Claude Skills by infometa

Retrieve the legal basis and professional-database facts that intellectual-property work depends on — supporting statutes/司法解释 and their effectiveness status, similar-case adjudication rules, and — critically — the authoritative registration/technical facts held in IP专业数据库 (patent literature, trademark registers, copyright registration, domain WHOIS, entity-credit data). Runs a multi-layer retrieval pipeline: structured IP-fact extraction, legal-issue positioning, statutory-hierarchy scanning...

Format IP analysis/drafting results into the deliverable shape the routed scenario requires, following the house style distilled from real IP work-product templates. Use after analysis/drafting to produce the final text and citation style. Chooses among output modes (rights-confirmation opinion, patent search report, similarity/近似 comparison, infringement/FTO memo, trade-secret element analysis, domain strategy, litigation-venue memo, etc.), applies the standard 5-part skeleton (问题定位/思考过程 → 整...

Identify the user's true intellectual-property intent and route it to the correct scenario (IP-A~IP-F across copyright, patent, trademark, trade secret, domain and综合 needs). Use this skill FIRST for every IP request to determine scenario type, core objective, binding output standard, whether interactive intake is required, which professional IP databases to use, output weight tier, and the next skill in the chain — before any retrieval, analysis or drafting happens.

知识产权检索核验工作台。任务单出现【核验工作台：必用】、【输出档位：重量】或输出形态属于专利/商标/著作权检索报告、布局全景分析、侵权风险/侵权认定分析（FTO）、无效宣告/驳回复审策略、商业秘密认定、尽职调查、诉讼管辖方案、企业IP战略等成体系交付物时必须使用。本 skill 执行脚本化动作：保存 answer/sources/claims，运行 ip-verify all/html/repair-* 生成模板 HTML；禁止手写 HTML。

全媒体广告分析专家技能（公共版）。支持百度/360/腾讯/Google/Bing五平台，引导式MCP安装配置，自动生成含关键词、创意、素材分析的结构化日报。

通过金数据（Jinshuju，jinshuju.net）MCP 操作用户托管在金数据平台上的在线表单：创建 / 复制 / 编辑表单与主题，含自动判分的考试表单、选项计分的测评表单；查询、新增（单条或批量）、更新、删除、批量修改数据；用上传凭证上传本地图片或文件；查询账户套餐额度与团队成员。仅在用户操作其金数据平台数据时使用——触发信号：提到 金数据 / Jinshuju / jinshuju.net、给出 form_token，或要操作一张已托管在金数据上的表单或数据。不要用于：用代码开发表单 / 问卷系统、处理本地文件或表格（Excel / CSV）、图片 / 票据 OCR、物流或监控等与平台无关的自动化，以及与金数据平台无关的通用数据处理。

通过金数据（Jinshuju，jinshuju.net）MCP 操作用户托管在金数据平台上的在线表单：创建 / 复制 / 编辑表单与主题，含自动判分的考试表单、选项计分的测评表单；查询、新增（单条或批量）、更新、删除、批量修改数据；用上传凭证上传本地图片或文件；查询账户套餐额度与团队成员。仅在用户操作其金数据平台数据时使用——触发信号：提到 金数据 / Jinshuju / jinshuju.net、给出 form_token，或要操作一张已托管在金数据上的表单或数据。不要用于：用代码开发表单 / 问卷系统、处理本地文件或表格（Excel / CSV）、图片 / 票据 OCR、物流或监控等与平台无关的自动化，以及与金数据平台无关的通用数据处理。

通过金数据（Jinshuju，jinshuju.net）MCP 操作用户托管在金数据平台上的数据表格：创建 / 编辑数据表与列（含自动计算的公式列）；查询、新增（单条或批量）、更新、批量更新、删除行数据；用上传凭证把本地文件写入附件列；查询账户套餐额度与团队成员。仅在用户操作其金数据数据表时使用——触发信号：提到 金数据表格 / Jinshuju 表格 / 数据表，或要在金数据上建表、加改列、批量维护行数据。不要用于：用代码开发表格系统、处理本地文件或表格（Excel / CSV）、搭建对外收集的表单 / 问卷、图片 / 票据 OCR，以及与金数据平台无关的通用数据处理。

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

Stage 4 of the Job Companion Team flow. Builds a STAR story bank and behavioral interview question set tailored to a target role, equipping the user with structured answers before any real interview.

Stage 5 of the Job Companion Team flow. Runs role-play mock interviews (behavioral / technical / case) with per-question scoring and three concrete improvement points, producing a final feedback table.

