 수집·분석·트렌드 리포트
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | seo-article-harvester |
| title | SEO Article Harvester — Full Pipeline |
| description | RSS 피드 모니터링 → SEO 기사 수집·분석·트렌드 리포트 |
| type | skill |
| space | outcome |
| tags | ["outcome","seo","rss","crawling","pipeline"] |
| created | "2026-05-20T00:00:00.000Z" |
| updated | "2026-06-29T00:00:00.000Z" |
| links | ["[[@action/skills/SKILL-INDEX]]","[[skills/seo-article-harvester/references/crawling-tools]]","[[@memory/knowledge/seo-articles]]","[[@memory/growth/seo/index]]","[[@identity/brain/rules]]"] |
[수집] cron_seo_harvester.sh (no_agent, 6h)
│
▼
[분석] kanban worker (LLM, daily 12:00)
│ → 기사 요약 + 주제 태깅 + 중요도 점수
│ → Google 업데이트/알고리즘 변경 발견 시 kanban task
▼
[트렌드] kanban worker (LLM, weekly Mon 14:00)
│ → 주간 SEO 트렌드 리포트
│ → P4-cortex/growth/seo/weekly/ + Discord
▼
[정리] 스크립트 (no_agent, monthly)
→ 3개월 지난 기사 _archive/ 이동
SEO Article Harvester (no_agent, 0 */6 * * *)cron_seo_harvester.sh → cron_seo_harvester.py → harvester.py + label_heritage.pyseo-articles/YYYY/article-slug.md (YAML frontmatter 포함)seo-analyze-trigger (LLM, daily 12:00 KST, fast model)seo-articles/YYYY/*.md (아직 분석 안 된 새 기사)P4-cortex/growth/seo/analyzed/YYYY-MM-DD-hash.jsonP4-cortex/growth/seo/seo_analysis_state.jsonseo-trend-trigger (LLM, weekly Mon 14:00 KST, fast model)P4-cortex/growth/seo/weekly/YYYY-MM-DD-trends.md_archive/| Job | Schedule | Type | Model | LLM? |
|---|---|---|---|---|
| SEO Article Harvester | 0 */6 * * * | no_agent | — | ❌ |
seo-analyze-trigger | 0 12 * * * | LLM agent | opencode-go/deepseek-v4-flash | ✅ |
seo-trend-trigger | 0 14 * * 1 | LLM agent | opencode-go/deepseek-v4-flash | ✅ |
P2-hippocampus/knowledge/seo-articles/
├── YYYY/ # 연도별 수집 기사
│ └── *.md
├── _new/ # 최근 수집 (미분류)
├── _archive/ # 오래된 기사
├── collected_urls.json
└── report.json
P4-cortex/growth/seo/
├── seo_analysis_state.json # 분석 상태 추적
├── analyzed/ # 분석 결과 (YYYY-MM-DD-hash.json)
└── weekly/ # 주간 트렌드 리포트
└── YYYY-MM-DD-trends.md
ahrefs.com/blog/feed, searchengineland.com/feed, semrush.com/blog/feedyoast.com/feed/, seopress.org/feed, ascentkorea.com/feedgrowthmk.com/feed, moz.com/blog/feed, searchenginejournal.com/feedcopyblogger.com/feedblog.google/technology/ai/rss, developers.googleblog.com/feeds/posts/defaultblog.chromium.org/feeds/posts/default, techcrunch.com/feedtheverge.com/rss/index.xml, wired.com/feed/rss, zdnet.com/rss.xmlfeeds.arstechnica.com/arstechnica/index, css-tricks.com/feedsmashingmagazine.com/feed, aws.amazon.com/blogs/aws/feed, github.blog/feedopenschema.co.jp/feed, hnrss.org/frontpage, dev.to/feednews.ycombinator.com/rss, techmeme.com/feed.xmlThe analyzer should surface Generative Engine Optimization (GEO) concepts alongside traditional SEO:
| Signal | What to capture |
|---|---|
| Citability scoring | Passage length, self-contained facts, direct-answer structure, citation readiness |
| AI crawler analysis | New AI bot signals (GPTBot, ClaudeBot, PerplexityBot), robots.txt guidance, llms.txt relevance |
| Brand authority | Brand mentions as an AI visibility signal, entity authority shifts |
| Platform optimization | ChatGPT, Perplexity, Gemini, Google AI Overviews-specific tactics |
| Schema for AI | JSON-LD, llms.txt, ARD/AI discovery signals, structured data for LLM consumption |
{
"article_url": "https://...",
"title": "Article Title",
"summary": "1-2 sentence LLM summary",
"topic_tags": ["google-update", "core-web-vitals", "ranking", "geo", "ai-search"],
"relevance_score": 4,
"geo_relevance_score": 3,
"ai_citation_readiness": 3,
"key_insight": "Main actionable takeaway",
"geo_insight": "AI-search / GEO takeaway, if any",
"is_critical": false,
"analyzed_at": "2026-06-14T12:00:00"
}
references/crawling-tools.md — 크롤링 도구references/discord-webhook-limits.md — Discord embed 제한{{AGENT_NAME}} brain signal architecture — event bus, signal processor, awareness reporter, brain monitor
TDD-PDCA plan for building a self-replicating branching agent in {{AGENT_NAME}}. 단일 에이전트가 스스로 서브에이전트를 분기하고, 결과를 수렴시키는 구조.
Integrate {{AGENT_NAME}} with ACP (Agent Client Protocol) agents. Reverse-engineered from goose's Rust ACP provider implementation.
Maintain .{{AGENT_NAME_LOWER}} as an Obsidian vault — graph connectivity overhaul (P-layer mesh, skill clusters, SEO article web), broken link detection, backlink density verification via Obsidian CLI, filename deduplication, bidirectional linking, auto-generated orphan management, cron output graph bloat prevention, and Obsidian compatibility.
AI Trend Collection & Filtering — collect GitHub trending repos, score via 5-axis philosophy filter, evaluate, apply, and retire.
Authoring and using agent profiles — pre-defined subagent roles that set model, provider, toolsets, and instructions in one task() call. Covers profile format, the 14 standard roles, pipeline patterns, cost-tiered model assignment, and the ESCALATE mechanism for capability routing.