Menu
Single page smart extraction - articles, docs, blog posts to clean markdown
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.
Lambda best practices, S3 event patterns, SQS/SNS fanout, and DynamoDB access patterns for serverless AWS architectures.
Azure Functions, Cosmos DB modeling, Service Bus patterns, Bicep templates
Traffic splitting, health checks, automated rollback, progressive delivery, and canary analysis for safe deployments.
Failure injection patterns, blast radius control, steady state hypothesis, and gameday planning for resilience testing.
OpenAI Codex CLI + Claude Code (Hizir) birlikte kullanim rehberi. Is dagitim pattern'leri, GitHub Actions workflow ornekleri, review dongusu ve iki AI yazilim asistaninin guclu yanlarini birlestiren orchestration stratejileri.
Create git commits with user approval and no Claude attribution
Based on SOC occupation classification
| name | harvest-single |
| description | Single page smart extraction - articles, docs, blog posts to clean markdown |
| allowed-tools | ["Bash","Read","Write","WebFetch"] |
| keywords | ["harvest","scrape","extract","single","page","article","documentation","markdown"] |
Extract and clean content from a single web page. Auto-detects content type (article, documentation, API reference, blog post) and produces clean, structured markdown.
/harvest <url>
# Extract a blog post
/harvest https://blog.example.com/best-practices-2024
# Extract API documentation page
/harvest https://docs.stripe.com/api/charges
# Extract a GitHub README
/harvest https://github.com/owner/repo
.claude/cache/agents/harvest/# [Page Title]
> Source: [URL]
> Extracted: [timestamp]
> Type: [article|docs|api|blog|wiki]
> Words: [count]
[Clean extracted content in markdown]
## Links Found
- [Link text](URL)