| 7201 | brandkitImage-generation and art-direction skill for brand-kit boards: logo directions, palette, typography, identity applications, and cohesive visual systems. | thefireKS/thefireKS.github.io | 0 | 2026-06-09 |
| 7202 | testing-enemy-arroganceUse when probing enemy leadership's judgment quality and decision-making state. Based on Zhong's grain-request test against Wu: make a resource request, observe whether wise counsel is heeded or ignored, and interpret the response to assess arrogance and internal divisions for attack timing. | baojie/shiji-kb | 2.3k | 2026-03-25 |
| 7203 | event-prospectingEvent prospecting skill. Takes a conference / event speakers URL,
extracts the people, filters their companies against the user's
ICP, then deep-researches only the speakers at ICP-fit companies.
Outputs a person-first HTML report where each card answers "why
should the AE talk to this person?" with all public links and a
one-click DM opener.
Use when the user wants to: (1) find leads at a specific
conference, (2) prep for an event, (3) research event speakers,
(4) build a target list from a sponsor/exhibitor page,
(5) scrape conference speakers and rank by ICP fit.
Triggers: "find leads at {event}", "research speakers at",
"prospect this conference", "stripe sessions leads",
"ai engineer summit prospects", "event prospecting",
"scrape conference speakers", "who should I meet at". | browserbase/skills | 3.7k | 2026-06-15 |
| 7204 | rnd-android-performance-analyzerAndroid 性能分析专家 - 专业的 Android 系统性能问题诊断与优化。适用场景：(1) 系统性能问题诊断（卡顿/运行缓慢/ANR），(2) 性能数据分析（logcat/systrace/traceview/dumpsys/perfetto），(3) CPU 性能分析（占用峰值/主线程阻塞/死循环/低效算法），(4) 内存性能分析（内存泄漏/GC频率/OOM风险），(5) IO 性能分析（磁盘读写/数据库操作/网络IO），(6) 应用响应性分析（ANR/消息队列阻塞/UI渲染/启动时间），(7) 性能优化方案设计（代码级优化/架构改进），(8) 性能监控与预防方案 | chendongqi/OPB-Skills | 103 | 2026-02-11 |
| 7205 | leetcode-coach算法刷题专属教练 SOP。采用特征映射、模板提取、边界熔断与费曼测试的闭环工作流，结合 LeetCode Hot 100 结构化分类体系，帮助用户系统性地建立算法知识体系。当用户进行 LeetCode 刷题、复习或询问算法解析时激活。 | Decalogue/flyllm | 15 | 2026-03-30 |
| 7206 | motion-graphicsWorld-class motion graphics expertise combining the animation principles of Disney, the kinetic typography of MK12, and the visual storytelling of studios like Buck and Ordinary Folk. Motion graphics transforms static ideas into dynamic visual experiences. Great motion graphics doesn't just move—it communicates. Every animation should have purpose: to guide attention, reinforce message, create emotion, or clarify concept. The best motion designers understand that restraint is power, that timing is everything, and that the animation should be invisible—viewers should feel the story, not notice the effects. Use when "motion graphics, animation, animate, motion design, kinetic, logo animation, title sequence, lower thirds, animated, after effects, lottie, transitions, motion, motion, graphics, animation, after-effects, lottie, kinetic, typography, design" mentioned. | omer-metin/skills-for-antigravity | 114 | 2026-01-22 |
| 7207 | create-portfolio-optimizerCreate a new open-xquant PortfolioOptimizer with weight-invariant tests and registry wiring; use after create-component confirms no existing optimizer satisfies the allocation request. | xingwudao/open-xquant | 102 | 2026-06-26 |
| 7208 | generalized-few-shot-point-cloud-segmentationSegment novel 3D point cloud classes with few support samples by combining dense but noisy pseudo-labels from 3D vision-language models with precise sparse few-shot annotations. GFS-VL adapts to new classes while retaining base class performance, using prototype-guided filtering and adaptive infilling strategies ideal for applications with limited labeled training data. | ADu2021/skillXiv | 6 | 2026-03-26 |
| 7209 | write-reproducerWrite minimal, reliable bug reproducers (repros) for any project. Use when: (1) a bug report or issue needs a test that reliably demonstrates the failure, (2) converting a described failure scenario into runnable code, (3) minimizing an existing complex test to its essential trigger conditions. Covers the full repro workflow: failure characterization, scope selection, writing the repro, verifying it fails for the right reason, and minimizing to the smallest possible trigger. | apache/cassandra | 9.9k | 2026-06-09 |
| 7210 | dknowc-official-doc-writer**深知写作助手** — 必须使用的公文写作技能
**触发条件（满足任一即必须使用本技能）：**
- 用户说"写"、"帮我写"、"起草"、"撰写"、"生成"任何公文
- 提到：通知、请示、函、报告、纪要、总结、方案、发言稿、讲话稿、管理办法等
- 要求：Word文档、公文、正式文书
**功能：** 政策搜索 + 公文撰写 + Word排版（普通/红头）
**支持文种：**
- 法定公文（15种）：决议、命令、公报、公告、通告、意见、通知、通报、报告、请示、批复、议案、函、纪要
- 事务文书：工作总结、年度总结、学习计划、发言稿、讲话稿、管理办法、实施细则、汇报材料等 | 18816132863/xiaoyi-claw-omega-final | 2 | 2026-04-25 |
