brettdavies
UserScrape JavaScript-heavy sites and extract structured data via reusable CSS schemas. Portable agent skill wrapping the Crawl4AI CLI and Python SDK.
Categories
Indexed Skills (2)
crawl4ai
Use when scraping JavaScript-heavy pages or SPAs, crawling multiple URLs concurrently, extracting structured data with reusable CSS/JSON schemas, or building automated web data pipelines. Wraps the Crawl4AI library (`crwl` CLI and Python SDK) with schema-generation patterns for LLM-free extraction. Triggers on crawl4ai, crwl, scrape JS-heavy site, scrape SPA, headless browser scrape, schema-based extraction, batch crawl, sitemap crawl, web data pipeline. SKIP when a static HTML page can be read with `defuddle` / `fetch-web` — those are faster cold-start and don't need a browser.
bird
Drive the `bird` CLI for the X (Twitter) API — entity-store-backed reads (`--refresh` / `--no-cache` / `--cache-only`), watchlist monitoring, thread reconstruction, API usage and cost ledger, `bird doctor` self-diagnostics, JSON Schema output documents, search with sort/min-likes/pages, and the bird-specific write-op confirmation flow (`--dry-run`, `--force`, exit 2 `requires-confirmation`). Use when the user wants to read bookmarks or a profile, search recent tweets with ranking, rebuild a conversation thread, manage a watchlist, check API cost, inspect cache, run diagnostics, install the skill bundle, or any task where bird's local cache or structured error envelope matters. For OAuth flows, raw write-op transport, or full xr surface, route to the companion `xurl-rs` skill; for X API v2 endpoint, scope, and billing reference, route to the companion `x-api` skill. Triggers on "bird command", "bird search", "bird watchlist", "bird bookmarks", "bird thread", "bird doctor", "bird cache", "bird usage", "X API co
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.