agentsclimarketplace

Open source jp scraper

Skill GeekFamilyCorp/TricorderKit/.claude/skills/open-source-jp-scraper

The local-first Agentic Knowledge OS - CLI-first, self-improving, measured. Turn intentions into traceable, auditable, reusable workflows. Runs on your machine (Ollama, Neo4j, Qdrant).From the repository description

Install
npx -y skills add GeekFamilyCorp/TricorderKit --skill open-source-jp-scraper

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

0.7 KB, as published. Nobody here has run it

Open Source Web Scraper Skill

Use this skill when Claude must collect information from websites with minimal token usage.

Tool priority

  1. your-scraper sources audit
  2. your-scraper scrape source <id> --mode auto
  3. your-scraper delta build --source <id>
  4. your-scraper report summary --source <id>
  5. Read scan_summary.md
  6. Read scan_delta.jsonl only when necessary

Adapt your-scraper to your actual CLI tool name (see tools/ directory).

Forbidden by default

  • Reading raw HTML
  • Reading full DOM snapshots
  • Sending full pages to LLM
  • Using browser fallback before RSS/HTTP/trafilatura
  • Ignoring robots.txt

Output expected

Return:

  • new records
  • changed records
  • errors
  • source reliability
  • next command

Keep looking

Skills are one crate of 612,213. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.