| 7211 | quarkus-verificationBucle de verificación para proyectos Quarkus: build, análisis estático, pruebas con cobertura, escaneos de seguridad, compilación nativa y revisión de diff antes del lanzamiento o PR. | affaan-m/ECC | 232.1k | 2026-06-07 |
| 7212 | council曖昧な決定、トレードオフ、ゴー/ノーゴーの判断のために4つの声のカウンシルを召集します。複数の有効なパスが存在し、選択前に構造化された異議が必要な場合に使用します。 | affaan-m/ECC | 232.1k | 2026-05-17 |
| 7213 | terminal-ops基于证据优先的仓库执行工作流，适用于ECC。当用户需要运行命令、检查仓库、调试CI失败或推送带有精确执行和验证证明的窄修复时使用。 | affaan-m/ECC | 232.1k | 2026-05-11 |
| 7214 | lenis-smooth-scrollImplement cinematic, momentum-based smooth scrolling using Lenis to eliminate native browser scroll jank. | Ahmet-Talha-Kavakli/ai-body-backend | 0 | 2026-04-12 |
| 7215 | pentest-boundary渗透测试规范边界约束系统 v1.0.0。定义渗透测试的安全红线与操作规范， 确保所有测试活动在安全可控的范围内进行。覆盖：授权边界、速率控制、 操作安全、数据保护、漏洞验证、应急响应、法律合规。 本技能作为约束层，所有渗透测试技能 (SecSkills-main/advsec-plus/api-unauth-fuzz) 在执行任何漏洞检测/利用/验证操作前，必须先加载本规范清单进行安全检查。 违反红线规则的操作直接拒绝执行，并输出违规原因。 | bingook/bingo | 303 | 2026-06-11 |
| 7216 | construction-takeoffAutomated construction quantity surveying from PDF plans using AI. Processes construction drawings, extracts quantities/materials, analyzes competitor solutions via Firecrawl, calculates costs, and generates Excel-based takeoff reports for stakeholder collaboration. | breverdbidder/spd-site-plan-dev | 1 | 2025-12-19 |
| 7217 | planningCreate and manage persistent markdown planning files for structured task execution. Use when the user asks to "create a plan", "track progress", "start a research project", or when a task requires more than 5 tool calls and needs structured phase tracking to stay focused and avoid goal drift. | davila7/claude-code-templates | 29.8k | 2026-02-23 |
| 7218 | context-architectureAudit a codebase and bind every claim it makes about itself to a mechanism that fails when the claim stops being true, so it is legible to people and AI agents. Applies Context Architecture's nine principles: make structure say what the system does, place AGENTS.md at boundaries, codify conventions, and bind every claim the repo makes about itself to a mechanism (compiler, linter, automated tests, review) that fails when the claim stops being true. Works greenfield (a repo born legible) and brownfield (a repo restructured in steps). Use when an agent reimplements code that already exists, invents structure, follows stale or deleted docs, propagates a deprecated pattern, or resolves ambiguity at random, or when asked to make a repository "agent-ready", "AI-legible", or to add or fix AGENTS.md / CLAUDE.md files. | davila7/claude-code-templates | 29.8k | 2026-07-05 |
| 7219 | industry-deep-explainer快速且通俗易懂地讲透一个行业，输出图文并茂的深度分析 Markdown 报告，保存到当前项目的 markdown/ 目录。触发条件：用户输入一个行业名称，并希望获得全面、通俗易懂的行业深度分析，关键词包括"讲透"、"深度分析行业"、"行业分析"、"帮我搞懂XX行业"、"XX行业是怎么赚钱的"、"XX行业有什么机会"、"XX行业怎么进入"、"产业链分析"、"行业机会"等。即使用户只说"帮我了解一下XX行业"或"XX行业值得进入吗"，也应使用本 skill。输出报告覆盖：产业链分布与利润图谱、供给-需求-连接分析、人货场分析、代表企业与产品分析、产业链不合理之处、机会推演与进入策略（产品/服务/目标客户/商业模式/定价/市场规模）、竞争对手与合作伙伴分析，要求逻辑清晰、有理论依据、有历史数据/事件支撑、图文并茂（SVG/Mermaid/ASCII图）。 | digoal/blog | 8.5k | 2026-06-08 |
| 7220 | dingtalk-sheet钉钉电子表格。Use when 用户说 电子表格/导入Excel为在线表格/工作表/单元格读写/单元格追加/查找/公式/超链接/插入图片/浮动图片/sheet。Distinct from dingtalk-aitable(AI表格/多维表/字段类型)、dingtalk-doc(普通文档)。命令前缀：dws sheet。 | DingTalk-Real-AI/dingtalk-workspace-cli | 2.5k | 2026-07-15 |
| 7221 | fitness-plan健身计划生成器。增肌减脂方案、训练计划、饮食建议、运动记录。Fitness plan generator with muscle building, fat loss, workout plans, diet advice. 健身教练、减肥计划、运动方案。Use when creating workout plans. | dvcrn/openclaw-skills-marketplace | 24 | 2026-03-15 |
| 7222 | wordpress-plugin-to-emdashPort a WordPress plugin to EmDash CMS. Use this skill when asked to migrate, convert, or port a WordPress plugin, theme functionality, or custom post type to EmDash. Provides concept mapping and implementation patterns. | emdash-cms/emdash | 11.3k | 2026-05-03 |
| 7223 | polishPerforms a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great. | fengshao1227/ccg-workflow | 5.7k | 2026-03-31 |
| 7224 | mitools-desensitize数据脱敏工具，支持手机号、身份证、银行卡、邮箱、IP地址、中文姓名等多种敏感信息脱敏 | GeorgeDoors888/GB-Power-Market-JJ | 3 | 2026-04-16 |
| 7225 | research-citation-check当用户明确要求"核查/优化综述 `{主题}_review.tex` 的正文引用"、"运行 research-citation-check"，或要求使用旧名 check-review-alignment skill 时使用。通过宿主 AI 的语义理解逐条核查引用是否与文献内容吻合，只在发现致命性引用错误时对"包含引用的句子"做最小化改写，并优先复用 `research-literature-review` 的渲染脚本输出 PDF/Word，过渡期允许 fallback 到旧名 systematic-literature-review。核心原则：不为了改而改，无法确定是否为致命性错误时保留原样并在报告中警告。⚠️ 不适用：用户只是想生成系统综述正文（应使用 research-literature-review）；用户只是想新增/核对 BibTeX 条目（应使用专门的 bib 管理流程）。 | huangwb8/ChineseResearchLaTeX | 2.5k | 2026-07-17 |
| 7226 | geo-optimizer生成式引擎优化专家，分析和优化内容在 AI 搜索引擎（ChatGPT、Claude、Perplexity、Google SGE）中的可见性和引用率。 | huifer/claude-code-seo | 109 | 2026-01-04 |
| 7227 | excel-pivot-wizardCreate advanced Excel pivot tables with calculated fields and slicers.
