#SkillRepo stars
- 4369Ponytail DebtKunoLu/640-skillsList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.559
- 4370Ponytail ReviewKunoLu/640-skillsQuality review of a change: is the logic right, is it safe, does it hold under real load, is risky code tested, is it fast enough, and is every line needed. Reads the connected code, not only the diff. Each finding is explained in plain English. Use for "review this", "code review", "review the last commit", "review my PR", "is this over-engineered", /ponytail-review.559
- 4371Project ValidationKunoLu/640-skillsUse after code changes to choose and run validation commands for Node, JavaScript, TypeScript, Python, Go, Dart, Java, Kotlin, C++, Swift, or Objective-C projects. Prefer project-defined commands and report skipped checks and risks.559
- 4372Question Refinerliangdabiao/Claude-Code-Deep-Research-main将原始研究问题细化为结构化的深度研究任务。通过提问澄清需求,生成符合 OpenAI/Google Deep Research 标准的结构化提示词。当用户提出研究问题、需要帮助定义研究范围、或想要生成结构化研究提示词时使用此技能。290
- 4373Research Executorliangdabiao/Claude-Code-Deep-Research-main执行完整的 7 阶段深度研究流程。接收结构化研究任务,自动部署多个并行研究智能体,生成带完整引用的综合研究报告。当用户有结构化的研究提示词时使用此技能。290
- 4374Sbtd TaskKunoLu/640-skillsUse for SBTD task execution and continuation, explicit default/lite/strict mode selection, task records and status changes, cross-session recovery, and task handoffs. Load strict gates only for strict tasks; ordinary questions and read-only work do not create task files.559
- 4375Sbtd Workflow OnboardKunoLu/640-skillsChecks, installs, resets, or explicitly upgrades and verifies selected SBTD workflow Skills, AGENTS and host configuration domains; plans and applies authorized legacy migrations and recovery; reconciles interrupted migration deployment evidence from current state; routes separately confirmed legacy cleanup and local Dashboard launch via "sbtd dashboard" or "sbtd ui".559
- 4376SEO GeoKunoLu/640-skillsSEO & GEO (Generative Engine Optimization) for websites. Analyze keywords, generate schema markup, optimize for AI search engines (ChatGPT, Perplexity, Gemini, Copilot, Claude) and traditional search (Google, Bing). Use when user wants to improve search visibility, search optimization, search ranking, AI visibility, ChatGPT ranking, Google AI Overview, indexing, JSON-LD, meta tags, or keyword research.559
- 4377Synthesizerliangdabiao/Claude-Code-Deep-Research-main将多个研究智能体的发现综合成连贯、结构化的研究报告。解决矛盾、提取共识、创建统一叙述。当多个研究智能体完成研究、需要将发现组合成统一报告、发现之间存在矛盾时使用此技能。290
- 4378Web UI Autotest GeneratorKunoLu/640-skills从前端和后端源码中生成可维护的 Web UI 自动化测试。适用于分析页面、路由、组件、接口、用户流程,生成 Playwright UI 测试,运行测试,生成中文报告,并自检页面功能和跨页面逻辑是否被独立测试资产覆盖。 Generate maintainable Web UI automated tests from frontend and backend source code. Use for analyzing pages, routes, components, APIs, and user flows; generating and running Playwright UI tests; producing Chinese test reports; and checking whether page features and cross-page logic are covered by independent test assets.559
