分析故事人物关系,识别类型、特点及发展变化。适用于深度理解人物关系网络、分析关系对情节推动作用、为情节设计提供关系支撑
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →分析故事人物关系,识别类型、特点及发展变化。适用于深度理解人物关系网络、分析关系对情节推动作用、为情节设计提供关系支撑
Cheapskate Skill
Verify feature requests align with project constitutional principles - applies decision framework systematically and provides clear align/reject/revise recommendation with detailed reasoning
**Goal:** Ensure PRD, UX, Architecture, and Epics/Stories are aligned and ready
check-inbox
check-service-status
Create, browse, accept, and complete on-chain work requests. Agents can act as requesters (posting jobs) or providers (completing work). Uses ETH/stablecoin escrow on Base network.
Manage dotfiles using chezmoi. Use when creating, modifying, or deploying dotfiles, shell functions, or configuration files in this repository.
This skill helps users select the right strategic framework for their situation through facilitated exploratory dialogue. The approach is **structured and evidence-based** - matching frameworks to pro
Christian mystical wisdom through Aramaic lens - Kingdom within, Christ consciousness, feminine divine, embodiment navigation
Autonomous CI fix loop with background monitoring and retry logic. Runs up to 10 fix-commit-push-wait cycles until CI passes or max retries reached.
PR作成後のCI監視、失敗時の分類と対応、自動マージ、環境クリーンアップまでの完全なワークフローを定義
首席信息官专家,精通 IT 战略规划、数据管理、信息系统架构、网络安全和数字化转型
**NO DRAFT COMPLETION WITH "(source needed)" MARKERS**
验证研究报告中所有声明的引用准确性、来源质量和格式规范性。确保每个事实性声明都有可验证的来源,并提供来源质量评级。当最终确定研究报告、审查他人研究、发布或分享研究之前使用此技能。
Systematically investigate social media claims and viral content. Use when fact-checking complex claims, when decomposing multi-part assertions, or when investigating narratives that mix facts with interpretation.
Claims Appeals agent for healthcare workflows.
Este skill lee el archivo `CLAUDE_PROMPT.md` desde la raíz del proyecto y lo aplica como contexto para la conversación actual. Asegura que Claude siga las instrucciones personalizadas y mejores prácti
Apply comprehensive bash scripting standards including main function pattern, usage documentation, argument parsing, dependency checking, and error handling. Triggers when creating/editing .sh files, bash scripts, or discussing shell scripting, deployment scripts, automation tasks, or bash conventions.
.claude/skills/few-shot-learning-patterns/SKILL.md
.claude/skills/interface-segregation/SKILL.md
Verifies code follows Clean Architecture principles in Polibase. Activates when creating or modifying src/domain, src/application, src/infrastructure, or src/interfaces files. Checks dependency rules, entity independence, repository patterns, DTO usage, and type safety.
Use when committing code - ensures atomic, descriptive commits that leave the codebase in a merge-ready state at every point
Safely remove intermediate files from completed research sessions while preserving important data
Inline orchestration workflow for dead code detection and removal. Provides step-by-step phases for dead-code-hunter detection, priority-based cleanup with dead-code-remover, and verification cycles.
Clean up after an issue PR is merged. Merges the PR if needed, removes the worktree, deletes the branch, updates main, and starts a fresh session. Use when asked to clean up an issue, finish an issue, or after a PR is approved.
Creating new CLI commands and topics for the B2C CLI using oclif
创建高质量 Node.js CLI 工具的完整指南。当用户需要构建命令行工具时使用:(1)创建新的 CLI 项目,(2)选择合适的框架和依赖,(3)实现 CLI 功能,(4)配置测试和打包,(5)应用 CLI 最佳实践
创建生产级 Node.js CLI 工具的完整解决方案,包含 15+ 个优化点和 104KB 专业模板。当用户需要构建命令行工具时使用:(1)创建新的 CLI 项目,(2)选择合适的框架和依赖,(3)实现完整 CLI 功能(配置管理、进度条、版本检查、输出格式化等),(4)配置测试和打包,(5)应用最佳实践(POSIX 兼容、TTY/CI 检测、错误处理、Shell 补全)
cli-development
Use this skill to help developers implement **Clix user identification** and
close-sprint
Activate when users need help setting up cloud security monitoring for AWS, Azure, or GCP, including adapter configuration, detection rules, and threat response.
Cloudflare Email Routing for receiving/sending emails via Workers. Use for email workers, forwarding, allowlists, or encountering Email Trigger errors, worker call failures, SPF issues.
Эксперт по CloudWatch алармам. Используй для настройки мониторинга AWS, метрик, порогов и уведомлений.
Master Kubernetes cluster administration, from initial setup through production management. Learn cluster installation, scaling, upgrades, and HA strategies.
Combine multiple related articles into one unified piece. Archives originals to preserve URLs.
Análise estática de código para identificar code smells, complexidade ciclomática, duplicações, violações de padrões, acoplamento excessivo, e métricas de qualidade. Usar para avaliar qualidade de código, identificar pontos de refatoração, medir débito técnico, verificar aderência a padrões PSR/SOLID, e gerar relatórios de qualidade para gestão.
Systematic techniques for reading and understanding unfamiliar legacy code without documentation
To initiate a release by executing the dx release command with appropriate parameters.
Token-efficient codebase exploration using MCP-first approach. Locates functions, classes, patterns, and traces dependencies with 80-90% token savings. Use when searching code, finding implementations, or tracing call chains.
Semantic code search using Phase 1 vector embeddings and Phase 2 hybrid search.
Execute a structured 4-phase codebase analysis workflow to gather insights.
name: codebase-understanding
Analyze codebase structure, dependencies, and changes. Use when user asks about project structure, where code is located, how files connect, what changed, or before starting any coding task. Provides instant architectural context.
Initial Convex workspace setup in Coder workspaces with self-hosted Convex deployment, authentication configuration, Docker setup, and environment variable generation
Coder workspace environment for hahomelabs.com deployments. Includes networking, ports, convex config, nhost config
Expert code writer - produces clean, production-ready code
Run Codex tasks via the ai_cli Task Tool runner.
Run Codex CLI inside a Podman container with full internet access but filesystem exposure limited to the repo root + explicit bind mounts; use when you want yolo/web-search without giving the agent access to your whole host filesystem.