Skip to content
Development
Command

/cs-scrape

Route, extract, and validate a scraping job (URL or local file) via the universal-scraping-architect skill — refuses to deliver unvalidated data.

From plugin
claude-skills
24k116 skills100 agents116 commands1 MCP
Install
$ npx -y skills add alirezarezvani/claude-skills --agent claude-code

How it fires

How this command gets triggered: by you, by Claude, or both.

  • Fires itselfClaude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/cs-scrape

Context preview

What this command does when you run it.

Route, extract, and validate a scraping job (URL or local file) via the universal-scraping-architect skill — refuses to deliver unvalidated data.

Command definition

cs-scrape.md
name: cs-scrape
description: Route, extract, and validate a scraping job (URL or local file) via the universal-scraping-architect skill — refuses to deliver unvalidated data.
argument-hint: "<url-or-file-path> [desired output: csv|json|markdown]"

/cs-scrape

Run a gated extraction pipeline for `$ARGUMENTS` using `skills/universal-scraping-architect/SKILL.md`.

Pre-flight gates (stop if any fails)

1. **Target stated?** If `$ARGUMENTS` is empty, ask for the URL or file path plus the desired output format — do not guess. 2. **Live-site etiquette:** for URLs, check `robots.txt` and plan rate limits; refuse disallowed targets. 3. **Privacy:** if the target is a local/sensitive file, do not send it to an external API — force Mode 2 (local Python). 4. **Secrets:** Firecrawl key only via `os.getenv('FIRECRAWL_API_KEY')`; if a key appears inline anywhere, fix that first.

Workflow

1. **Route** — state the mode and why (per the skill's routing rules): Mode 1 Firecrawl (public/JS-heavy URL, bulk crawl) · Mode 2 local Python (local files, private data, simple static HTML) · Mode 3 hybrid (Firecrawl extract + pandas clean). 2. **Budget** — estimate API quota / token limits before multi-page jobs; add checkpointing + pagination. 3. **Extract** — start from the matching runner template (run from the plugin root; `--sample` previews the summary shape offline):

   python3 skills/universal-scraping-architect/scripts/firecrawl_example.py --sample
   python3 skills/universal-scraping-architect/scripts/local_bs4_example.py --sample

4. **Validate (mandatory, exit-code gated):**

   python3 skills/universal-scraping-architect/scripts/validate_extraction.py extracted_output.json --json
  • exit 0 (`status: ok`) → continue
  • exit 1 (`warning` = empty output, `error` = malformed JSON) → fix and re-extract; **never deliver unvalidated data**

Then check required fields and duplicates against the job spec. 5. **Deliver** — CSV (tabular) / JSON (nested) / Markdown (docs, chunked), per the user's requested format, with a summary of mode chosen, row counts, empty values, and the validation verdict.

Read more
Ships withclaude-skills

362 production-ready Claude Code skills, plugins, and agent skills for 13 AI coding tools. The most comprehensive open-source library of Claude Code skills and agent plugins — also works with OpenAI Codex, Gemini CLI, Cursor, and 9 more coding agents.

Get the whole plugin, auto-invoked
Stats
24,115
Stars
1
Views
3,400
Forks
Active
Maintenance
Python
Language
MIT
License
3d ago
Last commit
9mo ago
Created

Repo: alirezarezvani/claude-skills