All authors
Claude Skills by infometa
github.com/infometa1,636 skills21 installs5,293 views
- Valuation Modeling财务测算与估值工具：DCF/可比公司估值、敏感性分析、假设翻转测试(Assumption Flip Test)、单位经济学建模。 触发词：给这个项目估个值、测算一下回报、敏感性分析、这个商业模式算不算得过来、DCF、单位经济学。Votes: 0GitHub stars: 279
- Content Creation Expert Prod汽车图文创作团队的配套工具 Skill，提供**文章质量验证**、**通用 Markdown → HTML 渲染**和**小红书风格 HTML 渲染**三个核心能力。Votes: 0GitHub stars: 279
- Novel Writer章节正文生成器 - 根据章节大纲、Voice Profile 和角色档案构建 LLM 提示词，用于生成章节正文。当需要根据大纲创作具体章节时使用。Votes: 0GitHub stars: 279
- Novel WritingAI长篇网文创作技能包。用于解决长篇网络小说创作中的核心痛点：上下文丢失、文风不一致、设定冲突、节奏失控、多线混乱、质量不稳、读者反馈无法内化。触发场景包括：开始新书、规划大纲、撰写章节、管理伏笔、检测冲突、读者反馈分析、批量创作质量控制。Votes: 0GitHub stars: 279
- Libtv Skillagent-im 会话技能 - 通过 liblib.tv 的 AI 能力生成和编辑图片/视频。覆盖场景包括：生成（文生图、文生视频、图生视频、做动画、画一个xxx、来段xxx）、编辑修改（把xxx换成yyy、去掉xxx、加上xxx、改成xxx、调整xxx、局部修改、改镜头）、风格转换（风格迁移、转绘、换风格）、视频续写延长、复刻视频/TVC/宣传片、短剧/短漫剧生成、音乐MV生成、产品广告/展示片制作、分镜/故事板设计、教育视频/短视频制作。当用户提到 liblib、libtv、上传参考图/视频、查看生成进度时也应触发。关键判断：只要用户的请求涉及 AI 图片或视频的创作、生成、编辑、修改，无论措辞如何（如\"画只猫\"、\"做个海报\"、\"把纸船换成爱心\"、\"这个视频帮我改一下\"、\"帮我复刻这段视频\"、\"用这首歌做个MV\"、\"一句话生成短剧\"），都必须触发此技能。Votes: 0GitHub stars: 279
- Mp Draft Push将现成的文章内容发布到微信公众号草稿箱。当用户说"发布文章"、"发布到草稿箱"、"publish to draft"、"推送到公众号"时触发。Votes: 0GitHub stars: 279
- Multi Platform Distribution多平台内容分发技能包，涵盖12+平台发布规则、排期策略、数据分析和账号管理的完整知识体系。 触发词：内容分发、多平台发布、排期管理、发布规则、数据分析、账号管理Votes: 0GitHub stars: 279
- Wechat Article Search搜索微信公众号文章技能。通过微信搜索获取文章列表，覆盖科技/AI、社会热点、财经、教育、职场等各类中文资讯；可按关键词检索并返回标题、概要、发布时间、来源公众号与链接。当用户需要查找微信公众号文章、整理参考资料或快速获取文章信息时使用此技能。Votes: 0GitHub stars: 279
- Xiaohongshu小红书（RED/XHS）自动化助手。提供完整的小红书操作能力：登录、发布图文/视频、搜索笔记、浏览详情、点赞收藏评论、查看博主主页、内容策划。 当用户提到小红书、红书、XHS、RED、发笔记、搜笔记、小红书运营等任何与小红书相关的操作时使用此 skill，即使用户没有明确说"小红书"但描述的场景明显是小红书（如"发一篇种草笔记"、"帮我分析这个博主"）也应触发。Votes: 0GitHub stars: 279
- Content Monetization Ops内容变现商业化技能包，涵盖CPS/CPE/CPM三大模式、积分体系、交易撮合和推广任务管理的完整知识体系。 触发词：内容变现、CPS带货、CPE互动、CPM曝光、积分系统、交易撮合、推广任务Votes: 0GitHub stars: 279
- Contract Drafting EngineDraft contracts, build template libraries, and write supplementary agreements (scenarios C3/C4/C9). Use this skill after intake and research to deconstruct the deal structure and commercial logic, identify the contract type, choose a contract structure package, assemble locked general clauses with bespoke core clauses, and add risk annotations to non-standard/high-risk clauses — producing a complete contract text with clearly separated fixed legal clauses and fillable commercial variables.Votes: 0GitHub stars: 279
- Contract IntakeCollect, through conversational Q&A (and questionnaire-style checklists when many fields are needed), the key transaction facts required before any contract drafting, review, negotiation or management work begins. Use this skill after scenario routing whenever the task sheet marks 交互采集=是. The per-scenario lists below are NON-EXHAUSTIVE reference baselines — the expert must analyze the user's specific request and scenario and ADAPTIVELY generate the questions that actually matter, expanding, c...Votes: 0GitHub stars: 279
