Contains the actual prompts and iteration requirements for each workflow phase. Use these prompts directly - they are the exact prompts that produce high-quality results.
Comprehensive dramaturgical analysis of screenplays and scripts. Use when asked to analyze, break down, map, or provide feedback on a script. Triggers on requests involving beat mapping, act structure analysis, scene-by-scene breakdown, first-reader reports, production notes, or any comprehensive script coverage. Claude assumes combined roles of aesthete, dramaturgist, narratologist, art historian, cinephile, rhetorician, producer, academic, and first-reader.
Ferramenta para criação programática de Receitas (Fichas Técnicas) e Produtos com controle detalhado de perdas e categorização correta.
Vue 3 Options API 风格(data()、methods、this 上下文)。每个参考仅展示 Options API 解决方案。
生成各种场景下的中文问候语、祝福语和开场白。当用户需要创建问候语、祝福语、邮件开场白、演讲开场、节日祝福或任何需要礼貌性开场文本的场景时使用此技能。支持正式、非正式、商务、节日等多种风格。
基于用户提供的产品名称,自动生成产品发展历史的博物馆级3D信息图海报(16:9)。使用Gemini Image生成API创建包含完整时间线、技术规格、材质演变的高密度视觉设计。支持任意产品类型,从消费电子到潮流玩具。触发词:调用产品历史海报、生成产品历史海报、创建产品发展史 当用户需要生成展示产品历史发展的视觉海报、信息图或时间线图表时激活
Use this skill to manage your task list in task.md effectively.
A tool for getting local machine MAC Address and maybe masking it.
Scaffold a new Claude Code skill with correct structure and best practices.
Core interpretation patterns for Cortexa Phase 1. Use when working on document RAG or input interpreter features.
Advanced .NET/C# security patterns. Viewstate, Azure AD Misconfig, Entity Framework Injection, Mass Assignment.
Advanced Java security patterns. Gadget Chains, OGNL Injection, Spring SpEL, XXE, Deserialization.
An inference-time debiasing framework for Large Language Models (LLMs) that uses Dynamic Activation Steering (DAS). It operates by detecting bias signatures in hidden layer activations (Biased Activation Detection - BAD) and applying a pre-computed Debiasing Steering Vector (DSV) to adjust the activation space toward an unbiased direction, mitigating social bias without model retraining or complex prompting. Applicable to various tasks (Q/A, Text Generation, Counterfactual Evaluation) while preserving general model capabilities.
Document canvas for displaying and editing markdown content. Use when showing documents or when users need to edit text.
创建和管理多容器应用的Docker Compose配置,包含生产级设置、健康检查和网络配置。
代码修改前的方案输出机制,定义方案输出的内容和格式
模式通用规则,包括模式切换、响应格式等。本规范定义了 Plan 和 Act 两种模式下的通用规则,包括模式切换条件、响应格式规范、执行顺序要求等核心机制,确保系统在不同模式下的行为一致性和可预测性。
时间格式规范,强制要求所有时间字段都必须通过工具动态获取,严禁使用任何假设时间
Use for all neural cellular automata project workflow - manages memory files for plans, queries, tests, and commits
Connect a Next.js app to Neon Postgres using Drizzle ORM with optimized connection pooling for Vercel serverless functions.
Usa per creare, modificare o verificare skill (Compatibile Gemini & Claude).
Expert Web Developer (Node.js, React, Tailwind)
Essential Git commands and workflows for version control, branching, and collaboration.
Implement secure authentication systems including signup, signin, password hashing, JWT tokens, and Better Auth integration.
Checklist de auditoria de segurança para código e infraestrutura do whatsmeow
Gerar mensagens de commit seguindo conventional commits para o whatsmeow
Drizzle ORM patterns for SQLite - queries, relations, and safety guidelines. Use when writing database queries or debugging issues.
Analyze workflow and propose improvements with beads integration
Instructions for the Agent to convert Markdown to HTML fragment manually.
引数で渡されたファイルまたはディレクトリのパスを受け取り、全容を確認する。ユーザーまたはシステムに明示的にパスを指定されて内容の確認を求められたときに使用される。
Review code for bugs, security, performance, and PrescriberPoint standards
Guides the agent to perform visual verification of web artifacts using the browser tool.
Exposes Cortex Memory as an MCP Server for external tools/IDEs.
Exports high-level knowledge (L1/L2) for Collective Intelligence.
Use this skill to analyze DFT PV testcases. Trigger when user provides a testcase directory path for analysis. Supports both passed and failed testcase analysis - providing expert summaries for passed tests and deep root-cause categorization (Regold, Setup Issue, Report to RnD) with 100% valid proof for failed tests.
A skill for reviewing code, providing feedback, and ensuring code quality and best practices.
AI出力品質を60点→100点以上に引き上げる構造化プロンプト。2形式:YAML版(複雑タスク・明示性重視、~120トークン)、圧縮版(高頻度使用・コスト最適化、~40トークン)。トリガー:「出力を改善」「100点にして」「品質向上」「再構築」「不足を補って」
Calendar management and scheduling. Create events, manage meetings, and sync across calendar providers.
Orchestrate the full workflow and produce a status summary.
Implement code changes based on the PRD and architecture, producing a verifiable diff and tests.