Stage 7 of the Job Companion Team flow. Converts a chosen offer into a 90-day onboarding plan, runs monthly probation reflections, and projects 3-5 year career paths with quarterly milestone checkpoints.

Stage 3 of the Job Companion Team flow. Turns a candidate direction plus raw experience into ATS-friendly resume versions, one-line self-introductions, and 90-second elevator pitches.

Stage 6 of the Job Companion Team flow. Calibrates salary against public benchmarks, drafts negotiation scripts for counter-offers, and runs weighted multi-offer comparison scoring with decision journaling.

Stage 1 of the Job Companion Team flow. A four-card self-inventory system that helps job seekers turn fuzzy self-knowledge into a clear self-portrait card covering interests, values, abilities and 3-year identity anchors.

Stage 2 of the Job Companion Team flow. Turns a completed self-portrait into 1-3 candidate directions, each with industry image, typical role profiles, market thresholds and salary bands.

"根据用户场景自动推断表头字段，创建信息收集或报名登记表格（.ksheet）。 当用户提到「报名表」、「信息收集」、「登记表」、「做个表单」、「收集信息」时使用。 若需要美化已有表格样式，请使用 table-beautify 技能。

"自动识别接龙文本内容，提取结构化数据并生成在线表格（.ksheet）。 当用户粘贴接龙文本或提到「接龙转表格」、「整理接龙」、「接龙统计」、「文字转表格」时使用。

"对在线表格（.xlsx / .ksheet）进行格式化、样式调整与数据美化操作。可浏览目录定位目标表格文件。 当用户要求「美化表格」、「格式化表格」、「调整表格样式」、「表格排版」时使用。 若需要新建表格并写入数据，请使用 form-generator 或 jielong-table 技能。

"快速创建各类金山在线文档（智能文档、Word、Excel、PDF、PPT、智能表格、多维表格）并写入内容。 当用户要求「新建文档」、「创建文件」、「写一份文档」、「新建表格」时使用。 若需要读取已有文档，请使用 doc-to-markdown 技能。

"自动按内容分类创建文件夹、移动文件，支持标签管理与按标签检索。 当用户要求「分类整理」、「自动归类」、「打标签」、「按标签查找」、「文件归档」时使用。 若仅需搜索定位文件，请使用 doc-search 技能。

"搜索云盘文件、浏览目录结构，快速定位并整理文档。支持批量移动归档、回收站查看与恢复。 当用户要求「找文件」、「搜索文档」、「浏览目录」、「查找资料」时使用。 若需要按内容分类或打标签，请使用 doc-classify 技能。

"将金山文档在线文档（智能文档 .otl、Word .docx、PDF .pdf）内容提取为 Markdown 格式输出。 当用户要求「读取文档内容」、「提取文档文本」、「导出 Markdown」、「文档转文本」时使用。 若需要写入或创建文档，请使用 create-doc 技能。

"搜索多份云文档，提取信息并自动生成总结报告或新文档内容。可浏览目录定位目标文档。 当用户要求「汇总报告」、「多文档总结」、「定期播报」、「内容整合」时使用。 若只需读取单篇文档，请使用 doc-to-markdown 技能。

"从多份云文档中提取碎片内容，整合生成结构化的汇总文档。可浏览目录定位源文件和目标文件。 当用户要求「整理碎片笔记」、「合并文档」、「整合分散内容」、「汇总资料」时使用。 若需要在知识库中整理，请使用 knowledge-format 技能。

"对知识库中的零散内容进行智能化整理和结构化重组。支持读取文档内容、调整格式与排版、规范化标题层级，可浏览目录批量处理多个文档。 当用户要求「整理知识库」、「重组笔记」、「知识库内容整理」、「结构化知识」、「格式化文档」时使用。 若需要将内容存入知识库，请使用 knowledge-save 技能。

"将各类内容（网页、文件、云文档）一键保存到个人知识库。支持按时间筛选批量归档和自动分类，可浏览目录选择保存位置。 当用户要求「存入知识库」、「保存到知识库」、「归档到知识库」、「放到知识库」时使用。 若需要整理知识库已有内容，请使用 knowledge-format 技能。

"将网页内容剪藏并自动保存为金山文档智能文档（.otl）。 当用户提供 URL 并要求「保存网页」、「收藏网页」、「剪藏」、「网页存到文档」时使用。 若需要存入知识库，请使用 knowledge-save 技能。

"PDF 文档的创建、内容读取、页数查询与页面提取操作。可浏览目录定位 PDF 文件。 当用户提到「PDF」、「读取 PDF」、「PDF 页数」、「提取 PDF 页面」、「PDF 拆分」时使用。 若需要操作其他文档类型，请使用 kdocs 或对应类型技能。

