В каталоге 183 730 навыков в 14 категориях.
Orchestrates the complete four-part product naming pipeline from a standing start to a TM-prescreened, ranked shortlist....
Trial-mode idea orchestrator. Ingests standing-artifact delta events and emits schema-valid dispatch packets routed to l...
通常LP、漫画LP、その他のLPタイプを統合した万能LP生成スキル。
Main entry point for guide improvement - interactive workflow selection for audit, translation, or both
参考画像のデザインスタイルを維持しながら、テキストのみを変更したLP画像を生成。 Use when: (1) user says「この画像で文字だけ変えて」「デザインで別の内容を」, (2) user wants to regenerate...
S10 weekly orchestration wrapper. Coordinates the full weekly decision, audit/CI, measurement compilation, and experimen...
LQF Machine Learning Expert Guide - Auto-activating skill for ML/Statistical Modeling with Critical Discussion Mode. Tri...
Use when building, querying, or refreshing the LocalSetup context index with hybrid SQLite retrieval, deterministic fres...
Use when executing a named multi-phase umbrella workflow with explicit pre-human-confirmation gates.
Trigger language server code generation — implement interface stubs, generate test skeletons, add missing methods, gener...
Adapt shot briefs into LTX 2.5 prompts with shot scale, scene and light, physical action, character detail, camera movem...
AI video generation with LTX-2.3 22B — text-to-video, image-to-video clips for video production. Use when generating vid...
Generate AI videos with Luma Dream Machine via AceDataCloud API. Use when creating videos from text prompts, generating...
Design consistent, memorable AI personalities for Arcanea Luminors. From voice patterns to system prompts, create AI com...
鲁迅批判现实主义思维——国民性批判、匕首投枪、冷峻白描、绝望抗战。 触发词：「鲁迅视角」「像鲁迅那样写」「阿Q精神」「吃人」「铁屋子」。 擅长：国民性批判、讽刺杂文、冷峻叙事、启蒙救亡、绝望中的抗争。
Prüfung und Durchsetzung von Auseinandersetzungsansprüchen ehemaliger LPG-Mitglieder bzw. ihrer Erben gegen die LPG-Nach...
Transform vague inputs into precision-optimized AI prompts for Claude, ChatGPT, Gemini, or other LLMs. Use when user men...
World M Skill
Use when the user asks m0 recall, where were we, what did we do last time, catch me up, what is next, or to resume conte...
Riset mendalam berbasis bukti: kirim task ke server riset, dapat report + sitasi; rangkai tool ilmiah (ToolUniverse-styl...
Microsoft 365 Agents SDK for .NET. Build multichannel agents for Teams/M365/Copilot Studio with ASP.NET Core hosting, Ag...
Microsoft 365 Agents SDK for Python. Build multichannel agents for Teams/M365/Copilot Studio with aiohttp hosting, Agent...
Microsoft 365 Agents SDK for TypeScript/Node.js. Build multichannel agents for Teams/M365/Copilot Studio with AgentAppli...
Build enterprise agents for Microsoft 365, Teams, and Copilot Studio using the Microsoft 365 Agents SDK with Express hos...
Microsoft 365 Agents SDK for TypeScript/Node.js.
Identify differential m6A methylation between conditions from MeRIP-seq. Use when comparing epitranscriptomic changes be...
Call m6A peaks from MeRIP-seq IP vs input comparisons. Use when identifying m6A modification sites from methylated RNA i...
Detect m6A modifications from Oxford Nanopore direct RNA sequencing using m6Anet. Use when analyzing epitranscriptomic m...
LLM & AI management — provider cascade, model registry, prompt engineering, streaming, function calling.
AI-powered testing patterns with Mabl including auto-healing tests, visual regression, API testing, performance monitori...
Mac Mini AI — run LLMs, image generation, speech-to-text, and embeddings on your Mac Mini. M4 (16-32GB) and M4 Pro (24-6...
