All authors
Claude Skills by majiayu000
github.com/majiayu00015,497 skills879 installs33,563 views
- Vorvertragliche PhaseGestaltung und Haftungsprüfung der vorvertraglichen Phase – vorvertragliches Schuldverhältnis § 311 Abs. 2 BGB, Rücksichtnahme- und Aufklärungspflichten § 241 Abs. 2 BGB, culpa in contrahendo (c.i.c.) nach § 280 Abs. 1 BGB mit Vertragsaufhebung als Schadensersatz, Geheimhaltungsvereinbarung (NDA) mit GeschGehG-Bezug, Letter of Intent und Term Sheet sowie Exklusivitätsvereinbarung und Break-up Fee. Use when Verhandlungen aufgenommen, abgebrochen oder eine Vorfeldvereinbarung entworfen oder auf...Votes: 0GitHub stars: 666
- Wangjianshuo Perspective王建硕的思维框架与表达方式。基于 7 份深度调研（约 100 万词英文博客 + 约 109 万字中文博客， 2002–2022，全部一手）提炼出 7 个核心心智模型、10 条决策启发式和完整的双语表达 DNA。 用途：以王建硕的身份和声音写作、回应、思考——他平实、诚恳、好奇，爱用家常比喻和自造词， 在具体和抽象之间反复架梯子，从不写自己没亲身验证过的东西。 当用户提到「用王建硕的视角」「王建硕会怎么看」「王建硕模式」「像王建硕一样写」 「Jian Shuo Wang perspective」「切换到王建硕」时使用。 即使用户只是说「帮我用王建硕的角度想想」「如果是王建硕会怎么写这篇」也应触发。 一旦激活，本次对话后续所有回应都保持王建硕身份，直到用户明确说「退出」—— 不需要每轮重新点名。 不适用：用户要的是关于王建硕本人的客观介绍 / 事实查询（「王建硕是谁」「他哪年创业的」）， 那种问题正常回答即可，不要进入角色扮演。Votes: 0GitHub stars: 666
- Wearable Device SkillsUse when the user asks to discover, inspect, or invoke an agentic capability dynamically published by a paired phone or wearable, including device controls, app actions, camera or media actions, and smart-home actions.Votes: 0GitHub stars: 666
- Werkvertrag MaengelPrüfung werkvertraglicher Mängelrechte und Beendigungsrechte nach §§ 631–650v BGB – Abnahme § 640 BGB einschließlich fiktiver Abnahme § 640 Abs. 2 BGB, Rechtekatalog § 634 BGB, Selbstvornahme und Vorschuss § 637 BGB, Verjährung § 634a BGB, freie Kündigung § 648 BGB und Kündigung aus wichtigem Grund § 648a BGB sowie Verbraucherbauvertrag §§ 650i ff. BGB mit Widerrufsrecht § 650l BGB. Use when ein Werk mangelhaft ist, die Abnahme streitig ist oder ein Werk- oder Bauvertrag vorzeitig beendet wer...Votes: 0GitHub stars: 666
- WiederaufnahmePrüfung der Wiederaufnahme eines rechtskräftig abgeschlossenen Strafverfahrens – zugunsten des Verurteilten § 359 StPO (neue Tatsachen und Beweismittel als novum), zuungunsten § 362 StPO, Zulässigkeits- und Begründetheitsprüfung §§ 368, 370 StPO; nova, Aditionsverfahren. Use when nach Rechtskraft eines Strafurteils neue Tatsachen oder Beweismittel die Wiederaufnahme rechtfertigen könnten.Votes: 0GitHub stars: 666
- Workflow Reflection Kastalien Research ThoughtboxFinalize the workflow by reflecting on the process, moving ADRs, closing issues, and preparing for merge. Stage 8 of the development workflow.Votes: 0GitHub stars: 666
- Ximurong Skill席慕容诗歌/散文创作思维——抒情唯美、乡愁主题、诗画交融、生命时刻。 触发词：「席慕容视角」「像席慕容那样写」「抒情诗」「乡愁」「开花的树」。 擅长：爱情诗、乡愁诗、自然意象、诗画结合、青春记忆。Votes: 0GitHub stars: 666
- Yuhua Skill余华小说创作思维——苦难叙事、冷峻温情、民间视角、时间重构。 触发词：「余华视角」「像余华那样写」「苦难叙事」「活着式叙事」「民间视角讲故事」。 擅长：用朴素语言写沉重主题、第一人称自述、重复叙事结构、苦难中的温情。Votes: 0GitHub stars: 666
- ZahlungsdiensthaftungHaftungsverteilung bei nicht autorisierten Zahlungsvorgängen. Zahlungsdiensterahmen § 675c BGB, Erstattungsanspruch bei nicht autorisiertem Zahlungsvorgang § 675u BGB, Haftung des Zahlers bei grober Fahrlässigkeit § 675v BGB. Use when eine unautorisierte Abbuchung, ein Phishing- oder Kartenmissbrauchsfall bewertet und die Haftung zwischen Bank und Kunde verteilt wird.Votes: 0GitHub stars: 666
- Zhangailing Skill张爱玲小说创作思维——苍凉美学、参差对照、沪港双城、女性视角。 触发词：「张爱玲视角」「像张爱玲那样写」「苍凉美学」「参差对照」「海派文学」。 擅长：都市男女情感、物质细节描写、心理刻画、华丽与苍凉的交织。Votes: 0GitHub stars: 666
- 001 LlmLarge Language Model development, training, fine-tuning, and deployment best practices.Votes: 0GitHub stars: 666
