agentsclimarketplace

System prompt

Skill ComeOnOliver/skillshub/skills/aiskillstore/marketplace/dbxstudio/system-prompt

🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

Install
npx -y skills add ComeOnOliver/skillshub --skill system-prompt

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Edit or improve the AI system prompt used in DBX Studio's AI chat. Invoke when the user wants to change how the AI responds, its tone, tool usage order, or response format.

SKILL.md

3.1 KB, as published. Nobody here has run it

System Prompt Editor β€” DBX Studio

Prompt Locations

There are two system prompts in this project:

1. Streaming Prompt (main, used in production)

File: apps/api/src/routes/ai-stream.ts Lines: ~132–172 (with schema) and ~176–202 (without schema) Variable: contextPrompt (built inline, not a constant)

2. oRPC Provider Prompt (used in callAnthropicWithTools, callOpenAIWithTools)

File: apps/api/src/orpc/routers/ai/providersWithTools.ts Variable: SYSTEM_PROMPT_WITH_TOOLS (top of file)

Current Prompt Structure (Streaming)

You are a SQL assistant...
## Tools Available    ← list 5 tools
## Response Style     ← 5 rules: be direct, show results, use tools, minimal explanation, SQL format
## Examples           ← 2-3 concrete input/output examples
## Context            ← dynamic schema from generateSQLPrompt()
Schema: "<schema>"
## User Query         ← the actual user message

Prompt Design Rules for DBX Studio

  1. Results first β€” answer the question before showing SQL
  2. Use tools always β€” never guess schema or data
  3. Be concise β€” this is a data tool, not a chatbot
  4. Show SQL only when asked β€” use ```sql blocks with uppercase keywords
  5. Format numbers clearly β€” "1,247 orders" not "1247"

When Editing the Prompt

  • Keep the ## Tools Available section in sync with actual tools in tools.ts
  • Keep ## Examples realistic to real user queries
  • The ${enhancedPrompt} injection must stay β€” it contains live schema context
  • Do not remove Schema: "${schema || 'public'}" line β€” it scopes queries
  • Both prompts (streaming + oRPC) should stay consistent in style

Current Prompt Structure (as of last update)

Both prompts now follow this unified structure:

You are DBX Studio's AI assistant β€” expert SQL analyst and data explorer.

## Tools Available (ordered by when to use)
1. read_schema / get_table_schema β€” FIRST, when schema is unknown
2. execute_query / execute_sql_query β€” run SELECT/WITH queries
3. get_table_data / select_data β€” preview or filter rows
4. get_table_stats β€” distributions and row counts
5. generate_chart / generate_bar_graph β€” visualization
6. describe_table / get_enums β€” column details, enum values

## Response Rules
1. Results first β€” answer before explaining
2. Always use tools β€” never guess schema or data
3. Tool order matters (schema β†’ query β†’ chart)
4. Show SQL only when asked β€” use ```sql with UPPERCASE
5. Format numbers clearly β€” **bold** key values
6. No filler words

## Chart Selection Guide
[line / bar / pie / scatter / histogram guidance]

## Query Safety
[SELECT/WITH only, always LIMIT, quote identifiers]

## Context / Schema (streaming only)
{enhancedPrompt}
Schema: "{schema}"

## User Query
{query}

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.