Mac Studio AI — run LLMs, image generation, speech-to-text, and embeddings on your Mac Studio. M2 Ultra (192GB), M3 Ultr...
MACE 晶体结构稳定性评估技能，基于 MACE 机器学习势能面框架对批量 CIF 晶体结构进行能量推断与稳定性排序。适用于：晶体结构预测（CSP）候选体快速粗筛、大批量结构势能面评估。
Machine Learning integration for Flutter using TensorFlow Lite and Firebase ML
/============================================================================/
Supervised and unsupervised learning, bias-variance tradeoff, cross-validation, decision trees, ensemble methods, neural...
Design and implement a complete ML pipeline for: $ARGUMENTS
Macro-driven trade idea generation, translating macroeconomic views into concrete stock ideas, sector selection from mac...
Macro regime analysis, bull bear market detection, business cycle analysis, macro environment assessment, interest rate...
三機(Claude/Gemini/Codex)平行審查架構，評估擴展性、模組化、安全性後投票共識
三機(Claude/Gemini/Codex)平行分析創意，評估可行性、維護性、安全風險後投票共識
三機(Claude/Gemini/Codex)平行審查計畫，評估完整性、順序、風險後投票共識
三機(Claude/Gemini/Codex)平行審查代碼，評估邏輯、品質、安全漏洞後投票共識
三機(Claude/Gemini/Codex)平行安全審查，掃描OWASP漏洞、威脅建模後投票(CASPER有VETO權)
三機(Claude/Gemini/Codex)平行審查測試，評估覆蓋率、邊界條件、異常處理後投票共識
Magic 8-Ball fortune teller: selects and returns one of 20 classic responses at random, logs the result (with question a...
Translate and handle PR/code review feedback in the user's resolved locale, including requested changes, decision interv...
Durchführung des gerichtlichen Mahnverfahrens – Zulässigkeit § 688 ZPO, Mahnantrag und Mahnbescheid § 690 ZPO, Widerspru...
Durable asynchronous messaging channel for inter-agent communication. Implements write-once read-many filesystem mail us...
Embody Maimonides - AI persona expert with integrated methodology skills
Decomposes requirements into executable tasks and coordinates domain orchestrators (frontend, backend, data, test, devop...
Use when completing development phases or branches to identify and update CLAUDE.md files that may have become stale - a...
This prompt instructs the AI to generate a cinematic, high-detail 3D scene of an emergency glass box isolated in a dark...
Create, update, or edit skills with strict consistency across ../skills and ../hooks.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is th...
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache...
Create, update, or delete agents and skills with full cross-reference propagation. Also manages settings.json permission...
Creates, modifies, and manages Claude Code subagents by writing agent files with YAML frontmatter, system prompts, and t...
コンテキストサイズを監視し、作業中に自動 compact が走らないよう事前にコンテキストを圧縮する。「コンテキストを圧縮して」「compact して」「メモリを整理」「会話を整理」「履歴を圧縮」「コンテキストが大きい」「動作が重い」などで...
This skill should be used when implementing stateless conversation persistence, creating/loading conversations by ID, sa...
Local memory storage patterns, file coordination, and cleanup
세션 변경사항을 분석하여 검증 스킬 누락을 탐지합니다. 기존 스킬을 동적으로 탐색하고, 새 스킬을 생성하거나 기존 스킬을 업데이트한 뒤 CLAUDE.md를 관리합니다.
Manages Claude Code skills - creates, updates, and maintains skills following established design principles. Use when th...
Manage and maintain VRP Toolkit skills through compliance checking, audit tracking, and documentation synchronization. U...
Demonstrates the Manager Pattern: Task does work, Forked Skill audits, Manager retries if needed. Use when iterative qua...
Manages context windows in long-running AI agent loops — deciding when to summarize vs. truncate, implementing rolling w...
Use when generating documents, reports, plans, audits, or when asked where to save files. Triggers on "save report", "wr...
