Backend

Implement comprehensive validation with server-side enforcement, client-side UX feedback, early failure, specific error messages, allowlists over blocklists, type checking, input sanitization, and consistent validation across all entry points. Use this skill when implementing validation logic in forms, API endpoints, data models, user inputs, or any data processing. Apply when validating form inputs, API request parameters, database model fields, implementing client-side validation for user experience, enforcing server-side validation for security, sanitizing user input to prevent injection attacks, checking data types and formats, validating business rules, or providing field-specific error messages. Use for any task involving input validation, data integrity checks, security validation, or user input processing.

Use when creating Zed extensions with custom slash commands, language support, themes, or MCP servers - provides Rust/WASM extension structure, slash command API (run_slash_command, SlashCommandOutput), and development workflow for compiled extensions

Define database models with clear naming, appropriate data types, constraints, relationships, and validation at multiple layers. Use this skill when creating or modifying database model files, ORM classes, schema definitions, or data model relationships. Apply when working with model files (e.g., models.py, models/, ActiveRecord classes, Prisma schema, Sequelize models), defining table structures, setting up foreign keys and relationships, configuring cascade behaviors, implementing model validations, adding timestamps, or working with database constraints (NOT NULL, UNIQUE, foreign keys). Use for any task involving data integrity enforcement, relationship definitions, or model-level data validation.

Instrument API requests with spans and distributed tracing. Use when tracking request latency, correlating client-backend traces, or debugging API issues.

Bypass a Coraza WAF protecting a vulnerable Next.js 16 backend. Analyze parser differentials between Go (WAF) and Node.js (backend) to find bypasses.

Node.js development principles and decision-making. Framework selection, async patterns, security, and architecture. Teaches thinking, not copying.

Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.

API design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination. Teaches thinking, not fixed patterns.

Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

Documentation templates and structure guidelines. README, API docs, code comments, and AI-friendly documentation.

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Use gh CLI for all GitHub operations like PRs, issues, workflows, releases. Always prefer gh commands over web URLs or API calls.

多AI协作编排技能 - 自动协调Claude、Codex、Gemini完成需求分析→代码生成→代码审查工作流。 【核心触发场景】 - 开发任务、写代码、实现功能、编程任务 - 新功能开发、功能实现、代码实现 - 重构、优化代码、代码改进 - Bug修复、问题修复、错误处理 - 系统设计、架构设计、模块设计 【显式触发词】 - "AI编排"、"ai编排"、"多AI协作"、"三引擎"、"三AI" - "codex"、"gemini"、"kim team"、"kim-team" - "协作开发"、"编排流程" 【任务类型触发】 - 实现XXX功能、开发XXX模块、写一个XXX - 创建XXX、构建XXX、搭建XXX - 添加XXX功能、新增XXX特性 - 修改XXX、更新XXX、升级XXX - 修复XXX、解决XXX问题 - 重构XXX、优化XXX性能 - 设计XXX架构、规划XXX系统 【技术任务触发】 - API开发、接口实现、后端开发、前端开发 - 数据库设计、表结构、CRUD操作 - 用户认证、登录注册、权限控制 - 文件处理、数据导入导出 - 第三方集成、SDK接入

This skill should be used when the user asks to "update dependencies", "update npm packages", "run taze", "upgrade node packages", "check for outdated packages", "update package.json", or mentions dependency updates, npm/pnpm/yarn package upgrades, or taze CLI usage.

Example skill demonstrating nested directory structure at depth 3

Example skill in category B demonstrating flat organization within nested structure

Example skill demonstrating nested directory structure at depth 2

Example skill at the root of the nested structure demonstrating depth 1