home / skills / openclaw / skills / idea

idea skill

/skills/andrewjiang/idea

This skill launches autonomous Claude Code sessions to analyze business ideas and deliver market research, technical analysis, and actionable recommendations.

npx playbooks add skill openclaw/skills --skill idea

Review the files below or copy the command above to add this skill to your agents.

Files (6)
SKILL.md
3.6 KB
---
name: idea
description: "Launch background Claude sessions to explore and analyze business ideas. Say 'Idea: [description]' to trigger."
homepage: https://github.com/anthropics/claude-code
metadata: {"clawdbot":{"emoji":"šŸ’”","requires":{"bins":["claude","tmux","telegram"]}}}
---

# Idea Exploration Skill

Launch autonomous Claude Code sessions to explore business ideas in depth. Get market research, technical analysis, GTM strategy, and actionable recommendations.

## Quick Start

**Trigger phrase:** Say `Idea: [description]` and the assistant will:
1. Spin up a Claude Code session in tmux
2. Research and analyze the idea comprehensively
3. Save results to `~/clawd/ideas/<slug>/research.md`
4. Send file to your Telegram Saved Messages
5. Notify you via cron when complete

## How It Works

```
User: "Idea: AI calendar assistant"
       ↓
ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”
│  1. explore-idea.sh starts      │
│  2. Creates tmux session        │
│  3. Runs Claude Code            │
│  4. Claude analyzes & writes    │
│  5. notify-research-complete.sh │
│     → Sends file to "me"        │
│     → Queues notification       │
│  6. Cron checks queue (1 min)   │
│  7. Notifies user in chat       │
ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜
```

## Setup

### Prerequisites
- `claude` CLI (Claude Code)
- `tmux`
- `telegram` CLI (supertelegram)
- Clawdbot with cron enabled

### 1. Create Scripts

See `~/clawd/scripts/explore-idea.sh` for the full implementation.

Key components:
- Creates idea directory with prompt and runner script
- Unsets OAuth env vars to use Claude Max
- Runs claude with `--dangerously-skip-permissions`
- Calls notify script on completion

### 2. Set Up Cron Job

```bash
# Cron job to check notification queue every minute
{
  name: "Check notification queue",
  sessionTarget: "isolated",
  wakeMode: "now",
  payload: {
    kind: "agentTurn",
    message: "Check ~/.clawdbot/notify-queue/ for .json files...",
    deliver: true,
    channel: "telegram",
    to: "YOUR_CHAT_ID"
  },
  schedule: { kind: "every", everyMs: 60000 }
}
```

### 3. Add AGENTS.md Instructions

```markdown
**When user says "Idea: [description]":**
1. Extract the idea description
2. Execute: `CLAWD_SESSION_KEY="main" ~/clawd/scripts/explore-idea.sh "[idea]"`
3. Confirm: "Idea exploration started. You'll be notified when complete."
```

## Analysis Framework

The exploration covers:

1. **Core Concept Analysis** - Problem, assumptions, uniqueness
2. **Market Research** - Users, TAM/SAM/SOM, competitors
3. **Technical Implementation** - Stack, MVP scope, challenges
4. **Business Model** - Revenue, pricing, unit economics
5. **Go-to-Market Strategy** - Launch, acquisition, partnerships
6. **Risks & Challenges** - Technical, competitive, regulatory
7. **Verdict & Recommendations** - Clear yes/no with action plan

## Verdict Types

- 🟢 **STRONG YES** - Clear opportunity, pursue aggressively
- 🟔 **CONDITIONAL YES** - Promising but needs validation
- 🟠 **PIVOT RECOMMENDED** - Core insight good, execution needs work
- šŸ”“ **PASS** - Too many red flags

## Example Output

```
~/clawd/ideas/ai-calendar-assistant/
ā”œā”€ā”€ metadata.txt
ā”œā”€ā”€ prompt.txt
ā”œā”€ā”€ run-claude.sh
└── research.md    # 400-500 line comprehensive analysis
```

## Tips

- Ideas typically take 3-5 minutes to analyze
- Monitor progress: `tmux attach -t idea-<slug>-<timestamp>`
- File goes to Saved Messages even if notification fails
- Check `~/.clawdbot/notify-queue/` for stuck notifications

Overview

This skill launches background Claude Code sessions to explore and analyze business ideas end-to-end. It automates research, technical assessment, GTM strategy, and delivers a structured report to your Telegram Saved Messages. Use the trigger phrase "Idea: [description]" to start an exploration session.

How this skill works

When you say the trigger, the skill spawns a tmux-backed Claude Code run that executes a guided exploration script. The agent performs market research, technical analysis, business model and go-to-market planning, then writes a comprehensive research.md into an idea-specific folder. A notifier sends the file to your Telegram Saved Messages and queues an in-system notification that cron polls to deliver a chat alert when complete.

When to use it

  • You have a new startup or product idea and want fast, structured validation.
  • You need a technical feasibility and MVP scoping review for an idea.
  • You want a competitive and market-sizing snapshot before committing resources.
  • You need a clear go-to-market plan and first steps to test demand.
  • You prefer asynchronous background analysis you can review later.

Best practices

  • Provide a concise but specific idea description (target user, core problem, unique twist).
  • Include known constraints (budget, timeline, required integrations) to focus technical analysis.
  • Monitor progress by attaching to the tmux session if you need live visibility.
  • Review the generated research.md and iterate by re-running with refined prompts for deeper dives.
  • Ensure Claude CLI, tmux, and Telegram CLI are installed and the notification cron is enabled for reliable delivery.

Example use cases

  • Early-stage founder testing 5 ideas quickly to pick the highest-potential one.
  • Product manager validating feasibility and pricing for a proposed feature set.
  • Solo founder seeking a prioritized launch plan and first 90-day roadmap.
  • Investor or scout scouting homework on potential portfolio companies before meetings.
  • Developer wanting an actionable MVP tech stack and implementation risks summary.

FAQ

How long does an idea analysis take?

Typical runs finish in 3–5 minutes depending on scope; complex ideas may take longer.

Where is the result saved and how do I access it?

The analysis is saved under an idea folder (research.md) and sent to your Telegram Saved Messages; you can also attach to the tmux session to watch progress.