ai-tools
Reference for all AI tools available in DBX Studio's AI chat system. Use when adding, modifying, or debugging AI tool definitions, tool execution, or provider integrations.
Best use case
ai-tools is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Reference for all AI tools available in DBX Studio's AI chat system. Use when adding, modifying, or debugging AI tool definitions, tool execution, or provider integrations.
Teams using ai-tools should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/ai-tools/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ai-tools Compares
| Feature / Agent | ai-tools | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Reference for all AI tools available in DBX Studio's AI chat system. Use when adding, modifying, or debugging AI tool definitions, tool execution, or provider integrations.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# DBX Studio AI Tools Reference
## Tool Definitions Location
[apps/api/src/orpc/routers/ai/tools.ts](apps/api/src/orpc/routers/ai/tools.ts)
## Tool Executor Location
[apps/api/src/orpc/routers/ai/toolExecutor.ts](apps/api/src/orpc/routers/ai/toolExecutor.ts)
## Available Tools (AI_TOOLS array)
| Tool Name | Purpose | Required Params |
|-----------|---------|-----------------|
| `read_schema` | Get all tables and structure from schema store | `schema_name` |
| `get_table_data` | Preview rows from a table (generates SELECT) | `table_name` |
| `execute_query` | Run a SELECT/WITH query | `sql` |
| `generate_chart` | Create chart config (bar/line/pie/scatter/area/histogram) | `chart_type`, `title`, `data_query` |
| `describe_table` | Get table metadata from `schemaTables` DB table | `table_name` |
| `get_table_stats` | Get statistics summary for a table | `table_name` |
## AI Providers
| Service ID | Provider | File |
|------------|----------|------|
| 1 | AWS Bedrock | `ai-stream.ts` (streaming) + `providersWithTools.ts` |
| 2 | OpenAI | `providersWithTools.ts` → `callOpenAIWithTools` |
| 3 | Anthropic | `providersWithTools.ts` → `callAnthropicWithTools` |
| 4 | Qwen | `index.ts` |
| 5 | Ollama | `index.ts` |
| 6 | Gemini | `index.ts` |
| 7 | Groq | `index.ts` |
| 8 | DBX Agent | External → `MAIN_SERVER_URL` |
## Tool Format Conversions
```typescript
// Anthropic format
getAnthropicTools() → { name, description, input_schema }
// OpenAI format
getOpenAITools() → { type: 'function', function: { name, description, parameters } }
// Bedrock format (in ai-stream.ts)
{ toolSpec: { name, description, inputSchema: { json: input_schema } } }
```
## Adding a New Tool
1. Add to `AI_TOOLS` array in `tools.ts`
2. Add execution logic in `toolExecutor.ts` → `executeTool` switch
3. Implement the handler function `executeMyNewTool(input, context)`
4. Both `getAnthropicTools()` and `getOpenAITools()` will pick it up automatically
5. For Bedrock, the conversion in `ai-stream.ts` is also automatic
## System Prompt Location
Main streaming system prompt: [apps/api/src/routes/ai-stream.ts](apps/api/src/routes/ai-stream.ts) around line 132–172
oRPC chat system prompt: [apps/api/src/orpc/routers/ai/providersWithTools.ts](apps/api/src/orpc/routers/ai/providersWithTools.ts) — `SYSTEM_PROMPT_WITH_TOOLS` constantRelated Skills
mermaid-tools
Extracts Mermaid diagrams from markdown files and generates high-quality PNG images using bundled scripts. Activates when working with Mermaid diagrams, converting diagrams to PNG, extracting diagrams from markdown, or processing markdown files with embedded Mermaid code.
markdown-tools
Converts documents to markdown with multi-tool orchestration for best quality. Supports Quick Mode (fast, single tool) and Heavy Mode (best quality, multi-tool merge). Use when converting PDF/DOCX/PPTX files to markdown, extracting images from documents, validating conversion quality, or needing LLM-optimized document output.
no-tools
Instructions only skill
security-scanning-tools
This skill should be used when the user asks to "perform vulnerability scanning", "scan networks for open ports", "assess web application security", "scan wireless networks", "detect malware", "check cloud security", or "evaluate system compliance". It provides comprehensive guidance on security scanning tools and methodologies.
scanning-tools
This skill should be used when the user asks to "perform vulnerability scanning", "scan networks for open ports", "assess web application security", "scan wireless networks", "detec...
red-team-tools
This skill should be used when the user asks to "follow red team methodology", "perform bug bounty hunting", "automate reconnaissance", "hunt for XSS vulnerabilities", "enumerate su...
red-team-tools-and-methodology
This skill should be used when the user asks to "follow red team methodology", "perform bug bounty hunting", "automate reconnaissance", "hunt for XSS vulnerabilities", "enumerate subdomains", or needs security researcher techniques and tool configurations from top bug bounty hunters.
n8n-mcp-tools-expert
Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.
tools-ui
Tool lifecycle UI components for React/Next.js from ui.inference.sh. Display tool calls: pending, progress, approval required, results. Capabilities: tool status, progress indicators, approval flows, results display. Use for: showing agent tool calls, human-in-the-loop approvals, tool output. Triggers: tool ui, tool calls, tool status, tool approval, tool results, agent tools, mcp tools ui, function calling ui, tool lifecycle, tool pending
agent-tools
Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok
receipt-scanning-tools
This skill helps you work with the receipt scanning tools in the nonprofit_finance_db project. It includes manual entry tools, automated OCR scanning, and database integration for tracking receipts...
dev-tools-skill
Use when the user says "use the DevTools skill" or when they need help debugging a web app with Chrome DevTools MCP (UI bugs, incorrect behavior, console errors, network/API failures, or performance/lag), especially if the user seems inexperienced and needs guided, step-by-step diagnosis.