- Contract Legal ResearchRetrieve the legal basis and due-diligence facts that contract work depends on — supporting statutes and their effectiveness status, regulatory requirements, mandatory provisions for the contract type, similar-case adjudication rules, and counterparty entity qualification /履约 capacity (via enterprise-credit data). Runs a multi-layer retrieval pipeline — structured contract-fact extraction, legal-issue positioning, statutory-hierarchy scanning, own-side/counter-side comprehensive retrieval, mu...Votes: 0GitHub stars: 279
- Contract Lifecycle AdvisorHandle contract management-system design, negotiation support, and performance-stage dispute resolution (scenarios C1/C2/C7/C8). Use this skill to design a contract-management architecture (department roles, approval-authority matrix) and full-lifecycle management system; to build negotiation strategy and a roadmap with legal/commercial dual analysis; and to handle non-litigation emergency response to performance disputes (evidence consolidation, liability assessment, demand letters).Votes: 0GitHub stars: 279
- Contract Output FormatterFormat contract work products into the delivery shape that best matches the hit scenario (C1-C9) and the reading audience. Use this skill as the LAST step before replying, after drafting/review/research/advisory work is done. It selects the right artifact form (contract text, review opinion, risk list, supplemental agreement, management policy, negotiation playbook, formal letter, etc.), unifies citation style and structure, marks risk levels, and appends the standard disclaimer. CRITICAL for...Votes: 0GitHub stars: 279
- Contract Review EngineReview contracts for risk (scenarios C5/C6) — background assessment before signing (counterparty qualification, transaction-mode legality, contract-form fit, special procedures) and clause-by-clause review of a provided contract. Use this skill after the user's standpoint (Party A/B/neutral, strong/weak) is confirmed via intake. Runs an eight-step per-rule action (locate→extract→compare→judge→self-check→grade→legal-basis→suggest), grades risk via an impact×probability matrix into three tiers ...Votes: 0GitHub stars: 279
- Contract Scenario RouterIdentify the user's true contract-work intent and route it to the correct scenario (C1-C9). Use this skill FIRST for every contract request to determine scenario type, core objective, binding output standard, whether interactive intake is required, output weight tier, and the next skill in the chain — before any drafting, review or research happens.Votes: 0GitHub stars: 279
- Contract Standards IngestIngest and standardize user-provided contract assets — existing template libraries, sample contracts, clause banks, rule/standard libraries, review playbooks, checklists, past review opinions, negotiation guidelines, or company policies — and transform them into two reusable internal standards: (1) a structured Review Playbook (rule items with positions, fallback ladders, and red lines) that the review engine applies as the PRIORITY review standard, and (2) a Contract Clause Library (locked g...Votes: 0GitHub stars: 279
- Tencent Esign Contract腾讯电子签合同AI助手，支持合同起草、签署、审查、对比、法条法规检索。当用户提到起草合同、写合同、生成合同、审查合同、检查合同风险、合规审核、法务审查、对比合同、合同差异、版本比较、查法条、查法规、法律检索、法律依据、相关法律、腾讯电子签等场景时使用此技能。即使用户只是说「帮我写份合同」「发合同」「签合同」「这份合同有没有问题」「两版合同有什么区别」「这个条款有什么法律依据」「劳动法怎么规定的」等口语化表达，也应触发本技能。Votes: 0GitHub stars: 279