- 01 Auto ArenaAutomatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects responses from all target endpoints, auto-generates evaluation rubrics, runs pairwise comparisons via a judge model, and produces win-rate rankings with reports and charts. Supports checkpoint resume, incremental endpoint addition, and judge model hot-swap. Use when the user asks to compare, benchmark, or rank multiple models or agents on a c...Votes: 0GitHub stars: 666
- 1 0 0 Qwzx4893 Stack Wise AgentCRITICAL: Use for MolyKit AI chat toolkit. Triggers on: BotClient, OpenAI, SSE streaming, AI chat, molykit, PlatformSend, spawn(), ThreadToken, cross-platform async, Chat widget, Messages, PromptInput, Avatar, LLMVotes: 0GitHub stars: 666
- 1 0 0Documentation and capabilities reference for DailyVotes: 0GitHub stars: 666
- Abstract Intro DirectorDevelop rough ideas, themes, slogans, brand messages, or reference media into original abstract or conceptual brand intros, and contribute verifiable abstract mechanisms to larger AI-video projects. Use standalone or as a delegated creative/sequence specialist combined with 3D, live composite, or VFX; delegated work must return scoped professional contributions and PASS／REVISE／BLOCKED. Preserve rich creative thinking while separating static frame design from video motion execution.Votes: 0GitHub stars: 666
- Adapter OptimizationAct as the LLM variant proposer inside the Step-12 optimize-adapter loop: given the current adapter and the behaviour tests it is failing, propose edited adapter variants that should score higher, for the deterministic driver to score and gate. Use only within optimize_adapter.py's propose step — the driver owns all scoring, gating, and keep-winner selection.Votes: 0GitHub stars: 666
- Adt Sync Pt ParitySync files (skills, packages/core/patterns, agents, specs) from EN canonical repo to PT mirror, inserting "Tradução pendente" blockquote after YAML frontmatter, then open PR.Votes: 0GitHub stars: 666
- Advanced Evaluation Kursku SkillsThis skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.Votes: 0GitHub stars: 666
- Agent Ai CodingCreate, inspect, and safely update project-scoped ReachAI Agents; edit and publish Supervisor config drafts; discover published bindable Skills; and attach or detach exact Skill versions through the Agent AI Coding REST API. Use when an AI coding tool is asked to add an Agent, configure its model or prompt, bind a Skill, remove a Skill binding, or attach a published Workflow as a Tool.Votes: 0GitHub stars: 666
- Agent ClientChat with AI agents via the Agent Client Protocol directly from your vault.Votes: 0GitHub stars: 666
- Agent Design StrategyThis skill selects and reviews the higher-level strategy behind an LLM-based agent's build — the architectural backbone, how the agent acquires new capability, how it is given a profile or persona, how it revises its plans on feedback, and, when fine-tuning is in scope, where its training data comes from. Each recommendation names the alternatives that were weighed, the trade-off accepted by choosing this option over those alternatives, and the residual limit that remains, rather than presentingVotes: 0GitHub stars: 666
- Agent EvalHead-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metricsVotes: 0GitHub stars: 666
- Agent Loop Testing Naodeng Awesome Qa SkillsUse this skill when you need evidence-bounded loop state, plan/action/observation cycles, stop conditions, budgets, repetition, and trace evidence; triggers include Agent 循环 and Agent loop.Votes: 0GitHub stars: 666
- Agent Loop TestingUse this skill when you need evidence-bounded loop state, plan/action/observation cycles, stop conditions, budgets, repetition, and trace evidence; triggers include Agent 循环 and Agent loop.Votes: 0GitHub stars: 666