- 4379Assets Overlay APIneutree-ai/openapi-to-skillsOverridden by a static asset to prove --assets takes precedence over generated files.341
- 4380Case Conflictneutree-ai/openapi-to-skills. Use when working with the Case Conflict or when the user needs to interact with this API.341
- 4381Inline Body APIneutree-ai/openapi-to-skillsExercises inline (non-$ref) request/response object schemas.. Use when working with the Inline Body API or when the user needs to interact with this API.341
- 4382Openapi to Skillsneutree-ai/openapi-to-skillsGenerate an Agent Skill from an OpenAPI 3.x file or URL using the openapi-to-skills CLI. Use when asked to convert an API specification into a skill or create API reference docs for on-demand loading.341
- 4383Releaseniaka3dayo/agent-skills-vrc-udonRelease procedure for agent-skills-vrc-udon: sync main into dev, bump the five version fields, open and merge the release PR, rewrite the Release Drafter notes, and publish to npm. Use when asked to cut, prepare, or publish a release, to bump the version, or to sync main into dev. Maintainer-only; not distributed.369
- 4384Swagger Petstore Openapi 3 0neutree-ai/openapi-to-skillsThis is a sample Pet Store Server based on the OpenAPI 3.0 specification. You can find out more about. Use when working with the Swagger Petstore - OpenAPI 3.0 or when the user needs to interact with this API.341
- 4385Teachiamyoki/qwen-image-2.1-skillTeach the user a new skill or concept, within this workspace.211
- 4386Triageiamyoki/qwen-image-2.1-skillMove issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.211
- 4387Unity Vrc Skills Renovatorniaka3dayo/agent-skills-vrc-udonVRChat skill renovator for knowledge fill, refresh, and quality improvement. Use this skill when updating VRChat skills to new SDK versions, filling missing knowledge, fixing outdated information, or improving skill quality. Targets unity-vrc-udon-sharp and unity-vrc-world-sdk-3 skills. Triggers on: update skills, SDK latest, knowledge fill, skill maintenance, information audit, catch-up, renovate, refresh, improve skills, SDK update.369
- 4388Unity Vrc Udon Sharpniaka3dayo/agent-skills-vrc-udonRules and references for VRChat UdonSharp on SDK 3.10.6, the active and verified target. UdonSharp compiles only a subset of C#, and its networking fails without an error, so load this skill before writing, reviewing, debugging, or migrating any UdonSharp or UdonBehaviour code, even a short script. Covers synced runtime state and ownership, NetworkCallable events, NetworkCalling.CallingPlayer and Udon network authorization, a local public helper or public-method audit, C# to Udon conversion, persistence, data containers, web loading, UdonSharp Assembly Version Defines, and runtime API access f369