Use when building data summaries or creating interactive dashboards.
Trigger with phrases like 'excel pivot', 'create pivot table', 'data summary'. | jeremylongshore/claude-code-plugins-plus-skills | 2.5k | 2026-07-17 |
| 7228 | creative-eyeGive AI agents creative judgment and design taste. Use when: (1) creating any visual content — merch, social posts, ads, product photography, brand materials, (2) evaluating creative quality before publishing, (3) building a reference library or style guide, (4) setting up creative quality gates, (5) training an agent to develop aesthetic judgment. Triggers: 'review this design,' 'is this good enough to post,' 'creative quality,' 'design feedback,' 'brand consistency,' 'visual audit,' 'creative evaluation,' 'design taste,' 'aesthetic judgment,' 'pre-publish check.' | LeoYeAI/openclaw-master-skills | 2.1k | 2026-05-05 |
| 7229 | ecom-details-imageCreate visual concepts, image-generation prompts, and optional AI-generated images for product hero images, marketing creatives, social posts, ads, ecommerce PDP visuals, and general visual design tasks. Use when the user asks for visual strategy, image prompt writing, product/marketing image direction, or direct text-to-image generation with their own OpenAI-compatible API. | liangdabiao/ecom-details-image | 692 | 2026-05-15 |
| 7230 | soccer-lottery足球分析与足彩预测助手：赛事抓取 → 战意分析 → 赔率走势 → 状态历史 → 三维加权 → 信心输出。
触发关键词：今日推荐、怎么买、足彩分析、足球预测、胜平负、让球、赔率截图、盘口波动、变盘、以我图为准。
核心逻辑：基于【战意分析40% + 赔率走势35% + 状态历史25%】三维加权模型输出方向与信心；赛季末段权重可调整为【战意50% + 赔率35% + 历史15%】；**不主动检索赔率**，赔率由用户提供；**用户自带多场赔率截图** 时仅以图中赔率为准做 **波动分析**，不联网替数。 | liming199364/soccer-lottery | 50 | 2026-05-25 |
| 7231 | cinematic-prompt电影级全流程提示词生成。用户给出故事主题，一键生成完整 markdown 文件，包含：角色设定提示词、场景提示词、完整剧本、分镜表、每个分镜的视频生成提示词。支持 Seedance 2.0 / 即梦 / Midjourney / SD。触发词：分镜、提示词、prompt、镜头、脚本、剧本、视频生成、电影风格、Seedance、生成剧本。 | LingyiChen-AI/image-prompts | 64 | 2026-04-02 |
| 7232 | desktopElectron desktop development guide — IPC handlers, controllers, preload scripts, window/menu management. | lobehub/lobehub | 80.7k | 2026-07-02 |
| 7233 | cfo财务总监专家，精通财务规划、预算管理、成本控制、投融资和税务筹划 | lotosbin/claude-skills | 13 | 2025-12-28 |
| 7234 | cv-research-copilot针对深度学习与医学图像分割（Medical Image Segmentation）方向的科研辅助。适用于准备高水平期刊投稿的专业研究人员。当用户提到“想个 idea”、“结合论文代码”、“科研创新”、“跑实验”或“优化模型架构”时触发。 | Luious-LYH/DepthPolypSegmentation | 0 | 2026-03-23 |
| 7235 | chat-perfRun chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline. | microsoft/vscode | 187.8k | 2026-07-13 |
| 7236 | machine-learningPython machine learning with scikit-learn, PyTorch, and TensorFlow | midudev/autoskills | 6.6k | 2026-04-24 |
| 7237 | simulation机器人仿真环境 — Gazebo/Mujoco/Isaac Sim 对比、仿真-真实差距、时钟同步，适用于所有仿真需求 | MIUAV/vibe-coding-ros2 | 21 | 2026-04-05 |
| 7238 | a-stock-monitorA股量化监控系统 - 7维度市场情绪评分、智能选股引擎（短线5策略+中长线7策略）、实时价格监控、涨跌幅排行榜。支持全市场5000+股票数据采集与分析，多指标共振评分，精确买卖点计算，动态止损止盈。每日自动推荐短线3-5只、中长线5-10只优质股票。包含Web界面、自动化Cron任务、历史数据回溯。适用于A股量化交易、技术分析、选股决策。 | modbender/skill-library-mcp | 10 | 2026-03-06 |
| 7239 | news-writing新闻素材收集、整理、写作、排版与校对的完整工作流。用于用户需要生成新闻稿、快讯、深度稿、企业新闻、活动报道，或需要对现有新闻内容进行事实核实、结构优化、标题导语改写、版式统一与发布前审校时。 | modbender/skill-library-mcp | 10 | 2026-03-06 |
| 7240 | material-ui-tailwindIntegrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges. | mui/material-ui | 98.6k | 2026-06-29 |