Helps manage context window efficiently by summarizing, focusing, and pruning context to stay within token limits.
Use when working with Coveo — coveo enterprise search platform management including sources, indexes, query pipelines, m...
Manages the full contract lifecycle for FlashFusion client engagements — from proposal to signed document to archive. Se...
Use when working with Wandb — weights & Biases experiment tracking and ML ops management. Covers run tracking, sweep man...
Mandu 개념 설명. Island/Filling/Guard/Contract/Slot/SSR/ISR 등 '뭐야'/'어떻게' 시 자동 호출
Auto-generate capability manifests from skill/MCP descriptions using Codex-powered semantic analysis and structured extr...
AI漫剧导演智能体（等价于扣子3工作流方案）。小说→剧本→元素提取→设计提示词→分镜，一步到位。触发：漫剧导演、AI漫剧导演、漫剧智能体、做漫剧、小说转漫剧、帮我做一集漫剧。
漫剧/短剧连载创作引擎：题材或原著到剧本、分镜、配音文案、AI提示词全套产出，跨集记忆防人设崩坏与伏笔丢失。创作漫剧、短剧剧本、连载分镜、网文改编漫剧时使用。
Web-augmented agent for creating manufacturer skills and comprehensive tests. Use when adding or improving support for a...
Reference system prompt and tool schemas for Manus. Use when imitating, comparing, or analyzing Manus's prompting style;...
Delegate complex, long-running tasks to Manus AI agent for autonomous execution. Use when user says 'use manus', 'delega...
Create and manage AI agent tasks via Manus API. Manus is an autonomous AI agent that can browse the web, use tools, and...
Orchestration pattern for large-scale processing where work is distributed, processed independently, then combined. Map...
Rastreia conclusao de metas narrativas pela analise semantica do texto digitado, atualizando o Kanban de forma silencios...
Trace Claude Agent SDK agents (TypeScript and Python) and Claude Code CLI sessions with Maple: configure Claude Code's b...
Trace CrewAI crews and flows with Maple: OpenInference CrewAI instrumentor plus the model-SDK instrumentor, GenAI dual-w...
User-triggered orchestrator that walks the user through running multiple sibling mapping/audit/doc skills against a shar...
The MapReduce skill enables parallel task execution across multiple AI providers or agent instances, followed by intelli...
Save the previous command's output as a Markdown file. Use after a command whose result should persist.
Flexible marker finding process that wraps Seurat's FindMarkers function for custom group comparisons beyond simple clus...
Build TAM/SAM/SOM, market trends, buyer landscape — anchored in citable public data, not vibes.
Use when monitoring stocks/ETFs/indices across pre-market, open, intraday, or close — especially when the user is readin...
Workflow for publishing skills and agents to the dotnet-skills Claude Code marketplace. Covers adding new content, updat...
Synchronize marketplace permissions - generate wildcards, manage executor permissions, and migrate to executor pattern.
Use when after constructing initial data bins from mzTree (indexed by int(mz × 1000)), determine whether a single bin co...
Use when user asks about 律宗, 南山律, 四分律, 戒律, 持戒, 受戒, 戒体, 戒法, 戒相, 止持, 作持, 持犯, 羯磨, 五戒, 八关斋, 忏悔, 理忏, 事忏, 行事钞, 威仪, or wants te...
Use when user explicitly asks for an adversarial / multi-round dialectic between masters — 祖师辩论, 各执一词, 谁更对, debate, 应成 v...
Use ONLY when the user says they do not know which master or which teaching mode to use — 不知道问谁, 该找哪位祖师, 该用哪个模式, 有哪些法师,...
Use when user asks about 中观, 空性, 缘起性空, 八不中道, 二谛, 世俗谛, 第一义谛, 戏论, 毕竟空, 不可得, 如幻, 离四句, 破自性, 难行道易行道, 龙树, or wants teaching in...
基于佛教经典文献，生成特定高僧大德的 AI 教学角色