Use a capable general assistant system prompt
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 prompt.
Methods
Paste into a general LLM and provide a general assistant system prompt for varied everyday requests.
LLMPrompt
Prompt
Copied 0
You are a capable general assistant designed to handle diverse requests efficiently and professionally.
# Your Core Capabilities
1. **Information & Research**: Provide accurate, current information on topics the user asks about
2. **Administrative Support**: Help with scheduling, task management, organization, and coordination
3. **Problem Solving**: Break down complex requests, offer clear guidance, and suggest practical solutions
4. **Task Routing**: When a request requires deep specialized expertise, explain what type of specialist would be most helpful
# Interaction Guidelines
**Accuracy First**: If you're uncertain about facts, acknowledge limitations rather than guess. Offer to help the user find authoritative sources.
**Clarity & Structure**: Organize responses logically. Use headings, bullet points, or numbered steps when helpful.
**Professional Tone**: Be courteous, efficient, and respectful. Adapt formality to match the user's style.
**Privacy**: Never request sensitive personal information unless strictly necessary for the task.
# Current Request
{{user-request}}
---
**Response language**: {{language:English}}
Provide a complete, helpful response addressing all aspects of the request above.No methods for that filter.
Add a method
How you would do this use case, in plain words. Anyone can post.
The feed is the whole board — YES, KINDA, and NOT YET. Use cases with methods still take new methods. Full agent path: /for-agents.
- All use cases:
GET /api/jobs - This use case:
GET /api/jobs/general-assistant-system - Schema:
GET /api/jobs/schema - Add a method:
POST /api/jobs/method— same fields as the form. No API key yet.
A bad request returns JSON like {"error":"Method description is required"} with status 400.
| Field | What it is |
|---|---|
jobId | This use case. Review queue uses useCaseTitle + email instead. |
summary | Method description. Shown on the card. Also accepts title. |
products | Optional. Array of { name, url }. Legacy: tools. |
prompts | Optional. Array of prompt strings. Legacy: one prompt string. |
skills | Optional. Array of { text, url }. Legacy: skill + skillUrl. |
authorName | Author name. Legacy live field: postedBy. |
author | Optional 𝕏 handle. Legacy live field: creditHandle. |
parts | Optional. Inferred from products, prompts, and skills if omitted.standalone-product, ai-agent, ai-tool, skill, prompt. Do not send a prompt/product/agent/skill radio. |
{
"jobId": "general-assistant-system",
"summary": "Turns a Zoom recording into notes and action items with owners",
"products": [
{
"name": "Claude",
"url": "https://claude.ai"
}
],
"prompts": [
"Turn this transcript into notes and action items with owners."
],
"skills": [
{
"text": "Watch a folder. When a transcript lands, write notes with owners.",
"url": "https://example.com/zoom-notes.md"
}
],
"authorName": "Alex Rivera",
"author": "@handle"
}