| 7241 | org-design-toolkit组织设计交付物生成器 v2.0 — 面向中小企业组织咨询场景的 AI 副驾驶。 通过 2 轮极简对话（仅需 2 个核心输入：经营创利流程 + 行业）采集企业信息，自动产出"三张分工矩阵 + 工作分析表合集 + 组织设计预览"五件套交付物。 10 项核心特性： ① 启动时强制 RAG 关联文件夹的官方分工矩阵案例对齐格式； ② 矩阵拆为三张表（公司级 / 部门级 / 岗位级）； ③ RACI 编码本地化：部门级用「主责/参与/监督」中文，岗位级用 R/A/I 字母； ④ 每行必填「产出表单」列（从"经验治理→流程治理"的物理载体）； ⑤ 按完整创利流程顺序排列（不是按抽象主题）； ⑥ 岗位矩阵增「部门职责权限」承上启下列，确保表 1 表 2 自动一致； ⑦ 内置精品包装/外贸出口/双工厂总部+工厂等子行业模板； ⑧ 三个专项动作（客户产品流程图对接 / 外部资源转内部 / 双工厂协同）； ⑨ 支持增量迭代（v1→v2→v3 版本机制）； ⑩ 七道质量闸（RACI 完整性、A 数过载、KPI 可量化、表间一致、行业适配、产出表单完整、流程顺序对齐）。 v2.0.3 起对话流程从 10 轮简化为 5 轮融合版（默认 12-18 分钟）+ 3 轮极简版（快速通道）。 v2.0.4 起明确为「跨 AI Agent / LLM 通用工具」：原生支持 Claude Code，可移植到 Cursor / Cline / ChatGPT GPTs / 本地 LLM 等，详见 PORTABILITY.md。 v2.0.5 起**输入极简化**：核心输入仅 2 项——「经营创利流程」+「行业」，其他字段（企业简称/规模/战略/架构/岗位/事项/KPI/表单）由 RAG + 行业模板自动推导，咨询师只需一次 review 拍板。对话从 5 轮简化为 2 轮（5-10 分钟）。
触发条件：用户说"做分工矩阵""出工作分析""组织设计交付""部门分工矩阵""岗位分工矩阵""分工手册""部门职责""岗位职责书" 或在组织咨询场景下提到"分工 / 岗位 / 部门"等关键词时使用。
适用场景：中小企业（50~500 人）的组织设计、组织变革、分工梳理、职责归位项目，服务对象为咨询师本人。 | namucoxc/org-design-toolkit-nmc | 1 | 2026-05-16 |
| 7242 | ai-short-dramaAI 短剧分镜脚本生产管线。从剧情头脑风暴 → 画风与人设建议 → 人物生图提示词（GPT Image / Nano Banana）→ 分镜拆解 → 中英双语台词 → 转场与运镜指导 → 产物归档。专为 AI 视频工具（Seedance、Runway、Kling 等）优化，规避真人版权、保证多镜头一致性、降低 AI 生成不确定性。触发词：「生成 AI 短剧脚本」「写个短剧」「做短剧分镜」「短剧角色画像」「打磨剧本」。 | NealST/blog-source | 1 | 2026-06-03 |
| 7243 | shopify-dropshippingDropshipping setup and scaling — supplier integration, automation, pricing strategy, customer experience | nexscope-ai/eCommerce-Skills | 446 | 2026-04-10 |
| 7244 | feishu-troubleshoot飞书插件问题排查工具。包含常见问题 FAQ 和深度诊断命令（/feishu_doctor）。
常见问题可随时查阅。诊断命令用于排查复杂问题（多次授权仍失败、自动授权无法解决等），
会检查账户配置、API 连通性、应用权限、用户授权状态，并生成详细的诊断报告和解决方案。 | nexu-io/nexu | 3.2k | 2026-03-16 |
| 7245 | design-briefParse a structured design brief written in I-Lang protocol format into a
concrete design spec. Eliminates ambiguity from vague requests like
"make it professional" by requiring explicit dimensions: palette, typography,
layout, mood, density, and constraints.
Trigger keywords: "design brief", "create a design brief", "ilang brief", "structured brief". | nexu-io/open-design | 80.6k | 2026-07-18 |
| 7246 | huashu-slidesA career-pivot story from consultant to product leader — the arc, the proof, and why the next role is the right bet. Built as a decision-grade career deck for hiring manager, mentors. | nexu-io/open-design | 80.6k | 2026-07-14 |
| 7247 | director-shot-language-skill导演分镜与镜头语言知识库。用于把剧本/场景转成有明确主体、主体表现、机位角度、构图、焦段、光圈、运镜、前中后景、灯光、转场、轴线、情绪服务、长对话、打斗、长叙事设计的可拍摄分镜提示词。核心铁律：每个镜头都必须回答“这一秒观众必须看到的那一个信息是什么？” | storyverse2025/canvas_timeline | 0 | 2026-05-05 |
| 7248 | enterprise-b2b-sales-masterB2B 大客户销售 (B2B 大客户销售 / 企业级复杂销售 (Enterprise B2B Sales / Complex Selling) — 面向企业客户的高价值、长周期、多干系人复杂销售的职业认知操作系统，从业者(AE/客户经理/SE 售前/销售负责人 VP Sales/CRO)、想入行者、以及服务这行(销售咨询/enablement/RevOps)的视角。覆盖: (a) 第一性张力 — 三大方法论流派之争: **买方主导的诊断式提问 (consultative/discovery-led: SPIN 提问 → 痛点 → 方案, 「像医生先诊断再开方」) ⇄ 卖方主导的教学式挑战 (Challenger: Teach-Tailor-Take control, 用商业洞见 reframe 客户认知, 「像老师挑战客户的既有想法」) ⇄ 资格审查纪律 (MEDDIC/MEDDPICC: 先严格 qualify/disqualify, 「no deal 好过 bad deal」)**; 三派不是非此即彼, 资深人混用, 但底层世界观分歧真实(问 vs 教 vs 筛); 更深层张力 — 「过程/方法论纪律 (process rigor: 预测准确、deal inspection、qualify) ⇄ 关系/信任 (relationship: champion 培养、高管关系、人情)」, 「卖结果/业务价值 (business outcome/ROI、卖给经济决策人) ⇄ 卖产品/功能 (feature selling)」, 「多线程触达买方委员会 (multithreading buying committee) ⇄ 单一 champion 依赖」; (b) 方法论正典 (最标准化、最易蒸出高质量+CLI 化) — MEDDIC/MEDDPICC (Metrics 量化指标/Economic buyer 经济决策人/Decision Criteria 决策标准/Decision Process 决策流程/Identify Pain 痛点/Champion 内部拥护者 + Paper process 签约流程/Competition 竞争), SPIN (Situation/Problem/Implication/Need-payoff 提问序列), Challenger (商业洞见 commercial insi | swaylq/master-skill | 108 | 2026-06-11 |
