From bf871484eadabdc60bed379d134f966c3b541da8 Mon Sep 17 00:00:00 2001 From: a2a-cloud Date: Tue, 9 Jun 2026 11:46:33 +0000 Subject: [PATCH] a2a-source-edit: remove skills/llm-iterative-scrape/SKILL.md --- skills/llm-iterative-scrape/SKILL.md | 31 ---------------------------- 1 file changed, 31 deletions(-) delete mode 100644 skills/llm-iterative-scrape/SKILL.md diff --git a/skills/llm-iterative-scrape/SKILL.md b/skills/llm-iterative-scrape/SKILL.md deleted file mode 100644 index ffcad0a..0000000 --- a/skills/llm-iterative-scrape/SKILL.md +++ /dev/null @@ -1,31 +0,0 @@ ---- -name: llm-iterative-scrape -description: "Iterative compliant scraping workflow: plan -> bounded browser step -> evaluate -> refine until goal satisfied or safety/budget stops." ---- -# llm-iterative-scrape - -Use this skill for iterative, goal-driven scraping on authorized public or user-owned sites. - -Loop: -1) Translate the natural-language goal into a minimal set of CSS selectors and a short plan for ONE bounded browser step. -2) Execute exactly one small browser step with a polite wait/rate limit via the host agent's primitives. -3) Evaluate observations vs. the goal. Refine minimally. Stop when satisfied or when any safety/budget condition triggers. - -Hard safety constraints: -- Never solve or route around CAPTCHAs/anti-bot. -- Never log in or pass paywalls. -- Restrict pagination to same-origin as the start URL by default; also respect provided allowed_domains. -- When `respect_robots` is true, treat any robots.txt disallow or failure-to-check as a stop condition. - -Selectors guidance: -- Use compact CSS selectors. Suffix conventions: `::text`, `::html`, `::attr(name)`. -- Use one pagination field: `pagination_next` or `next` for the next-page `href`. -- Prefer domain-agnostic patterns like `a[rel='next']::attr(href)` or `li.next a::attr(href)`. - -Planning output contract: -Return strictly compact JSON only: {"plan_summary": str, "selectors": {str:str}, "continue": bool, "notes": str}. Keep under ~600 chars when possible. - -Evaluation guidance: -- If extracted data matches the requested fields and count threshold, set continue=false and summarize. -- If pagination is needed for more pages and a next link exists, keep continue=true. -- On any safety trigger (captcha/login/paywall/robots), set continue=false and summarize the stop reason.