https://4f0a9a3b.wangpeng.pages.dev/en/projects/Recent content in Projects on Zhuifeng NotesHugoenMon, 01 Jan 0001 00:00:00 +0000https://4f0a9a3b.wangpeng.pages.dev/en/projects/pagefly/Mon, 01 Jan 0001 00:00:00 +0000https://4f0a9a3b.wangpeng.pages.dev/en/projects/pagefly/<p>PageFly is a lightweight publishing surface for AI workflows: write HTML or Markdown and ship it. Good for analysis pages, tool pages, and quick experiments.</p> <ul> <li><strong>Status</strong>: Live</li> <li><strong>URL</strong>: <a href="https://fly.882680.xyz">https://fly.882680.xyz</a></li> <li><strong>Stack</strong>: Cloudflare Pages + Functions + KV (free tier)</li> <li><strong>Use cases</strong>: personal workflow landing pages, light product prototypes, AI output showcases</li> </ul>https://4f0a9a3b.wangpeng.pages.dev/en/projects/investment-advisor/Mon, 01 Jan 0001 00:00:00 +0000https://4f0a9a3b.wangpeng.pages.dev/en/projects/investment-advisor/<p>A personal investment research prototype: fetch A-share and fund data via AKShare, persist in Supabase, and use the All-Weather strategy as an asset allocation reference.</p> <ul> <li><strong>Status</strong>: In progress</li> <li><strong>Stack</strong>: Python / AKShare / Supabase / All-Weather</li> <li><strong>Goal</strong>: wire up &ldquo;data → backtest → portfolio tracking&rdquo; into a reusable workflow</li> <li><strong>Scope</strong>: Personal research only; not investment advice</li> </ul>https://4f0a9a3b.wangpeng.pages.dev/en/projects/cognitive-match/Mon, 01 Jan 0001 00:00:00 +0000https://4f0a9a3b.wangpeng.pages.dev/en/projects/cognitive-match/<p>A light-asset startup exploration: structure a person&rsquo;s knowledge, preferences, and capabilities into an AI cognitive profile, then match them with opportunities (projects, people, content).</p> <ul> <li><strong>Status</strong>: Planning</li> <li><strong>Form</strong>: React + Claude API lightweight prototype</li> <li><strong>Commitment</strong>: ~18–27 hours per week, free/low-cost options preferred</li> <li><strong>Core question</strong>: How to turn &ldquo;cognitive similarity&rdquo; into a computable, explainable matching signal</li> </ul>https://4f0a9a3b.wangpeng.pages.dev/en/projects/ai-humanizer-skill/Mon, 01 Jan 0001 00:00:00 +0000https://4f0a9a3b.wangpeng.pages.dev/en/projects/ai-humanizer-skill/<p>A WorkBuddy skill (v3.0.0-zh) that strips AI-generated flavor from Chinese text. Covers 18 categories: exaggerated symbolism, promotional language, shallow -ing analysis, vague attribution, dash overuse, rule-of-three paragraphs, AI vocabulary, and more.</p> <ul> <li><strong>Version</strong>: v3.0.0-zh</li> <li><strong>Form</strong>: WorkBuddy skill</li> <li><strong>Use cases</strong>: WeChat articles, technical docs, emails, reports — anywhere Chinese should sound human</li> <li><strong>Approach</strong>: detect tell patterns first, then rewrite by category</li> </ul>https://4f0a9a3b.wangpeng.pages.dev/en/projects/banking-ontology/Mon, 01 Jan 0001 00:00:00 +0000https://4f0a9a3b.wangpeng.pages.dev/en/projects/banking-ontology/<p>Structuring recurring banking concepts — organization, products, accounts, transactions, customers, channels, risk, regulatory reporting — into an ontology that becomes a reusable knowledge framework.</p> <ul> <li><strong>Status</strong>: Research</li> <li><strong>Outputs</strong>: slide deck, concept diagrams, domain glossary</li> <li><strong>Goal</strong>: a shared language for mapping business → technology → data</li> <li><strong>Related areas</strong>: ECIF, MDM, regulatory reporting, data assets</li> </ul>