| 7249 | management-consulting-master管理咨询 (管理咨询 (Management Consulting) — 战略与管理咨询的职业认知操作系统，从业者/咨询顾问/想入行者/采购咨询服务的客户视角。覆盖: (a) 第一性张力 — 假设驱动 (hypothesis-driven / answer-first / Day-1 answer) 的「先有答案再验证」⇄ 数据驱动 (data-led / bottom-up) 的「先穷尽事实再归纳」，这行的核心张力是「先射箭再画靶 vs 先画靶再射箭」，资深人偏 top-down 假设树减少 boil-the-ocean，但要时刻防 confirmation bias; 以及更深层的张力 — 「卖洞见 (insight / so-what) vs 卖工时 (analysis / 体力)」，「客户影响 (client impact / 落地) vs 智识严谨 (intellectual rigor / 漂亮 deck)」; (b) 方法论正典 (最标准化、最易蒸出高质量) — MECE (相互独立完全穷尽)、issue tree / logic tree (问题树/逻辑树)、hypothesis-driven problem solving (假设驱动)、Pyramid Principle (Minto 金字塔原理: SCQA 情境-冲突-疑问-回答 + 结论先行 + 自上而下 + 归纳/演绎)、80/20 (帕累托/抓大放小)、so-what (所以呢/洞见提炼)、storyline (故事线/ghost deck 鬼影稿)、driver tree / profit tree、2x2 矩阵、value chain、frameworks (Porter 五力/3C/4P/7S/BCG 矩阵/价值链) 既是脚手架也是陷阱 (套框架 vs 真洞见); (c) 行业结构 — MBB (McKinsey/BCG/Bain 战略三巨头) vs Big Four 咨询臂 (Deloitte/PwC Strategy&/EY-Parthenon/KPMG) vs 精品战略所 (Oliver Wyman/Kearney/Roland Berger/L.E.K./Arthur D. Little) vs 专业/职能 boutique (运营/数字化/PE 尽调); up-or-out (非升即走)、leverage model ( | swaylq/master-skill | 108 | 2026-06-10 |
| 7250 | study-abroad-consulting-master留学咨询规划 (留学咨询规划) Master OS — automated mastery of 留学咨询规划: top builders' mental models, tool stack, current workflows, jargon, and where to keep up.
Trigger this skill when the user works on 留学咨询规划 problems and wants industry-grade thinking, tool selection, or workflow guidance.
触发词：「留学咨询」「留学规划」「出国留学」「study abroad」「留学」 | swaylq/master-skill | 108 | 2026-05-24 |
| 7251 | novel-innovation网文创新、反套路与融合引擎。当用户需要创新写法、设计反套路、融合多种题材、植入热梗、规避AI写作陷阱时触发。覆盖类型融合相容性矩阵、30+反套路设计、2026网文趋势、AI辅助写作常见陷阱。 | uu201/character-arc | 405 | 2026-06-23 |
| 7252 | arkcli-plansARK 套餐管理(Agent Plan / Coding Plan,个人版 + 企业版):查询持有 / 购买 / 续费 / 模型清单 / 轮换 APIKey,**以及企业版席位的全部管理操作**:列出席位(`plans team seat-list`)、给员工分配席位(`plans team seat-assign`)、查谁绑了哪个 seat、轮换席位 APIKey(`plans team rotate-apikey`)。命中关键词:套餐 / 买 / 续费 / 列席位 / 看 seat 绑定 / 谁绑了哪个 seat / 给员工分席位 / 解绑 / 团队席位 admin 视图 / 轮换 APIKey。**用量类问题(还剩多少额度 / 用了几成 / 每个 seat 用了多少)走 [arkcli-usage](../arkcli-usage/SKILL.md)。**动词路由:**列 / 绑 / 分 / 轮换 / 解绑** → 这里;**用 / 消耗 / 多少** → arkcli-usage。另含 harness-status:只读查看本机 AI Agent(claude-code/codex/opencode/openclaw/trae)上 Agent Plan 内置 MCP(豆包搜索/dataPro/OpenViking)装没装、key 就没就绪;命中:我的 MCP 装好了吗 / 查 MCP 安装状态 / 看 agent 上的 MCP / harness 状态。 | volcengine/ark-cli | 82 | 2026-07-01 |
| 7253 | code-review-graphToken-efficient code review using Tree-sitter AST graphs and MCP. Cuts AI token usage on large codebases by computing the blast radius of changes instead of reading entire codebases. Uses a SQLite graph database for structural analysis. | vudovn/ag-kit | 7.8k | 2026-07-18 |
| 7254 | autocad-agentAutomate AutoCAD drafting and CAD workflows through doc-driven execution: discover installed AutoCAD/Core Console/API access, retrieve official/local command and API documentation, generate AutoLISP, scripts, .NET guidance, DXF transformations, or command sequences, validate drawings, diagnose blockers, and search trusted Autodesk forums when needed. Use when Codex is asked to create, modify, batch process, debug, or explain AutoCAD drawings, DWG/DXF files, layers, blocks, dimensions, plotting, standards checks, or CAD automation. | walterkken/doc-driven-engineering-software-skills | 4 | 2026-05-20 |
| 7255 | research-wikiPersistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern. Use when user says "知识库", "research wiki", "add paper", "wiki query", "查知识库", or wants to build/query a persistent field map. | wanshuiyin/Auto-claude-code-research-in-sleep | 13.7k | 2026-07-14 |
