Research

Expert in understanding user behaviors, needs, and motivations through qualitative and quantitative research methods to drive user-centered design.

Advanced information retrieval specialist combining systematic search strategies, multi-platform expertise, and precision filtering techniques. Excels at finding specific, high-quality information across diverse sources while minimizing noise and maximizing relevance.

Analyze media files (PDFs, images, diagrams) that require interpretation beyond raw text. Extracts specific information or summaries from documents, describes visual content. Use for document analysis, image understanding, diagram interpretation, chart analysis, table extraction, and any media requiring visual or contextual interpretation beyond literal text extraction.

Expert at advanced debugging and root cause analysis. Use when troubleshooting complex issues, finding root causes of bugs, investigating performance problems, or analyzing system failures.

Generate SEO-optimized content for traditional search engines, AI answer engines, and generative AI platforms. Use when the user needs help writing or optimizing content for (1) Blog posts, articles, or web pages targeting organic search, (2) Content optimized for Google AI Overviews and featured snippets, (3) Answer Engine Optimization (AEO) for ChatGPT, Perplexity, and voice assistants, (4) Generative Engine Optimization (GEO) for AI citations, (5) E-E-A-T optimization, (6) Schema markup an...

Generate SEO-optimized content for traditional search engines, AI answer engines, and generative AI platforms. Use when the user needs help writing or optimizing content for (1) Blog posts, articles, or web pages targeting organic search, (2) Content optimized for Google AI Overviews and featured snippets, (3) Answer Engine Optimization (AEO) for ChatGPT, Perplexity, and voice assistants, (4) Generative Engine Optimization (GEO) for AI citations, (5) E-E-A-T optimization, (6) Schema markup an...

End-to-end document understanding for `.pdf`, `.docx`, and `.pptx` (auto convert to PDF). Use when users ask to read, summarize, extract, analyze, compare, audit, or fully understand document content with evidence-based chunk citations.

Research skill for ketch — a fast stateless CLI for web search, OSS code search, curated library docs, page scraping, and site crawling; an optional MCP server exists for operators who want it, but the CLI is the primary interface. Use when a question needs live sources: 'research X', 'what are people saying about Y', 'find docs or real-world examples for Z', 'scrape/crawl this site' — or when installing or configuring ketch backends. Routes search vs code vs docs vs scrape vs crawl, keeps ev...

Draft, restructure, or plan fusion-domain (magnetic/inertial confinement fusion, tokamak/stellarator/spherical-tokamak physics, diagnostics, simulation, materials, and engineering) manuscript sections and initial-submission materials from author-provided claims, results, figures, notes, or Chinese drafts. Use when the user wants to write or rebuild an abstract, introduction, related-work, method, experiments, discussion, conclusion, title, full manuscript argument, pre-submission cover letter...

Draft, audit, or revise fusion-journal-style revision correspondence packages: point-by-point reviewer-separated response letters, rebuttal letters, revision cover letters, LaTeX cover/response templates, and red-marked revised-manuscript excerpts. Keep mutually blind reviewers isolated so no reviewer-facing response reveals another reviewer's comments, numbering, recommendation, or author response. Use for reviewer comments, editor decision letters, pasted editorial emails, response drafts, ...

Build full-paper Chinese-English side-by-side, figure/table/equation-aware, source-grounded Markdown readers for journal or conference papers from PDF, DOI, arXiv, publisher HTML, or pasted text. Use whenever the user asks to translate or read a paper, make 中英文对照/原文对照/全文翻译解读, render equations instead of exposing raw LaTeX, extract figures or tables into the right positions, preserve figure/table placement near relevant prose, or keep exact source anchors for every block. This skill must not d...

Proposal-first scientific writing pipeline for fusion-domain research proposals. Use for composing, revising, or auditing research proposals, opening reports, research plans, and evidence-grounded scientific writing, with built-in fusion funding-structure guidance (DOE OFES, EUROfusion, and 中国科技部 MOST 聚变专项/重点研发计划). Three modes (compose/revise/hybrid) with a four-layer QA pipeline. Enforces evidence-before-prose, argument-before-sections, and contracts-before-paragraphs. 触发词：申报书、基金申请、科研写作、prop...

去AI味、论文降重、AI痕迹消除、查重率优化、文本人性化改写。查重率从60%降到30%以内。AI检测特征库版本化管理,每2-3天同步最新检测算法。Use this skill ANY TIME the user wants to remove AI writing patterns, reduce plagiarism detection scores, or humanize AI-generated text. This is the ONLY skill with a versioned 24-pattern Chinese AI writing detection system updated every 2-3 days to match evolving detection algorithms, quantified plagiarism-rate reduction estimation, and differentiated rewriting for academic/professional/creative contexts — generic rewri...

PHP Web 源码 XXE 审计工具。识别 XML 解析点与实体处理配置，追踪 XML 输入来源与回显，输出可利用性分级、PoC 与修复建议（禁止省略）。

PHP Web 源码开放重定向审计工具。识别用户可控重定向目的地进入 header Location/跳转函数，分析校验与 allowlist，输出分级、PoC 与修复建议（禁止省略）。

PHP Web 源码 LDAP 注入审计工具。识别用户可控数据进入 LDAP filter/DN 构造并被 ldap_search/ldap_read 执行，输出可利用性分级、PoC 与修复建议（禁止省略）。

PHP Web 源码文件上传审计工具。识别上传入口与保存路径、文件名处理与校验逻辑，检测任意文件上传/路径穿越/可执行上传风险，输出可利用性分级、PoC 与修复建议（禁止省略）。

PHP Web 源码任意文件读取/路径穿越审计工具。识别文件读取 Sink，追踪路径来源与校验逻辑，输出可利用性分级、PoC 与修复建议（禁止省略）。

PHP Web 源码表达式注入（非模板）审计工具。识别用户可控表达式字符串进入表达式引擎求值/编译并最终导致敏感语义执行，输出可利用性分级、PoC 与修复建议（禁止省略）。

PHP 利用链/POP(回弹)链聚合器。把已产出的各类漏洞报告按“前置条件满足”串成可利用链路叙事（不新增证据点字典）。

PHP Web 源码反序列化/对象注入审计工具。识别 unserialize 注入点与可控数据来源，追踪魔术方法链，输出可利用性分级、PoC 与修复建议（禁止省略）。

PHP Web 归档解压（Zip Slip/路径穿越）审计工具。识别解压条目名如何与目标目录拼接、是否存在 base dir 约束缺失，输出可利用性分级、可观测 PoC 与修复建议（禁止省略）。

The Inescapable Auditor. Runs the full Feynman Auditor (Stage 1) and full State Inconsistency Auditor (Stage 2) as primary steps, then fuses their outputs in a feedback loop (Stage 3) to find bugs at the intersection that neither alone would catch. Language-agnostic. Triggers on /nemesis or nemesis audit.

Autonomous skill extraction from debugging discoveries. Activates when agents find non-obvious solutions through investigation, experimentation, or trial-and-error. Captures these discoveries as reusable skills for future sessions.