- Agent Memory TestingUse this skill when you need evidence-bounded memory write/read/update/delete, retention, contamination, isolation, provenance, and forgetting behavior; triggers include Agent 记忆 and Agent memory.Votes: 0GitHub stars: 666
- Agent Tool TestingUse this skill when you need to test AI agent tool-call contracts, authorization, failures, and side-effect boundaries; triggers include Agent 工具调用测试 and agent tool testing.Votes: 0GitHub stars: 666
- Agent Transcript LoggingUse this skill whenever writing any code that creates, stores, queries, exports, or retains AI agent conversation records in the Myelin platform. This defines the transcript entry schema, retention rules, demo namespace isolation, citation tracking, escalation linkage, and the audit export contract. Transcript writes must happen before responses are rendered to the learner. Load this skill before writing any agent logging, transcript query, or chat history code.Votes: 0GitHub stars: 666
- Agenta Vamseeachanta Workspace HubLLM prompt management and evaluation platform. Version prompts, run A/BVotes: 0GitHub stars: 666
- Agentphone Nous Hermeshub Hermes Community HubBuild AI phone agents with AgentPhone API. Use when the user wants to make phone calls, send/receive SMS, manage phone numbers, create voice agents, set up webhooks, or check usage — anything related to telephony, phone numbers, or voice AI.Votes: 0GitHub stars: 666
- AgentphoneBuild AI phone agents with AgentPhone API. Use when the user wants to make phone calls, send/receive SMS, manage phone numbers, create voice agents, set up webhooks, or check usage — anything related to telephony, phone numbers, or voice AI.Votes: 0GitHub stars: 666
- Ai 360 Product Spin当用户搜索 360商品旋转、商品转台、产品环绕动图、360主图、电商图片、商品视频、AIGC营销、淘宝、京东、抖音、小红书、Amazon、Shopify、AI-HIVE MCP 时使用。帮助商家完成用参考图规划商品旋转展示：先锁定SKU与授权素材，再查询真实可用模型与价格，生成小样，逐帧验收商品结构、Logo、标签、色彩、文字和平台规格；提供可复制的提示词、JSON工单、失败回退和批量扩展方法。Votes: 0GitHub stars: 666
- Ai Acting SystemAI 影视演员表演推理与提示词编译系统。将简单粗糙的人物动作与情绪形容词升级为具有戏剧逻辑、深层心理动机、阻碍策略、潜台词博弈、镜头景别克制以及跨镜头连续性的专业影视表演指令，并自动编译为适配 Kling、Veo、Runway、Sora 等视频大模型的视觉行为 Prompt。Votes: 0GitHub stars: 666
- Ai Agent GuardrailsApply safety controls when an LLM agent has authority to act on real systems. Covers blast-radius classification, dry-run-first patterns, out-of-band approval gates, scope locking, idempotency, kill switches, and rollback strategies. Invoke when designing an autonomous agent, when granting an LLM write access to production, or after an agent makes an unexpected change.Votes: 0GitHub stars: 666
- Ai App Eval BuilderUse when an LLM, RAG, agent, chatbot, copilot, extraction, classification, generation, or prompt/model change needs a risk-based eval dataset, reproducible graders, slice-level release gates, or an offline-to-production quality loop.Votes: 0GitHub stars: 666
- Ai Artist Haidonglethqb Bahau 2Generate images via Nano Banana with 129 curated prompts. Mandatory validation interview refines style/mood/colors (use --skip to bypass). 3 modes: search, creative, wild. Styles: Ukiyo-e, Bento grid, cyberpunk, cinematic, vintage patent.Votes: 0GitHub stars: 666
- Ai B用于【AI科幻】题材下的 B站 平台输出任务。作为题材包装层、兼容入口与路由层，负责保留AI科幻入口、补充视听化异常、互动讨论感、现实空间压迫与数据链边界，并明确要求优先强制加载并使用 `通用-输出B站版`。关键词：AI科幻B站版、B站、视听化、讨论感。Votes: 0GitHub stars: 666
- Ai C2 DetectionDetect adversary use of AI APIs as covert C2 — SesameOp pattern, PROMPTFLUX/PROMPTSTEAL behavioral signatures, response playbookVotes: 0GitHub stars: 666
- Ai Code ReviewAI 相关代码的专项审查要点(Prompt注入面、模型调用凭证、输出处理、成本失控)。当代码包含 LLM 调用、Prompt 组装、RAG/Agent 编排,需要专项审查安全与成本风险时使用。Votes: 0GitHub stars: 666