| 7256 | catia-automationUse when automating CATIA V5 engineering drawings, exploded views, multi-view PDF generation, A1 detail drawings, detail-page PDFs, or when using the local CATIA Drawing Assistant software. | wccjitou-lgtm/catia-drawing-assistant | 3 | 2026-05-26 |
| 7257 | financial-dataAI Berkshire skill: 财务数据获取与交叉验证规范. Source: skills/financial-data.md. | xbtlin/ai-berkshire | 13.7k | 2026-07-17 |
| 7258 | md-report-summary生成高质量 Markdown 周报、工作汇报、总结、介绍等文档。无草稿时从 Web 搜索并总结；有草稿时结合草稿整理、润色、补充。当用户提到周报、工作汇报、总结、介绍、述职、复盘时使用。 | xstongxue/best-skills | 2.4k | 2026-07-19 |
| 7259 | repo-analyzerUse when the user mentions "分析项目"、"分析仓库"、"分析 GitHub"、"项目分析"、"源码分析"、"架构分析"、"代码分析"、"学习这个项目"、"研究这个框架"、"看看这个库怎么实现的"、"对比两个项目"、"项目评测"、"框架评测" | yzddmr6/repo-analyzer | 454 | 2026-04-07 |
| 7260 | paper-deck将论文、技术文章或知识内容制作成高真实感的 AIGC 幻灯片。先做叙事结构和逐页视觉导演，再调用生图模型生成每一页 16:9 slide image，最后合成为 PPTX/PDF。适合论文汇报、组会、公开课、技术分享、商业化研究展示；当用户提到“论文PPT”“AI生成PPT”“不像AI的PPT”“高质感幻灯片”“逐页生图PPT”时使用。 | zsyggg/paper-craft-skills | 878 | 2026-05-27 |
| 7261 | pdf-converterConvert PDF files to and from Word, Excel, Image, and other formats | claude-office-skills/skills | 319 | 2026-01-30 |
| 7262 | react-expertUse when building React 18+ applications in .jsx or .tsx files, Next.js App Router projects, or create-react-app setups. Creates components, implements custom hooks, debugs rendering issues, migrates class components to functional, and implements state management. Invoke for Server Components, Suspense boundaries, useActionState forms, performance optimization, or React 19 features. | Jeffallan/claude-skills | 10.7k | 2026-04-29 |
| 7263 | vue-expertBuilds Vue 3 components with Composition API patterns, configures Nuxt 3 SSR/SSG projects, sets up Pinia stores, scaffolds Quasar/Capacitor mobile apps, implements PWA features, and optimises Vite builds. Use when creating Vue 3 applications with Composition API, writing reusable composables, managing state with Pinia, building hybrid mobile apps with Quasar or Capacitor, configuring service workers, or tuning Vite configuration and TypeScript integration. | Jeffallan/claude-skills | 10.7k | 2026-04-29 |
| 7264 | seedreamGenerate AI images using Volcengine Seedream model. Supports text-to-image (T2I), image editing (I2I), multi-image fusion, and web-search-based generation. Use this skill when the user wants to create, generate, or edit images. | netease-youdao/LobsterAI | 5.6k | 2026-03-02 |
| 7265 | pdf-converterPDF converter powered by MinerU — convert PDF to Word, Markdown, HTML, LaTeX, or plain text. Also handles image-to-text OCR, scanned document recognition, and Office formats (DOCX, PPTX, Excel). Supports 80+ languages. Use this skill when the user wants to convert, extract, read, parse, or summarize any PDF or document. Also applies when the user shares a PDF file or link and asks about its content, needs tables or formulas extracted, wants PDF OCR, or says things like 'turn this into a doc' or 'what does this paper say'. | tanis90/pdf-converter-mineru | 46 | 2026-05-15 |
| 7266 | taxue-job-search按地区、学历、企业类型精准搜索真实在招岗位，交叉验证多来源。不是职业建议，是查招聘信息。Search real job listings by region, education, employer type with cross-validation.
When to use / 适用场景: 搜招聘、找岗位、有没有招聘信息、有招人的吗、国企招聘、招聘、岗位、在招、报名、招人、XX市有没有招XX的、专科能报什么、帮我搜一下XX岗位、BOSS直聘上搜一下、有没有在招XX的。
EN: "job listings", "hiring near me", "job search", "who's hiring", "government jobs", "recruitment".