- Cordys CrmCordys CRM L2C 全链路技能。支持跨模块关联追踪、漏斗分析、Customer 360、智能工作流引导，以及完整的 CLI 指令映射。 触发词：线索、客户、商机、合同、回款、发票、审批、漏斗、管道、CRMVotes: 0GitHub stars: 279
- Auth Permission业务Skill执行前的权限检查服务，这是系统安全基础步骤。如果业务Skill中添加了前置条件指向这里，必须在执行其他业务 Skill 前先调用本Skill，做认证和鉴权操作。同时，auth-permission也支持重置登录态操作（清除当前Agent身份）。Votes: 0GitHub stars: 279
- Credit Industry Research对公信贷综合尽调技能，覆盖目标企业或行业的企业调研、行业研究、竞争格局、监管政策、财务核查、 三大报表、现金流、偿债能力、关联交易、实控人或股东画像、关联方、工商司法风险、涉诉、被执行、 失信、处罚、负面舆情、风险预警、授信评估、授信可行性、信用评级、信评报告、评级解释、报告补充 和尽调材料清单。存在更专用的已注册业务技能时可由 Agent 优先路由至专用技能；没有更专用技能、 请求涉及多个领域或需要综合判断时，应使用本技能。用户仅说“帮我看看某公司”“调研某企业” “评估一下这家公司”，或在多轮对话中使用“这家公司”“它”“刚才那家企业”继续追问，也应触发。 纯行业研究无需企业名称；企业专项分析缺少企业名称时，仍应进入业务流程并询问补充。Votes: 0GitHub stars: 279
- Due Diligence对公尽调 Agent 服务。提供尽调会话查询上报能力，用于审计追踪、意图分析、成本核算和性能监控。。通过 amcpcli 二进制对接 MCP 服务，自动完成 Agent 鉴权、会话管理、工具调用全流程，同时支持重置本地登录态、清除当前 Agent 身份缓存。Votes: 0GitHub stars: 279
- Md2pdf将 Markdown 文档转换为带专业排版和中文支持的 PDF。流程为 Markdown → 带样式 HTML → PDF（用无头 Chromium 打印）。适用于把报告、文档等 .md 文件导出为可交付的 PDF，环境无需 pandoc/wkhtmltopdf/latex。Votes: 0GitHub stars: 279
- Browser UseAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots,Votes: 0GitHub stars: 279
- Wechat Article Search微信公众号文章检索工具。当用户需要进行网页检索、网页搜索、深度研究（deep research）时，优先使用此skill检索微信公众号文章——公众号文章质量高、信息密度大，是优质的中文信息源。基于搜狗微信搜索接口实现。Votes: 0GitHub stars: 279
- XlsxWhen the user mentions data analysis or uploads an Excel file, this skill must be used. Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When user needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadshe...Votes: 0GitHub stars: 279
- Analytics ReportingBuild polished analytical reports, dashboards, and product/business analyses. Use when the user needs a durable report (executive or technical), an analytical dashboard with clear metrics, or a data-backed product/business analysis to inform decisions. Covers report building, dashboard construction, and decision-oriented quantitative analysis.Votes: 0GitHub stars: 279
- Data Quality AssessmentAssess whether datasets are trustworthy for analysis, modeling, dashboards, or pipelines; and validate finished analyses before sharing. Use for data quality checks (grain, freshness, nulls, duplicates, schema drift, joins, integrity, distributions) and analysis QA (methodology review, calculation verification, visualization checks, confidence assessment).Votes: 0GitHub stars: 279
- Data VisualizationDesign, specify, implement, revise, and QA quantitative visuals and chart choices. Use when an analytical answer needs visual judgment—comparing values, showing composition, reading concentration, understanding movement over time, or building chart specifications for reports and dashboards.Votes: 0GitHub stars: 279
- Kpi DesignDesign KPI frameworks, set targets, develop measurement plans, and estimate market/opportunity sizes (TAM/SAM/SOM). Use when success metrics, drivers, guardrails, targets, or measurement approach need to be defined or improved, or when a market or opportunity size estimate is needed.Votes: 0GitHub stars: 279