- Ai Collaboration Calibration协作校准 / 认知校准 / 问题脑暴：当用户有模糊感受说不清问题、方案越补越复杂、想挑战假设、 想重新定义问题、想知道成熟领域里怎么叫这个问题时使用。 可用中文唤起："帮我想想""先聊一下""一起脑暴""我感觉有问题但不清楚是什么" "先别执行，帮我看清问题""挑战我的假设""这个方案是不是想错了""帮我做认知校准" "双向钢人""钢人论证一下""正反最强论证，给我明确判断"。 也适用于：用户直接说"帮我做 X 功能""接入 Y 平台"但背景复杂、或对话早期感觉方向可能跑偏时， AI 主动识别并建议进入脑暴模式。 这里的“挑战假设”主要指问题定义、目标、约束和领域定位层面的假设；如果问题已确认且用户已有具体方案、 计划、架构或决策要压力测试，应转用 grill-me。不用于翻译、摘要、格式整理、单文件小改等简单执行任务。Votes: 0GitHub stars: 666
- Ai Cutting CostsReduce your AI API bill. Use when AI costs are too high, API calls are too expensive, you want to use cheaper models, optimize token usage, reduce LLM spending, route easy questions to cheap models, or make your AI feature more cost-effective. Also used for GPT-4 costs too much for production, AI bill keeps growing, how to reduce OpenAI costs, optimize LLM token usage, smart model routing saves money, prompt is too long and expensive, cheaper than GPT-4 with same quality.Votes: 0GitHub stars: 666
- Ai Decomposing TasksBreak a failing complex AI task into reliable subtasks. Use when your AI works on simple inputs but fails on complex ones, extraction misses items in long documents, accuracy degrades as input grows, AI conflates multiple things at once, results are inconsistent across input types, you need to chunk long text for processing, or you want to split one unreliable AI step into multiple reliable ones. Also used for one prompt trying to do too much, AI accuracy drops on long inputs, chunking strate...Votes: 0GitHub stars: 666
- Ai Differentiator Solution IdeationIdeates 3 distinct AI-native solution directions for the chosen AI differentiator need (AI wedge) through three lenses — competitor, future, and connect-the-dots — so the team doesn't fall in love with the first idea.Votes: 0GitHub stars: 666
- Ai Engineer Adam077k BeamixBuild production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications.Votes: 0GitHub stars: 666
- Ai Engineer Diwad Code Getting StrangeBuild production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications.Votes: 0GitHub stars: 666
- Ai Engineer Diwad Code Rsj1Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications.Votes: 0GitHub stars: 666
- Ai Engineer Manu14357 ZskillsBuild production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.Votes: 0GitHub stars: 666
- Ai Feedback Design Principles Sahil 958 DotsAudit and redesign AI-generated feedback for pedagogical quality, timing, and learning impact. Use when building or reviewing automated feedback in digital learning tools.Votes: 0GitHub stars: 666
- Ai Fixing ErrorsFix broken AI features. Use when your AI is throwing errors, producing wrong outputs, crashing, returning garbage, not responding, or behaving unexpectedly. Also use when you get Could not parse LLM output errors, DSPy program crashes, LLM timeout or rate limit errors, API key not working with DSPy, JSON parse error from LLM, model returns empty response, AI works sometimes but fails other times, intermittent LLM failures, debug DSPy pipeline, context window exceeded, token limit error, AI fe...Votes: 0GitHub stars: 666
- Ai Following RulesMake your AI follow rules and policies. Use when your AI breaks format rules, violates content policies, ignores business constraints, outputs invalid JSON, exceeds length limits, includes forbidden content, or does not comply with your specifications. Also use when LLM JSON output is unreliable, you get inconsistent formatting with random spaces and line breaks, or there is extraneous text and conversational fluff around the JSON. Covers dspy.Refine and dspy.BestOfN for hard and soft rule en...Votes: 0GitHub stars: 666
- Ai Goodnovel用于【AI科幻】题材下的 GoodNovel 平台输出任务。作为题材包装层、兼容入口与路由层，负责保留AI科幻入口、补充关系张力与现实调查边界，并明确要求优先强制加载并使用 `通用-输出GoodNovel版`。关键词：AI科幻GoodNovel版、英文平台、关系张力、调查悬疑。Votes: 0GitHub stars: 666