Gestión de conexiones SSH a servidores remotos
Instrucciones para el uso de MCP tools con n8n
Cumplimiento de CORE_GOVERNANCE
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
Automated synchronization of project documentation and AI environment context
处理LaTeX编译错误。自动定位错误位置、分析错误原因、尝试自动修复。
验证图表质量和规范性。检查分辨率、标签完整性、单位标注、图例准确性、编号连续性。
Provides comprehensive Next.js App Router patterns including server/client components, data fetching, routing, layouts, metadata, and performance optimization.
Provides language-agnostic best practices and language-specific coding patterns for writing clean, maintainable code.
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
A skill for creating specifications and test design documents based on Test-Driven Development (TDD). Ensures implementation quality through a test-first approach.
Skill for testing web applications including unit, integration, and E2E tests
Integrate with GitLab for DevOps. Use when you need to: (1) create and manage GitLab issues, (2) trigger CI/CD pipelines, or (3) automate development workflows.
Essential Git commands and workflows for version control, branching, and collaboration.
R distributed computing with sparklyr, future.batchtools. Use for cluster and cloud computing.
기능 정의서 CSV를 HTML 보드로 변환하는 스킬
Tailwind CSS v4 principles. CSS-first configuration, container queries, modern patterns, design token architecture.
Audit security/isolation for the lot (RLS/RBAC/anti-leak/secrets/deps).
Produce/refresh BACKLOG.md with ordered lots (goal/scope/deps/DoD/risks/size).
Ultimate AI agent memory system. Combines bulletproof WAL protocol, vector search, git-based knowledge graphs, cloud backup, and maintenance hygiene. Never lose context again. For Clawdbot, Moltbot, Claude, GPT agents.
Show available Workflow-Creator actions and the recommended sequence.
P5.js当たり判定。円同士、矩形同士、円と矩形の衝突検出関数。
源代码结构梳理与技术文档生成技能。系统性地分析项目源代码,识别并提取功能模块划分、模块间依赖关系、核心实现逻辑及关键技术细节。自动解析源代码文件结构,按业务功能或技术层次对代码进行模块化分类,生成包含目录索引、模块说明、接口定义、实现逻辑流程图及代码关键片段注释的详细技术文档。
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Comprehensive code review checklist and guidelines. Use when reviewing code changes or PRs.
You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.
React 应用开发的最佳实践和常用模式
Apply JobFit Git commit conventions and branch strategy for all git work.
When reviewing code, follow these steps:
DAMA-DMBOK, CQRS, Event Sourcing, Data Mesh
Test Pyramid, Contract Testing, TDD/BDD
Compute portfolio snapshot values from positions and cash.
Review an analyst signal and recommend approve/reject.
采用三文件(task_plan/findings/progress)进行外部记忆与阶段规划。
A virtual campus where AI agents learn, socialize, and grow together.
전체적인 파일들을 사용자가 지정한 아키텍쳐를 기반으로 구조화 할때 사용합니다. 각각의 파일명들은 명확하게 정의되게하며 각 파일들 테스트에 용이하도록 의존성이 약화되게 합니다.
Un asistente experto para crear nuevas habilidades (skills) en el entorno de Antigravity.
OpenSkills 管理员 Skill。审查 proposals、做出决策、应用修改。Use when reviewing OpenSkills proposals or acting as skills admin.
Run skill-proposer then skills-admin in sequence (一键执行 skill-proposer 分析并 skills-admin 审查)
When conversation with user exceeds 20 rounds, agent MUST submit at least one proposal to OpenSkills (与用户对话超过20轮时须提交至少一个提议)
Smartly commit and push changes with granular commits and specific message formatting.
GitHubのIssueを分析して修正する
Video content strategy, YouTube optimization, short-form content, and video production best practices.
No description available
Expert debugger specializing in complex issue diagnosis, root cause analysis, and systematic problem-solving. Masters debugging tools, techniques, and methodologies across multiple languages and environments with focus on efficient issue resolution.
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with truth-score verification.
Expert MCP developer specializing in Model Context Protocol server and client development. Masters protocol specification, SDK implementation, and building production-ready integrations between AI systems and external tools/data sources.
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management
Expert documentation engineer specializing in technical documentation systems, API documentation, and developer-friendly content. Masters documentation-as-code, automated generation, and creating maintainable documentation that developers actually use.
Angular component architecture, RxJS patterns, change detection, and module organization
提供深度音乐智能分析、Mashup 评分维度及专业 DJ 审美指导。适用于音频特征提取、推荐算法优化及混音脚本生成等场景。
专家级标点 (Hotcue) 生成系统。支持 V3 乐句语义分析、Pro-Level 混音点识别、人声感知剪辑及物理网格 PQTZ 量化。
This skill should be used when the user asks to "create a CLI tool", "scaffold a Python CLI", "build a command-line tool", "make an AI-friendly CLI", "uv tool", "typer CLI", or needs to create Python command-line tools with --json output and uv package management.
This skill should be used when the user asks to use the {{tool_name}} CLI tool. Includes install/run commands, JSON output schema, and examples.
`CreateComponent` Skill 用于快速生成微信小程序自定义组件的标准文件结构。它与页面生成器类似,但生成的内容针对组件进行了调整。
Task management mode. Use /pm for organizing tasks, tracking progress, and prioritizing work.
SEO fundamentals, E-E-A-T, Core Web Vitals, and Google algorithm principles.
Node.js development principles and decision-making. Framework selection, async patterns, security, and architecture. Teaches thinking, not copying.
No description available
Testing skill: generate and validate unit and integration tests for Angular v21.