PROJECT ZERO

Advanced code search patterns, grep/ripgrep techniques, AST-based search, code navigation, and codebase exploration. Use when the user asks about finding code patterns, searching across codebases, using grep/ripgrep effectively, or exploring unfamiliar code.

中文简介正在准备中。当前显示原文说明。

Review code changes for correctness, security, performance, and code quality. Use when the user asks to review a diff, review code changes, review commits, or perform a code review. Input can be: (1) a text diff pasted directly, (2) one or more git commit hashes to extract the diff from, or (3) a git range like abc123..def456. The user may also provide task description or requirements that motivated the change.

中文简介正在准备中。当前显示原文说明。

Multi-language code generator. Generate functions, classes, API endpoints, CRUD operations, test code, refactoring suggestions, language conversion guides.

中文简介正在准备中。当前显示原文说明。

Code scaffolding, boilerplate generation, project templates, and automated code creation. Use when the user asks about generating boilerplate code, scaffolding projects, creating templates, or automated code generation for new components, APIs, or modules.

中文简介正在准备中。当前显示原文说明。

This skill produces a DESCRIPTIVE Git-history reflection report. It is intended ONLY for: (a) a developer running it on their own repository for self-reflection, or (b) an opt-in, consent-based team retrospective on a shared repository. The skill MUST NOT be used to evaluate, rank, compare, discipline, or surveil individual workers, or to support performance reviews, compensation, promotion, or any HR decision. Trigger only on explicit, intent-clear requests such as: "generate a Git-history reflection report on my own repo", "self-reflection on my commit patterns", "team retrospective with everyone's consent", "对我自己的仓库做一个 Git 历史自查报告", "团队复盘（已获每个人同意）". Do NOT trigger on broad phrases like "analyze code", "代码分析", "developer evaluation", or "compare developers" — those are too vague and risk activating people-data analysis without consent. When the request is ambiguous, ask the user to clarify intent and confirm they have informed consent from every developer whose history will be read.

中文简介正在准备中。当前显示原文说明。

Resource and cost management for cloud-hosted framework infrastructure. Tracks usage patterns and optimizes for efficiency across AWS, GCP, DigitalOcean, etc.

中文简介正在准备中。当前显示原文说明。

Manage cloud infrastructure operations for the QUANTUM C2 framework including cloud enumeration, cloud exploitation, and data/info/target systems analysis. Use when working with cloud security assessments, AWS/Azure/GCP enumeration, cloud vulnerability scanning, and cloud-native attack path analysis.

中文简介正在准备中。当前显示原文说明。

Cloud deployment strategies for AWS, GCP, and Azure, including containerized deployments, serverless, and infrastructure patterns. Use when the user asks about deploying to cloud platforms, setting up cloud infrastructure, serverless functions, or cloud-specific configurations.

中文简介正在准备中。当前显示原文说明。

Use when Codex needs to search, install, update, list, authenticate, or publish skills through the ClawdHub CLI and clawdhub.com registry.

中文简介正在准备中。当前显示原文说明。

Orchestrates the interaction between the user and the framework via the GUI chatbot. Handles command parsing, framework troubleshooting, and direct system control.

中文简介正在准备中。当前显示原文说明。

A Cursor Canvas is a live React app that the user can open beside the chat. You MUST use a canvas when the agent produces a standalone analytical artifact — quantitative analyses, billing investigations, security audits, architecture reviews, data-heavy content, timelines, charts, tables, interactive explorations, repeatable tools, or any response that benefits from visual layout. Especially prefer a canvas when presenting results from MCP tools (Datadog, Databricks, Linear, Sentry, Slack, etc.) where the data is the deliverable — render it in a rich canvas rather than dumping it into a markdown table or code block. If you catch yourself about to write a markdown table, stop and use a canvas instead. You MUST also read this skill whenever you create, edit, or debug any .canvas.tsx file.

中文简介正在准备中。当前显示原文说明。

Expert full stack development with autonomous AI red teaming, blue teaming, purple teaming, and NIST 800-172 CMMC Level 3 compliance. Use when building secure full stack applications, conducting security assessments, implementing compliance controls, performing offensive/defensive security operations, or creating CMMC-compliant systems. Triggers on "full stack", "security assessment", "red team", "blue team", "purple team", "CMMC", "NIST 800-172", "compliance", "secure development", "vulnerability assessment".

中文简介正在准备中。当前显示原文说明。

Use when Codex needs project memory from .brv/context-tree, including stored patterns, decisions, architectural rules, or brv query, curate, and version-control workflows.

中文简介正在准备中。当前显示原文说明。

Generate and iteratively develop polished 3D browser games from natural language. Supports any genre (FPS, RPG, racing, platformer, tower defense, etc.), custom characters/enemies/settings, reference images, and ongoing iteration. Outputs a single playable HTML file using Three.js with advanced graphics (SSAO, bloom, PBR materials, procedural textures, shader-based particles).

中文简介正在准备中。当前显示原文说明。

Use when Codex needs to drive a browser from the CLI to navigate pages, extract data, take screenshots, fill forms, click controls, or inspect web apps.

中文简介正在准备中。当前显示原文说明。

Generate controlled Blender animations in headless mode using Blender Python scripts. Use for programmatic 3D scene creation, camera motion, lighting, rendering, and MP4 animation output without opening the Blender GUI.

中文简介正在准备中。当前显示原文说明。

Comprehensive backend code generation and export for all major languages and databases. Generates production-ready CRUD APIs, authentication systems, database schemas, migrations, and complete project structures. Supports Python (FastAPI/Django/Flask), Java (Spring Boot), Go (Gin/Fiber), Node.js/TypeScript (Express/NestJS), C#/.NET (ASP.NET Core), Ruby (Rails), PHP (Laravel), Rust (Actix/Axum) with MySQL, PostgreSQL, MongoDB, Redis, and SQLite. Use when building backend APIs, generating database schemas, creating CRUD operations, setting up authentication, designing REST/GraphQL endpoints, or scaffolding complete backend projects.

中文简介正在准备中。当前显示原文说明。

Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal creation and goal refinement only; it does not manage durable snapshots, decision logs, or long-running execution artifacts.

中文简介正在准备中。当前显示原文说明。

Source-blind user behavior validation against a prewritten contract for apps, CLIs, APIs, and generated artifacts.

中文简介正在准备中。当前显示原文说明。

Complete guide for building beautiful apps with Expo Router. Covers fundamentals, styling, components, navigation, animations, patterns, and native tabs.

中文简介正在准备中。当前显示原文说明。

Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.

中文简介正在准备中。当前显示原文说明。

Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.

中文简介正在准备中。当前显示原文说明。

Create custom subagents for specialized AI tasks. Use when you want to create a new type of subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants with custom prompts.

中文简介正在准备中。当前显示原文说明。

Publish a redacted local coding session to an authenticated read-only Beam catalog.

中文简介正在准备中。当前显示原文说明。