- 4389Unity Vrc World SDK 3niaka3dayo/agent-skills-vrc-udonScene, component, and upload guidance for VRChat World SDK 3. Active support / last verified: SDK 3.10.6. VRChat changes Unity behaviour in ways the editor does not show (reserved layers, runtime layer names, Android limits, Build Panel validation), so load this skill before setting up or reviewing a VRChat world scene, even for one component. Covers VRC SDK component placement and Inspector setup (VRC_SceneDescriptor, VRC_Pickup, VRC_Station, VRC_Mirror, VRC_ObjectSync, VRC_CameraDolly, VRCBillboard, VRCPlacementZone, spawn points), layers and collision matrices, baked lighting, Quest/Android369
- 4390XLSXQwen-Applications/Trace2SkillComprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Qwen-Agent 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 spreadsheets, or (5) Recalculating formulas339
- 4391XLSX 122BQwen-Applications/Trace2SkillUse when handling spreadsheet tasks in .xlsx files with the released 122B created-from-scratch skill339
- 4392XLSX 35BQwen-Applications/Trace2SkillUse when handling spreadsheet tasks in .xlsx files with the released 35B created-from-scratch skill339
- 4393日本語テストapineutree-ai/openapi-to-skillsJapanese character filename test. Use when working with the 日本語テストAPI or when the user needs to interact with this API.341
- 4394Archival Fragmentsttfake92-lab/skills从一个想法或一份文案,做出一条完整的「档案剪贴」风格短片——满幅象牙纸、单色印刷黑白、单一暗砖红,镜头用 MiniMax H3 首尾帧驱动,配音用 Fish Audio,成片用 ffmpeg 合成。当用户想用档案剪贴/编辑设计/纸质拼贴风格做视频,或要把一段文案、一个选题、一条新闻做成解说短片时使用。包含环境安装检查、拆故事拆画面拆节奏、逐镜生成、变速拼片的完整流程。337
- 4395Archival Fragments Litettfake92-lab/skills「档案剪贴」视觉风格 + 关键帧串联首尾帧方法。满幅象牙纸、单色印刷黑白、单一暗砖红;先出一串各不相同的参考图,再用相邻两张作为首尾帧生成镜头,接点严丝合缝。不绑定任何具体模型,任何支持首尾帧的视频工具都能用。当用户要做档案剪贴/纸质拼贴/编辑设计风格的短片,或想用首尾帧方式做连贯分镜时使用。337
- 4396Cavemankubestellar/consoleUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.155
- 4397CdafUditAkhourii/cdafRead CDAF sidecar files (.cdaf) instead of processing video with vision. Use whenever a task involves understanding, summarizing, searching, editing, or selecting from video files (b-roll, raw clips, footage libraries) — check for a .cdaf sidecar FIRST before analyzing any video directly.226
- 4398Claude Local Resetttfake92-lab/skills在 macOS 与 Windows 上备份重置 Claude Desktop 本地状态,检查网络出口、DNS/WebRTC、代理与中转配置,自动交付 HTML 质检回执和可跳转的 Claude 防封号指南。使用时先停下来确认任务范围:清除 Claude 本地使用痕迹,或只做网络检查;指南分别引导首次使用与曾被限制用户完成手动准备(时区、出口、TUN、登录前自检、账号与支付、日常使用、出发前清单)、调用 skill 质检。可单独检查环境;不承诺解除服务器关联或防止封号。Linux 与未核实的安装方式不要套用。337
- 4399College Applicationttfake92-lab/skills通过 Agent 对话帮助中国高考考生完成志愿填报决策:先做有科学依据的性格与职业兴趣测评,再研究适合的职业、专业和行业,最后结合省份、选科、分数/位次与官方招生数据生成可追溯来源的 HTML 报告。用户提到高考志愿、college application、选大学、选专业、性格测试、职业方向、行业前景、投档线、录取概率、冲稳保或志愿模拟时使用。337
- 4400Competitive AnalysisFokkyp/claude-skills产品经理竞品分析报告生成器。当用户提到竞品分析、竞品调研、竞品对比、竞争对手分析、市场竞争分析、行业竞品研究时触发。也适用于用户要求对比多个产品/平台/公司的功能、商业模式、市场定位等场景。即使用户只是说'帮我分析一下XX和YY'或'XX有哪些竞争对手',只要涉及产品/公司间的对比分析,都应该使用这个 skill。支持任意行业,支持快速分析和深度分析两种模式。236
