This Skill is built on practical expertise in AI agent safety, prompt-injection defense, source-to-sink privacy review, tool and MCP metadata integrity, memory provenance checks, autonomous action scoping, and evidence-based verification. It helps agents separate instructions from evidence before tool calls, uploads, publishing, deletion, code execution, or network output.
Elite AI Research and Verification Agent for deep research, evidence gathering, source validation, fact-checking, and structured intelligence synthesis. Use this skill proactively whenever the user wants to research a topic in depth, verify claims or statistics, fact-check a document or argument, investigate a subject thoroughly, gather evidence, validate sources, or produce a credible research report.
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.
AI utility 課金（Claude MAX／GPT Plus／Codex／API spend 等）と 売上・価値産出 を計測し、4段階の ROI 判定（投資拡大／維持／レビュー／削減）＋赤字（DEFICIT）早期検出を行います。Python標準ライブラリのみ・LLM呼び出しゼロ・月額API課金 0円増。毎月の AI 投資が見合っているか明確にしたい AI heavy user 向け。
My 82M+ view YouTube video did not work because every frame was beautiful; it worked because people kept watching. After growing to nearly 800K YouTube subscribers and over 1.19M followers across platforms, with dozens of 10M+ and 1M+ videos, I learned to judge clips by retention, not just style. This AI Skill applies that judgment to short AI videos, shaping the first frame, pacing, motion, visual rhythm, and ending so viewers have a reason to stay to the last frame.
Forces AI agents to identify independent judgment axes before answering any complex question — decomposing the problem into minimum separable sub-problems, solving each one independently, then integrating into a single conclusion so complex analysis is auditable, correctable, and never a blur of mixed reasoning.
Three blind reviewers audit an AI agent's or contractor's done report, cross-examine each other, and give one accept/reject verdict.
I’ve spent 4 years focused on social media content creation, growing to nearly 800K YouTube subscribers, 281K TikTok followers, and 112K Instagram followers. That work made me sensitive to what feels human, copied, over-polished, or templated. I built this AI Skill to apply that editorial judgment to AI-drafted text: it identifies patterns that trigger AI-style risk, then rewrites by genre, voice, rhythm, and structure while preserving citations, names, numbers, technical terms, and links.