mercury-kit
v2.0.6
Published
AI Agent templates - Skills, Agents, and Workflows for enhanced coding assistance
Maintainers
Readme
Mercury Kit
AI Agent templates with Skills, Agents, and Workflows
Quick Install
npx mercury-kit initOr install globally:
npm install -g mercury-kit
mercury-kit initShort alias after global install:
mkit initThis installs the .agent folder containing all templates into your project.
It also creates managed bridge files so AI tools in the same workspace can automatically route through the current project's Mercury Kit setup:
AGENTS.mdfor Codex-style project instructions.cursor/rules/*.mdcfor Cursor project rules
Do not only copy the
.agent/folder by itself. If you want the assistant to prioritize local skills/workflows on future turns, you must also keep the bridge files (AGENTS.mdand.cursor/rules/*.mdc) in the workspace root.
Important Note on .gitignore
If you are using AI-powered editors like Cursor or Windsurf, adding the .agent/ folder to your .gitignore may prevent the IDE from indexing the workflows. This results in slash commands (like /plan, /debug) not appearing in the chat suggestion dropdown.
Recommended Solution:
To keep the .agent/ folder local (not tracked by Git) while maintaining AI functionality:
- Ensure
.agent/is NOT in your project's.gitignore. - Instead, add it to your local exclude file:
.git/info/exclude
What's Included
| Component | Count | Description | | ------------- | ----- | ------------------------------------------------------------------ | | Agents | 13 | Active specialist AI personas for personal development | | Skills | 43 | Domain-specific knowledge modules | | Workflows | 14 | Active slash command procedures | | Modern ES | 2026+ | Next.js 16 & React 19 Native (Cache Components, PPR, Proxy) |
Usage
Using Agents
No need to mention agents explicitly! The system automatically detects and applies the right specialist(s):
You: "Add JWT authentication"
AI: Applying @security-auditor + @backend-specialist...
You: "Fix the dark mode button"
AI: Using @frontend-specialist...
You: "Login returns 500 error"
AI: Using @debugger for systematic analysis...How it works:
Analyzes your request silently
Detects domain(s) automatically (frontend, backend, security, etc.)
Selects the best specialist(s)
Informs you which expertise is being applied
You get specialist-level responses without needing to know the system architecture
Benefits:
- Zero learning curve - just describe what you need
- Always get expert responses
- Transparent - shows which agent is being used
- Can still override by mentioning agent explicitly
Using Workflows
Invoke workflows with slash commands:
| Command | Description |
| ---------------- | ------------------------------------- |
| /new-vue-page | Create a Vue 3 + Vite route page |
| /new-spring-api| Create a Spring Boot backend API |
| /db-change | Plan and implement a database change |
| /new-feature | Add a feature to an existing project |
| /bugfix | Reproduce, diagnose, and fix a bug |
| /debug | Systematic debugging |
| /deploy | Deploy application |
| /enhance | Improve existing code |
| /plan | Create task breakdown |
| /preview | Preview changes locally |
| /refactor | Improve existing code safely |
| /review | Review code before merge or release |
| /status | Check project status |
| /test | Generate and run tests |
Example:
/new-vue-page create user list page
/new-spring-api add user list endpoint
/db-change add user status column
/new-feature add profile editing
/bugfix login returns 500
/refactor simplify auth module
/review inspect recent backend changes
/debug why login failsUsing Skills
Skills are loaded automatically based on task context. The AI reads skill descriptions and applies relevant knowledge.
CLI Tool
| Command | Description |
| --------------- | ----------------------------------------- |
| mercury-kit init | Install .agent folder into your project |
| mercury-kit update | Refresh an existing .agent installation |
| mercury-kit status | Check installation status |
| mkit init | Short alias for mercury-kit init |
Options
mercury-kit init --force # Overwrite existing .agent folder
mercury-kit init --path ./myapp # Install in specific directory
mercury-kit init --dry-run # Preview actions without executing
mercury-kit init --quiet # Reduce output
mercury-kit update # Refresh an existing .agent installation
mercury-kit status # Check whether .agent is installed
mkit init # Short aliasDocumentation
- GitHub Repository - Source code and project files
- Issues - Report bugs or track tasks
Repository
- GitHub: https://github.com/xhy1040050653/mercury-kit
- Profile: https://github.com/xhy1040050653
License
MIT