Not for / 不适用: 改简历 → taxue-career-resume、职业方向 → taxue-career-direction、投递渠道选择 → taxue-career-channel。 | taxueseek/taxueskills | 20 | 2026-07-06 |
| 7267 | python-observabilityPython observability patterns including structured logging, metrics, and distributed tracing. Use when adding logging, implementing metrics collection, setting up tracing, or debugging production systems. | wshobson/agents | 38.1k | 2026-05-22 |
| 7268 | rust-patternsIdiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications. | affaan-m/ECC | 232.1k | 2026-06-07 |
| 7269 | instagram-post-commentsFetches comments from an Instagram post including comment text, username, timestamp, like count and reply count. Use when user mentions Instagram comments scraping, get comments from Instagram post, Instagram comment list, pull Instagram comments, read Instagram comments, Instagram post discussion, extract Instagram comments, comment data from Instagram, IG post replies, who commented on Instagram. | browser-act/skills | 4.6k | 2026-05-25 |
| 7270 | ctf-ai-mlProvides AI and machine learning techniques for CTF challenges. Use when attacking ML models, crafting adversarial examples, performing model extraction, prompt injection, membership inference, training data poisoning, fine-tuning manipulation, neural network analysis, LoRA adapter exploitation, LLM jailbreaking, or solving AI-related puzzles. | ljagiello/ctf-skills | 2.8k | 2026-04-17 |
| 7271 | glabGitLab workflow automation using glab CLI | gitlabhq/gitlabhq | 24.5k | 2026-07-07 |
| 7272 | tencent-ima-copilot-legal-consultation以资深律师分阶段办案思维，结合 RAG 法律知识库检索，为用户提供法律问题初步诊断与行动策略。当用户描述法律纠纷、咨询"怎么办""能不能告""会不会坐牢"、询问欠钱不还/被起诉/打官司/维权/赔偿/工伤/交通事故/租房纠纷/遗产继承/离婚/合同纠纷/消费者权益/公司劳动争议等场景，或要求分析合同/侵权/劳动/家事/行政/公司股权问题，或上传法律文件时触发。不适用于出具正式法律意见书、代写文书或替代律师出庭。支持分层精读策略、多轮换词搜索、结构化引用清单（含效力状态标注）、快速/专家双模式。内置反幻觉保障机制（绝对溯源+时效性验证+幻觉自检清单），确保法条引用可溯源、案例裁判经核验、失效法条自动标注。 | legalskill/legalskill | 7 | 2026-06-07 |
| 7273 | storyboard-scene-breakdown用于把爆款视频、参考图、截图或文字描述拆解成可复刻的 AI 视频/图像提示词。适用于“反推提示词”“复刻视频”“画面结构拆解”“逐帧拆解”“时间线”“空间关系”“镜头轨迹”“分镜分析”等场景。不输出标签词堆砌,而是输出时间切片、构图机位、主体动作、光影方向、环境纵深和镜头运动。 | 2799662352/ai-image-master | 1 | 2026-07-10 |
| 7274 | character-developmentBuild complete character profiles with psychology, backstory, arcs, and visual design for film/TV | a5c-ai/babysitter | 1.6k | 2026-06-01 |
| 7275 | lpd-pentestingHow to pentest Line Printer Daemon (LPD) services on port 515/tcp. Use this skill whenever you need to assess printer security, test LPD/LPRng implementations, enumerate printer services, or exploit LPD vulnerabilities. Trigger this skill for any task involving port 515, printer exploitation, LPRng testing, network printer security assessments, or when you discover an LPD service during reconnaissance. | abelrguezr/hacktricks-skills | 19 | 2026-03-23 |
| 7276 | afaAFA DTC 全链路独立站操盘系统——系统入口、一级路由器、工作流编排器，统筹品牌基建、付费获客、有机增长、变现留存、运营扩张五大业务线。Use when user mentions: 独立站, DTC, 电商, ecommerce, Shopify, 品牌站, 独立站运营, DTC品牌, 全链路, 操盘, 独立站诊断, 独立站增长, 独立站策略. | afadtc/afa-dtc-skills | 123 | 2026-05-07 |
| 7277 | hermes-importsHermesデータインポート、マッピング、変換、およびデータインテグリティ検証。 | affaan-m/ECC | 232.1k | 2026-05-17 |
| 7278 | investor-materials投資家向けマテリアル、ピッチデック、財務プレゼンテーション、およびビジネス概要。 | affaan-m/ECC | 232.1k | 2026-05-17 |
| 7279 | data-analysisStatistical data analysis skill — use when the user asks to analyze numbers, compute statistics, or summarize datasets. | agentscope-ai/agentscope-java | 4.6k | 2026-06-17 |
| 7280 | partnerships-architectUse when a startup is approached by a prospective partner and someone has to decide should we sign this partner, at what partner tier (referral / reseller / OEM / SI-consulting / strategic alliance), with what joint GTM commitment, and at what revshare. Classifies partner tier from independent-demand evidence vs. preferential-terms hunting, designs a 90-day joint GTM plan, models revshare against direct-sale margin, and surfaces kill criteria for unwinding under-performing partnerships. For Head of Partnerships, Head of BD, and Founder-CEOs doing reseller agreement, OEM deal, or strategic alliance review — not technical sale enablement, not channel cost economics, not M&A. | alirezarezvani/claude-skills | 23.0k | 2026-06-11 |
| 7281 | ai-content-writer文案诊断助手适合内容创作者、市场营销、运营、内容媒体在用户提出“这段文案能打动人吗”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成内容诊断、优化建议、执行清单。 | allinherog-star/ai-skills | 42 | 2026-05-25 |
| 7282 | nsfw-content-generationGenerate NSFW and adult content using each::sense API with safety checker disabled. Supports artistic nude, glamour, boudoir, fantasy, and mature themed content creation with full creative freedom. | antgroup/Agent3Sigma-Canary | 32 | 2026-05-14 |
| 7283 | strategy-agentMarket strategy analyst performing SWOT, competitive positioning, market-timing assessment, and go-to-market recommendations from research findings. Use after the research-agent has produced market data. | Atmosphere/atmosphere | 3.8k | 2026-05-05 |
