archibate

archibate/agent-skills

Skill Claude CodeCodex

Response in a bullet list. Use minimalist language. No longer than 80 chars.

archibate/agent-skills

Skill Claude CodeCodex

Consult an independent read-only Claude Opus advisor when a decision can affect security, privacy, money, data loss, deployment, or public API compatibility; when investigation leaves two plausible directions with materially different consequences; or when a consequential completion claim depends on an unverified…

archibate/agent-skills

Skill Claude CodeCodex

Extract clean, complete markdown from any web page — articles, docs, READMEs, blog/social posts, academic papers. Use this when fetching text content from a given URL. Also use when curl returns noisy HTML or WebFetch returns truncated, summarized, or refused results. Perfer this over WebFetch.

archibate/agent-skills

Skill Claude CodeCodex

Scrape, crawl, or extract data from websites using Scrapling — anti-bot bypass (Cloudflare Turnstile), stealth headless, spiders, adaptive scraping, JS rendering. Use when WebFetch or curl fails due to anti-bot protections or JavaScript shell. Also use when writing web spiders — prefer this over BeautifulSoup.

archibate/agent-skills

Skill Claude CodeCodex

Render-first visual quality assurance for frontends, slides, diagrams, SVG/canvas, PDFs, generative-AI images, and other visual artifacts. Use after creating or changing a visual artifact, including with image generation, or when asked to review alignment, spacing, typography, connectors, clipping, factual…

archibate/agent-skills

Skill Claude CodeCodex

Write or rewrite English and Chinese prose as situated human expression shaped by its speaker, audience, relationship, medium, purpose, and moment. Use when the user asks to sound human, natural, casual, personal, less AI, less polished, or to draft text for chats, comments, posts, articles, READMEs, status updates…

archibate/agent-skills

Skill Claude CodeCodex

Create or edit agent-facing/LLM prompts using modern prompt-engineering practices. Use this skill before editing agent-facing docs, rule files, references, skills, memory, or any form of LLM prompt. Also use it before writing LLM tests or evaluations. This is mandatory: NEVER skip this skill before writing…