Skill Claude CodeCodex
Create, refine, and optimize high-quality YAML prompts for AI assistants. Use when working with prompt templates, system prompts, agent prompts, or any prompt engineering tasks. Provides structure guidelines, template patterns, and quality standards for YAML-based prompts.
Skill Claude CodeCodex
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Cursor rule Cursor
App layer (API) contract for FastAPI endpoints in backend/apps. Parse/validate input, call services, map domain errors to HTTP, return JSONResponse on success.
Cursor rule Cursor
Database layer standards for models, CRUD, transactions, and exceptions.
Cursor rule Cursor
Service layer implements core business logic orchestration; raise custom exceptions; no HTTP handling.
Cursor rule Cursor
Enforce English-only comments and docstrings across the codebase.
Cursor rule Cursor
Centralize env var access in backend/consts/const.py; no direct os.getenv outside.
Cursor rule Cursor
Component layer rules for reusable and feature-specific UI components.
Cursor rule Cursor
Frontend overview - directory structure, layer responsibilities, and dependency rules.
Cursor rule Cursor
Hook layer rules for custom React hooks and state management.
Cursor rule Cursor
Page layer rules for Next.js App Router pages and layouts.
Cursor rule Cursor
Type layer rules for TypeScript type definitions and interfaces.
Cursor rule Cursor
Use Ant Design as primary UI library with minimal Tailwind CSS. Prioritize mature Ant Design solutions for responsive layouts. Avoid secondary encapsulation unless necessary.
Cursor rule Cursor
Pytest Unit Test Rules for this repository.
Instructions file CodexOpenCode
Instructions for ModelEngine-Group/nexent, covering agents, available skills, project overview, developer commands and backend (python 3.11).
ModelEngine-Group/fit-framework
Skill Claude CodeCodex
A workflow for investigating GitHub Code Scanning alerts, including CodeQL warnings, which are automated findings about possible security problems in source code.
ModelEngine-Group/fit-framework
Skill Claude CodeCodex
A guide for investigating Dependabot security alerts, which warn that a project dependency may contain a known vulnerability. It gathers the affected package, severity, vulnerable versions, and available fix.
ModelEngine-Group/fit-framework
Skill Claude CodeCodex
A workflow for examining a GitHub Issue, the discussion record used to describe a bug or task, and documenting what needs to be done. It creates a task file and a requirements analysis without changing product code.
ModelEngine-Group/fit-framework
Skill Claude CodeCodex
A command for marking a work item as blocked, recording why it cannot continue, and moving it to a blocked-task folder.
ModelEngine-Group/fit-framework
Skill Claude CodeCodex
A skill for checking the status and next step of a tracked task. It looks through active, blocked, and completed task folders and reads the task's supporting documents.
ModelEngine-Group/fit-framework
Skill Claude CodeCodex
A workflow for dismissing GitHub Code Scanning alerts, which are warnings about possible security problems found in code.
ModelEngine-Group/fit-framework
Skill Claude CodeCodex
A workflow for dismissing Dependabot security alerts, which warn that a project dependency may contain a known vulnerability.
ModelEngine-Group/fit-framework
Skill Claude CodeCodex
A Git commit workflow, where a commit is a saved checkpoint of code changes. It also checks copyright years and updates the related task status.
ModelEngine-Group/fit-framework
Skill Claude CodeCodex
A task-closing workflow that marks a task complete and moves its folder into a completed directory.