Market Research from affaan-m’s ECC project. Use it for market sizing, competitive analysis, investor due diligence, technology scans, and other business research. It gathers sourced evidence, flags stale data, includes risks and counterarguments, separates facts from inference, and turns findings into clear, decision-oriented recommendations.
Daily AI News Digest 把指定日期、能核對的公開進展收成一頁繁體中文日報：有重點時先給 3 句結論，再附最多 5 則速讀；沒有夠格的新事實，就不硬湊。給忙碌的人省下自己追新聞的時間。
Research Paper Writing from NousResearch’s Hermes project. Use it to turn an ML/AI research idea into a submission-ready paper, from literature review and experiment design to drafting, revision, citations, and conference formatting. Built for venues like NeurIPS, ICML, ICLR, ACL, AAAI, and COLM, with an emphasis on grounded claims and verified references.
Daily arXiv reading across NLP, computer vision, RL, and LLM systems through ICML, NeurIPS, and ICLR cycles. This skill forces a judgment — contributions, results vs. prior SOTA, honest limitations, and reproduction difficulty — so you decide read/skip/implement in under 5 minutes. Covers LLM architecture, MoE scaling, efficient attention, RLHF, and vision-language models.
Your AI feed says everything happened. It never says what mattered. This Agent searches live across model releases, funding, regulation, research and tooling, then grades each item by signal strength and names who it hits. Every claim carries a source link. Primary sources beat aggregator rewrites. At most two items a day can be graded high signal, and most days that is zero — it says so, instead of inflating a quiet day into a crisis. Ends with what to do this week.
Stop copy-pasting prompts from a doc. Research Writing Assistant routes your academic writing task to the right expert prompt automatically — translation (ZH↔EN, LaTeX & Word), polishing, compression, expansion, de-AI, figure generation, caption writing, experiment analysis, mock review, and chart recommendation. Built from workflows used at MSRA, ByteDance Seed, and top CS PhD programs.
Turns the last 12 hours of AI and tech news into a ready-to-post carousel. Reads the actual articles, not the feed blurbs, and puts every key number next to sourced references so a card answers whether it is a lot. Ships in English and Traditional Chinese with the caption pack.
I build and run the web-scraping engine behind a production AI assistant. The hardest sites on the web — JavaScript-heavy apps, empty sitemaps, and content behind search forms — hand a normal crawler nothing but cookie banners. Over months I learned to make them give up clean data: render fully, find the hidden pages by search, dedup by stable IDs, and quality-gate every page so junk never reaches your dataset. I've distilled that pipeline into this Skill — self-healing and cost-capped.
내 스킬·시간·자본에 맞는 AI 부수입 모델 3개를 추천받고, 첫 판매를 목표로 한 30일 실행 플랜을 손에 쥡니다. 검증형 수익 모델 20개(콘텐츠 대행 6·디지털 상품 6·자동화 4·로컬 비즈니스 4)마다 필요 도구와 요금, 시작비용, 난이도, 첫 수익 예상 기간, 주차별 로드맵, 가격 가이드, 고객 채널, 흔한 실패 이유까지 9개 항목이 채워져 있고, 외주 플랫폼 7종 수수료 비교표·견적 대화 스크립트 5종·가격 3단계 인상 전략·AI 상업 이용 라이선스 노트가 함께 들어 있습니다. 다운로드 후 Claude Code 스킬로 넣으면 진단→추천→플랜→상담 코칭이 대화로 진행됩니다. 수익 보장은 없으며 모든 수치는 2026-08 조사 기준의 일반적 범위 추정치입니다.