- 4401Composiocomposio-community/skillsUse 1000+ external apps via Composio - either directly through the CLI or by building AI agents and apps with the SDK189
- 4402Macos Migrationttfake92-lab/skillsmacOS 系统迁移助手 — 两阶段:先在旧系统采集清单(JSON),再在新系统还原。 Use when user mentions: 系统迁移、换电脑、新装系统、Time Machine 恢复、 数据迁移、重装系统、migration、setup new mac、restore from backup、备份系统。 自动检测当前是旧系统(采集模式)还是新系统(还原模式)。 前置:先做一次 Time Machine 全量备份;唯一软件依赖是 Homebrew。337
- 4403Prd GeneratorFokkyp/claude-skills协助产品经理生成专业的产品需求文档(PRD),通过交互式问答收集信息,进行竞品研究,迭代优化各模块内容,最终输出结构化的PRD文档。236
- 4404Product Marketing Contextmysticaltech/marketingskillsWhen the user wants to create or update their product marketing context document. Also use when the user mentions 'product context,' 'marketing context,' 'set up context,' 'positioning,' or wants to avoid repeating foundational information across marketing tasks. Creates `.claude/product-marketing-context.md` that other marketing skills reference.376
- 4405Skill SublationSven-Mirana/sublation技能扬弃 Sublation V5.0 完整版。把执行经验沉淀为观测、候选、验证、多 Agent 协作面板、默认关闭的受控唤醒意图、Skill 分类与 shadow 精准建议、用户批准、晋升和观察窗的可审计治理链路;仅在用户明确说出 sublation 或扬弃技能时触发。278
- 4406Vesti Handofffirefly-hefeng/VESTI-SKILLSProduce a schema-based work handoff when transferring a task to another AI or session, compacting context, switching tools, generating a handoff, or preparing for /compact. Require the receiving agent to re-run the latest verification before trusting the handoff. The V2 format aligns with the VESTI-APP RelayPackV2 schema.395
- 4407Vesti Memoryfirefly-hefeng/VESTI-SKILLSRecall past AI coding sessions and file touches captured by VESTI. Use when the user references earlier work ("继续上次…", "之前我们…"), asks which local file or project contained prior work, starts a session in a tracked project, merges work across projects or branches, or needs a decision made in missing context. Provides project context, file-level lookup, and progressive retrieval from session index to selected full turns.395
- 4408Web3 PolymarketPolymarket/agent-skillsPolymarket integration for prediction market trading on Polygon. Covers authentication (L1 EIP-712, L2 HMAC-SHA256, builder headers), order placement (GTC/GTD/FOK/FAK, batch, post-only, heartbeat), market data (Gamma API, Data API, orderbook, subgraph), WebSocket streaming (market/user/sports channels), CTF operations (split, merge, redeem, negative risk), bridge (deposits, withdrawals, multi-chain), and gasless relayer transactions. Use when building AI agents, autonomous market makers, prediction market UIs, or any application integrating with Polymarket on Polygon.201
- 4409Yyl Benchmark Breakdownttfake92-lab/skills拆解对标账号 / 竞品内容——丢一个链接进来,自动识别平台(抖音/小红书/B站/YouTube/公众号)和粒度(单条 or 整个账号),抓取内容后输出三件套:可复用爆款公式、画面+口播逐段拆解、人设与内容定位,并自动存档到 benchmarks/。短视频自动下载 + 转写口播 + 抽视觉帧(contact sheet 多模态读图),不只看 caption。当用户说「拆解这个账号/视频/笔记」「分析对标/竞品」「这条为什么火」「给链接拆内容」「teardown」「看看别人怎么做的」时使用。抓不到内容会引导粘贴文案/字幕,绝不直接报错。337