"AI 驱动的演示文稿生成能力 — 支持主题生成、文档转 PPT、单页生成与合并。 当用户需要生成 PPT、演示文稿、文档转 PPT、单页幻灯片时使用。

Creates deep-analysis short video scripts in "吟游诗人基德" (Minstrel Kidd) style. Uses a five-section structure (Hook→Foundation→Core→Counterintuitive Answer→Conclusion), with colloquial expression, "Farmer Lady" audience proxy mechanism, exaggerated analogies, and data visualization tables. Outputs colloquial, internet-native, northern-dialect-flavored scripts. Covers: international politics, finance/geopolitics, space science/astronomy, and hardcore tech. Use when the user asks to write video sc...

Parse an investor or client onboarding packet into structured KYC fields — identity, ownership, control, source of funds, and document inventory. Use as the first step of KYC screening; output feeds the rules engine.

Apply the firm's KYC/AML rules grid to a parsed onboarding record — assign a risk rating, list every rule outcome with the rule cited, and flag what's missing or escalation-worthy. Use after kyc-doc-parse; this skill decides nothing, it scores and routes.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx i...

Brief a case in your preferred format. In drill-me mode, makes the student state the holding first. Use when the user says "brief [case]", "what's the holding in", "case brief", or pastes a case.

Prep for a cold-call — predict the professor's likely questions and drill them Socratically, flagging where you're shaky so you know what to re-read before class. Use when the user says "prep for class tomorrow", "cold call [case]", "what might [professor] ask on", or points at assigned reading.

About-you interview and materials intake — classes, bar jurisdiction, learning style (drill-me vs explain-to-me), past outlines, graded essays, old exams, MBE sets, syllabi, papers. Use on a fresh install, when the user says "set up" or "get started", or with --check-integrations to re-probe connectors.

Guided customization of your law-student study profile — change one thing without re-running the whole cold-start interview. Adjust current classes, learning style, outline preferences, exam prep subjects, seed materials, or study session cadence. Use when the user says "change my [thing]", "add a class", "update my profile", "new semester", or "customize".

Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.

Generate or drill flashcards for black-letter memorization — Leitner-style buckets, per-subject markdown storage, drill mode with self-assessment. Use when the user says "drill flashcards", "make flashcards from", "quiz me on cards", or wants to memorize rules.

Grade an IRAC essay for structure, issue-spotting, rule accuracy, analysis depth, and organization. Does NOT rewrite the essay or show a model answer; tracks patterns across sessions. Use when the user says "grade my IRAC", "check my essay", or "I wrote this, give me feedback".

Structural feedback on a legal writing draft (memo, brief, paper, exam essay) — organization, analysis depth, clarity, citation form. NEVER rewrites the draft. Use when the user says "feedback on my memo", "read my draft", or "critique my brief".

Build or extend a course outline in your format, from class notes and casebook. Scaffolds — it does not write the outline for you. Use when the user says "outline [subject]", "add to my outline", "build an outline from", or points at class materials.

Run a focused N-question study session on a subject — MBE, essay, or flashcards. Tracks performance and updates the study plan. Use when the user says "run me 10 questions on [subject]", "do a session on [subject]", "let's do 5 cards on [subject]", or wants to drill a fixed number of questions and have the plan adapt.

Socratic drilling — it asks, you answer, it pushes back. Does NOT give you the answer until you've earned it. Use when the user says "drill me on", "quiz me", "socratic", "test me on [subject]", or wants to study actively.

Build or update a long-term exam prep (or exam prep) study plan — phases, subjects weighted by weakness, daily session schedule, adaptive to session history in study-plan.yaml. Use when the user says "build a study plan", "plan my exam prep", "schedule my studying", or "how should I study for [X]".

Consolidated workflow layer copied and merged from law-student. Use this skill as the exposed entry point while preserving detailed source workflows under references/source-workflows.

住宿选型 · 美团连接器一手房态价格为主，xhs-explore skill 拉真实住客评价识别水军，online-search（地理搜索） 评估位置。三维评分（位置 × 价位 × 口碑），输出 3-5 个酒店候选给用户挑。

预算平衡与取舍 · 按总预算分配交通/住宿/餐饮/门票/购物/备用六大类，超支时主动给"砍哪天/降哪档/换地点"的取舍建议。基于 price_benchmark.json 城市价格基准做合理性校验。

目的地调研 · 把"江西附近游玩"或"成都"这类输入，转成结构化的目的地候选清单（含特色/季节性/必玩/避雷）。完全调用 search-orchestrator 编排底座，不重复造检索逻辑。