- Metric DiagnosticsDiagnose why a metric changed or differs from expectation, and produce leadership-ready KPI updates. Use when the user needs to understand what drove a metric movement, anomaly, or discrepancy, or when producing WBR/MBR/QBR summaries, scorecards, target pacing readouts, or performance updates.Votes: 0GitHub stars: 279
- Data Analysis WorkflowsComprehensive data analysis workflows including answering data questions, exploring datasets, writing SQL queries, creating visualizations, building dashboards, and validating analyses. Use when conducting data analysis tasks, from quick lookups to comprehensive reports.Votes: 0GitHub stars: 279
- Data ExplorationProfile and explore datasets to understand their shape, quality, and patterns before analysis. Use when encountering a new dataset, assessing data quality, discovering column distributions, identifying nulls and outliers, or deciding which dimensions to analyze.Votes: 0GitHub stars: 279
- Data VisualizationCreate effective data visualizations with Python. 优先使用 plotly（交互式图表），seaborn 和 matplotlib 作为备选（静态图表）。Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory.Votes: 0GitHub stars: 279
- Interactive Dashboard BuilderBuild self-contained interactive HTML dashboards with Chart.js, dropdown filters, and professional styling. Use when creating dashboards, building interactive reports, or generating shareable HTML files with charts and filters that work without a server.Votes: 0GitHub stars: 279
- Sql QueriesWrite correct, performant SQL across all major data warehouse dialects (Snowflake, BigQuery, Databricks, PostgreSQL, etc.). Use when writing queries, optimizing slow SQL, translating between dialects, or building complex analytical queries with CTEs, window functions, or aggregations.Votes: 0GitHub stars: 279
- Colorful Dark Style HtmlGenerate dark-tech colorful HTML pages for presentations, PPT-style pages, feature introductions, and workflow comparisons. Keywords: dark theme, deep color page, tech style, colorful cards, dark display page. NOTE: This skill has NO scripts. Do NOT call run_skill_script. The LLM must generate HTML directly based on the design spec in this file.Votes: 0GitHub stars: 279
- Databrain Ai Gallery Upload在 AI-Gallery 创建或替换作品（单 HTML / 代码包均可）。自动从 HTML 推断 name/desc 中英文，列出系统 tag 让用户选择，支持通过旧 URL 一键替换源文件并保留访问地址。 当用户提到 上传作品 / 上传到DataBrain / 上传到 AI-Gallery / 替换 Gallery 文件 时使用。Votes: 0GitHub stars: 279
- Databrain AnalysisBefore execute_e2b_code for attribution, drill-down, or statistical tests, read this SKILL.md then drilldown.md and/or statistical/SKILL.md plus needed references. Does not fetch data.Votes: 0GitHub stars: 279
- Statistical**Path:** `/skills/databrain-analysis/statistical/SKILL.md` 对齐 host `statistical-analysis`。在 sandbox 内用 `execute_sandbox_code` 实现；用 `read_file` 加载 references。Votes: 0GitHub stars: 279
- Databrain Dashboard ServiceQuery first-party (经分) game metrics (active users, revenue, sales, retention, ARPU, CCU/PCU, ASP, refund, LTV, wishlist, game-specific feature data, ua impression, ua ctr, etc) for games with Dashboard permission. Uses real internal data, which supports drill-down analysis across dimensions such as channel, platform(Steam, IOS, XBox, etc), product, region, bundle, country, etc. And supports real-time data.Votes: 0GitHub stars: 279