- 4410Yyl Disk Cleaner Catttfake92-lab/skills像素小猫帮你清理 macOS 磁盘、优化空间与性能。扫描开发者缓存 / 系统缓存 / 大文件下载,给出性能与网络优化建议,然后打开一个「像素风网页」让你勾选确认——确认后一只 3D 像素小猫在房间里实时打扫,灰尘堆随真实删除进度缩小。带持续记忆:每次清理了什么、你的偏好都记在 ~/.disk-cleanup-cat/,下次更懂你。当用户说「清理磁盘 / 清理空间 / 磁盘满了 / C盘满了 / 优化电脑 / 优化性能 / 电脑变慢了 / 清缓存 / disk cleanup / free up space」时使用。仅限 macOS。337
- 4411Yyl Remotion Videottfake92-lab/skillsBuild 16:9 spoken-video compositions as standalone Remotion projects with React, TypeScript, frame-based animation, estimated durations, and direct mp4 rendering. Use when the user wants video files, Remotion, mp4 export, frame-accurate motion, post-production voiceover, or theme-driven video templates; do not use for click-driven web presentations.337
- 4412Yyl Vertical Videottfake92-lab/skills竖屏分屏口播 REEL — 把一份口播脚本做成 1080×1920 的「上方动效 + 下方人物卡」知识 / 观点短视频:Breeze 配音 → 音频驱动 HeyGen 数字人(Avatar V)→ 逐句配素材(TikHub 社媒、自己的录屏、即梦 Seedance AI 视频)→ 代码动效(拉高衬线标题模糊入场、液态玻璃卡片、清单、流程、手机墙、代码、质检表…)每段锚到口播的字 → 按动效出场配音效 → Epidemic 配乐自动避让人声 → 质检门槛(字幕挡脸、字幕对齐、响度、黑帧)。招牌细节:下方圆角人物卡里的人物抠像放大约 16%、底边对齐,头和手冲出卡片上沿,背景被卡片裁在下面,形成立体感。用户说「竖屏口播 / 上面动效下面人 / 人物出框 / 参考这种分屏 reels / 用数字人做一条口播 / 脚本发给你做成片」时使用。不用于:横版口播(talking-head-reel)、实拍长口播删减(talking-head-edit)、无出镜讲解(knowledge-explainer)、vlog。337
- 4413Yyl Video Promptttfake92-lab/skills鱼亦乐的主力 AI 视频提示词 Skill。先按脚本风格选档位,再像导演一样把脚本、故事、口播稿、分镜表或一句想法,拆成能直接生成的分段视频提示词。短视频档(抖音/小红书节奏:一镜到底、多分镜、街拍、角色小故事、竖屏短剧,标杆是《丹眉》和赛博原子)和电影精品档(慢节奏剧情、表演、对白、对手戏、AU 微表情、八维公式),各有结构和示例。每段含生成模式与参数、参考图绑定、人物道具场景、镜头时间轴、声音和硬约束。适用 Seedance 2.0/2.5、即梦、dreamina、LibTV、TT AI。Use when 用户要写视频提示词、AI 视频提示词、Seedance 提示词、即梦提示词、脚本转视频、拆分镜、分镜提示词、快剪、短视频提示词、storyboard、shot list、多图参考、首尾帧、人物表演提示词、AI 演技、情绪递进、导演式提示词,或给出脚本/故事/想法要变成视频。当前项目若有专用工作流 Skill(Vlog、情感钩子、新闻解说等),优先用专用的。337
- 4414Yyl Video Thumbnailttfake92-lab/skills生成 B站 / YouTube / 抖音 的高点击「视频封面 / 缩略图」——pop-out 技法:抠图人物全亮叠在自己那张被压暗的原图上、文字压在中间,一套内容用 HTML/CSS 重排成 16:9 / 4:3 / 3:4 三种比例。当用户要视频封面、缩略图、thumbnail、B站封面、YouTube 封面、抖音/视频号竖封面、把人物放封面上、Codex/Agent/AI 视频封面时使用。注意:这是「视频封面」专用,走 YouTube 高设计感美学;要小红书图文/信息图/PPT 风请用 yuyile-social-card-skill。337
- 4415Cheat Replynniiovoo/cheat-replyFind promising X/Twitter conversations, study their replies, and draft distinctive replies people have a reason to answer or share. Use for reply discovery, comment research, reply drafting, or reply growth strategy. Adapt to the user's audience, language, and voice; posting requires approval of the exact text and target.206
- 4416Geoliangdabiao/GEO-Content-Optimizer-Skill完整的 GEO(生成式引擎优化)服务流水线:给一个产品官网 URL 和介绍材料, 做站点诊断与 AI 答案采样、生成带验收标准的执行工单、产出可直接部署的资产 (llms.txt / JSON-LD / 定义块 / FAQ / 内容大纲与初稿)、自动验收工单是否闭环、 并打包成可直接发给客户的交付物。可按周期复跑,做长期 GEO 运营与月报。 国内和海外双市场并行:国内覆盖 智谱GLM/豆包/DeepSeek/Kimi/MiniMax/纳米AI/百度AI, 海外覆盖 Gemini/ChatGPT/Claude/Grok/Perplexity,问题库与指标按市场分开算。 当用户说「做 GEO」「生成式引擎优化」「让 AI 推荐我的产品」「AI 搜索里搜不到我们」 「GEO 方案/诊断/监测/月报/交付」「给客户做 GEO 服务」,或给一个产品网址要做 AI 可见性优化时使用。GEO 指生成式引擎优化,不是地理信息; 不用于传统 SEO 关键词排名、竞价投放或建站。241