| 7284 | swagger-writer专门为 Go handler 编写和补全 godoc-swagger 注释，严格对齐本项目 swag 风格与字段顺序。 | bamboo-services/bamboo-main | 0 | 2026-02-14 |
| 7285 | sima-qian-style将现代文本改写为司马迁《史记》文笔风格。
**触发场景**（主动使用）：
- 用户明确要求"用太史公文笔改写"、"以史记风格写..."、"太史公曰"、"列传体"
- 用户要求将现代文本转为文言文，且强调古雅、简洁、有文史韵味
- 用户提供人物传记、历史事件、技术概念等素材，要求古风改写
- 用户询问"司马迁会怎么写这件事"
**功能**：
- 三层转换：现代名词古化 → 白话转文言 → 太史公风格
- 应用《史记》特有句式（开篇定式、层递并列、简短断言、对话穿插动作等）
- 应用《史记》修辞（白描、先抑后扬、排比对仗、跳跃式剪辑等）
- 可选输出"太史公曰"评论段（50-80字精简版）
**不做什么**：
- 不复述《史记》原文内容
- 不模拟司马迁的历史观点
- 不套用《史记》名句
- 只学习语言形式、句法结构、修辞节奏
本技能基于《史记》130篇语料分析，适用于人物传记、历史事件、技术概念等现代素材的古风改写。 | baojie/shiji-kb | 2.3k | 2026-04-05 |
| 7286 | linux-yoctoUse when configuring, building, or debugging a Yocto Project-based Linux distribution for embedded targets. Covers BitBake, bblayers.conf, local.conf, recipe files (.bb / .bbappend), layers, image recipes, devtool, SDK generation, and common BSP layer patterns for automotive IVI, HUD, and RSE targets. | Binh230199/ai | 1 | 2026-03-14 |
| 7287 | test-case-design测试用例设计 — 覆盖正常路径、边界条件、异常路径、合规校验、性能安全 5 大类用例。开发前需定义验收标准、为测试团队提供输入时调用本 skill,确保 BRD 功能点全部可验证。 | BlueprintOS/analysis-to-delivery | 24 | 2026-06-26 |
| 7288 | taobao-shop-catalogBrowse a Taobao or Tmall shop's product catalog by shopId, returning paginated product listings with itemId and title. Use when user asks to scrape a Taobao shop, get all products from a store, list items in a Taobao/Tmall shop, fetch shop catalog by userId or shopId, 采集淘宝店铺商品, 抓取淘宝店铺所有商品, 获取天猫店铺商品列表, 淘宝店铺目录, 按店铺ID采集商品. Also applies to shop inventory monitoring, competitor store analysis, and bulk itemId collection from a specific seller. | browser-act/skills | 4.6k | 2026-06-10 |
| 7289 | paper-reading-assistantAI-assisted paper reading, PDF Q&A, and summarization workflows | brycewang-stanford/Auto-Empirical-Research-Skills | 3.0k | 2026-04-03 |
| 7290 | game-theory-paper-writerGenerate, continue, revise, polish, and stress-test game theory research papers. Use when the user provides a game theory topic, phenomenon, draft, outline, model idea, literature anchor, reviewer comments, or asks for 博弈论论文生成, 选题建模, 文献迁移, 模型修正, 均衡分析, 数值模拟, 论文润色, 改稿打磨, or R&R response work. | brycewang-stanford/Auto-Empirical-Research-Skills | 3.0k | 2026-06-15 |
| 7291 | wechat-article-ingest微信公众号文章 → Markdown 提取 + A层观点提取 + B层问题链生成。 支持直接链接抓取和 PDF 提取两种方式。 | chubbyguan/chubbyskills | 564 | 2026-06-30 |
| 7292 | xianyu-reply-cy闲鱼自动回复助手，通过 Playwright 驱动真实 Chrome 浏览器监控闲鱼网页版消息并自动回复买家咨询。 当用户说"开始闲鱼自动回复"、"监控闲鱼消息"、"闲鱼客服"、"闲鱼回复"时触发。 | CY-CHENYUE/xianyu-reply-cy | 7 | 2026-03-10 |
| 7293 | prompt-engineerExpert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when: prompt engineering, system prompt, few-shot, chain of thought, prompt design. | davila7/claude-code-templates | 29.8k | 2026-01-25 |
| 7294 | file-organizerIntelligently organizes files and folders by understanding context, finding duplicates, and suggesting better organizational structures. Use when user wants to clean up directories, organize downloads, remove duplicates, or restructure projects. | davila7/claude-code-templates | 29.8k | 2026-01-25 |
| 7295 | ashare-news-fetcher抓取 A 股消息面情报：从财联社、华尔街见闻、金十、新浪 7x24、东财快讯、 证监会/央行/上交所/财政部政策公告、东方财富股吧等公开来源抓取与股票相关的 新闻、政策、情绪，输出结构化 JSON 或 Markdown。 当用户提到“A 股消息面”、“抓新闻”、“个股消息”、“政策监管”、“股吧情绪”、 “财联社”、“东财快讯”、“市场情绪”或需要把某只股票相关的公开情报聚合出来时 触发。也适用于“帮我看看 000001 最近有什么消息”这类口语化请求。 | daymade/claude-code-skills | 1.3k | 2026-06-28 |
| 7296 | ponytail-helpQuick-reference card for all ponytail modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail". | DietrichGebert/ponytail | 87.7k | 2026-07-01 |
| 7297 | teacher-prep教师备课助手，用于小学语文教学备课。支持古诗、现代文、寓言、童话等各类课文。当用户提出备课需求时，自动执行：(1)搜索课文相关资料（原文、作者、背景、生字词、段落分析等），生成markdown备课资料；(2)生成教案PPT；(3)生成Word格式课后练习题及参考答案。适用于小学各年级语文备课场景。 | dvcrn/openclaw-skills-marketplace | 24 | 2026-03-15 |
| 7298 | pdf-translateTranslates PDF documents to Chinese with professional typography. Extracts text, translates section-by-section into well-structured Markdown, then generates PDF via weasyprint with full CJK support. Use when user asks to translate a PDF, says "翻译PDF", "translate this document", or "pdf translate". | dvcrn/openclaw-skills-marketplace | 24 | 2026-03-15 |
| 7299 | medlit-research医学文献检索、批判性评价与综合分析。支持PubMed/Embase/Cochrane多数据库检索、PMC全文获取、AI辅助分析、研究质量评价、系统综述写作。使用场景：(1)检索多数据库医学文献，(2)自动获取PMC开放获取全文，(3)基于全文的深度批判性评价，(4)AI辅助PICO提取与质量评价，(5)辅助系统综述和Meta分析。 | erongcao/medlit-research | 1 | 2026-04-10 |
| 7300 | flet-release-announcementCreate or update a Flet release announcement blog post from changelog notes, matching existing /blog style. Use when asked to draft, plan, or revise posts like "Flet X.Y.Z release announcement" with major feature sections, screenshots, code samples, upgrade instructions (pip and uv/pyproject.toml), and a compact "other changes" summary. | flet-dev/flet | 16.4k | 2026-04-24 |