shali10

agent-reach

Use when searching or extracting multimedia content including Bilibili/YouTube video subtitles, RSS feeds, and clean web text.

agent-system-design

Use when designing, architecting, or benchmarking multi-tier autonomous AI Agent systems with layered memory, semantic caching, model routing, and deterministic guardrails.

cloudflare-fullstack-ops

Use when deploying, configuring, or managing Cloudflare full-stack edge infrastructure including Pages, Workers, D1 SQL databases, R2 object storage, KV, and DNS routing.

cloudflare-worker-api-proxy

Use when deploying or maintaining a zero-cost OpenAI/Anthropic-compatible API reverse proxy on Cloudflare Workers with custom auth, streaming, and rate-limiting.

human-voice-writing

Use when writing technical tutorials, engineering blogs, and articles that sound like a real person with technical depth rather than robotic AI prose.

Data & Documents Listed

large-file-data-analysis

Use when analyzing, transforming, or extracting insights from massive Excel spreadsheets (10k-100k+ rows) and large PDF/Word documents without causing context overflow.

Data & Documents Listed

markdown-to-html-report

Use when converting plain Markdown documents into magazine-grade, responsive HTML reports and printable PDF documents with modern typography and card layouts.

multi-platform-distribution

Use when adapting a single piece of Markdown content into tailored, platform-compliant formats for Telegram, WeChat, Zhihu, Twitter/X, and QQ.

telegram-pipe-table-rendering

Use when sending Markdown tables to Telegram, resolving table degradation, CJK East Asian character alignment, and mobile viewport wrapping.

tiered-memory

Use when designing or managing AI Agent persistent memory architectures to prevent context overflow while preserving durable facts.

vps-bootstrap

Use when provisioning, benchmarking, and hardening a fresh Linux VPS node with SSH security, UFW firewall, Fail2ban, BBR acceleration, and hardware health inspection.