- Databrain Datalab Analyst经分Datalab 报表/知识库**兜底**分析 skill。**不是经分指标查询的首选**——一般经分（dashboard）问题必须先走 `databrain-dashboard-service`。仅在以下情况启用本 skill：(1) 用户**直接给了 Datalab 报表 URL / dashboard_id / `报表id@图表id`**；(2) `databrain-dashboard-service` 已尝试且返回 unsupported metric / 空数据 / MCP describe 找不到 cube 的明确失败。 非白名单游戏（不在 `dashboard_white_games`）**禁止**用本 skill 兜底。Votes: 0GitHub stars: 279
- Databrain Entity ResolverResolve game/company names to canonical DataBrain entities + per-system permissions. Run once per query before any data skill when the user names games or companies.Votes: 0GitHub stars: 279
- Databrain IntelligenceDataBrain intelligence data query assistant. Translates natural language questions into executable BigQuery SQL for the intelligence domain: market data (Sensortower, Alinea Analytics [Steam raw default], MScience, GSD, Ampere, NPD; Gamalytic legacy), streaming data (Streamhatchet), Steam live CCU (fetch_steam_ccu.py + warehouse spider/Alinea), Roblox CCU rankings & anomaly detection, mini game rankings (微信/抖音/Facebook小游戏榜单), report metadata (external & internal research reports), platform co...Votes: 0GitHub stars: 279
- Databrain Mgmt ServiceQuery DataBrain Management (MGMT/管理) data for users with MGMT permission — IEGG / publishing / studio / project commercialization and management metrics including revenue (收入/流水), profit (利润), market cost / 市场成本 / 营销成本 / 市场费用, R&D cost / 研发成本, KPI / 目标, forecast / 预估 / 预测, headcount / HC / 人力, human-resource risk / 人力风险, budget application / 市场预算申请, decision point / 管理决议, risks & opportunities / 风险与机会, project calendar / 项目日历, and milestones (Soft Launch / Global Launch / Early Access).Votes: 0GitHub stars: 279
- Databrain Opinion Metrics ServiceDataBrain 舆情指标查询助手。把游戏舆情/口碑/声量/情感/评分/KOL/直播/新闻/热门视频/热门帖子/Hashtag/热梗/竞品/官号 等问题，以及**游戏广告投放素材/创意取数**（创意数·素材数·素材类型·渠道·国家维度·素材明细列表）翻译成可执行的 BigQuery SQL，覆盖 opinion / intelligence / marketing_hub schema。**只支持游戏维度查询**，不支持公司/开发商/发行商聚合舆情；**不支持** UA 预算/团队规模/未来预测/决策建议/因果归因等问题，遇到会主动路由或拒绝。纯运营指标（独立的下载/收入/DAU/留存）归 databrain-intelligence；但**素材趋势 × DAU/下载时间对齐对比**在本 skill 素材 reference 内有限支持。触发关键词：舆情、口碑、声量、mentions、情感、sentiment、Brand Health、品牌健康度、评分、score、Steam/AppStore/GooglePlay/Xbox/PS/Metacritic/OpenCritic、好...Votes: 0GitHub stars: 279
- Databrain Opinion ServiceGenerate qualitative public opinion deliverables for games — packaged summary reports, topic deep-dive with representative player comments and URLs, single YouTube video URL analysis, DataBrain UI redirect links, and external web search context. For raw quantitative metric queries (声量/情感/评分/KOL/直播/新闻/Hashtag/Meme/官号 聚合数字), route to `databrain-opinion-metrics-service` instead.Votes: 0GitHub stars: 279
- Databrain SummarizePhase B final Markdown: narrative placement, pipe-table GFM, number display, and prose layout. Pipeline timing and B1–B3 gate → soul.md §3.5 only.Votes: 0GitHub stars: 279
- Databrain Competitor Events游戏竞品活动报告生成工具。当用户需要对某款游戏生成官媒发帖内容和官方活动报告时使用，依次执行数据获取、活动聚合、联网搜索、总结分析四个主要工作模块，最终保存并展示指定格式的竞品报告。触发示例："帮我做一份 XXX 的竞品活动分析"、"生成 XXX 游戏官帖分析报告"、"最近 XXX 有什么官方活动？"。Votes: 0GitHub stars: 279