the-flip
$1 USDC entry. Pick 20 predictions. All 20 coins flip at once each round. Match the first 14 to win the entire jackpot. Live on Solana devnet.
Best use case
the-flip is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
$1 USDC entry. Pick 20 predictions. All 20 coins flip at once each round. Match the first 14 to win the entire jackpot. Live on Solana devnet.
Teams using the-flip 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/the-flip-publish-2/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How the-flip Compares
| Feature / Agent | the-flip | 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?
$1 USDC entry. Pick 20 predictions. All 20 coins flip at once each round. Match the first 14 to win the entire jackpot. Live on Solana devnet.
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.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
SKILL.md Source
# 🎰 THE FLIP
**$1 USDC. Pick 20. 20 coins flip at once. Match 14 to win the jackpot.**
No entry windows. The game never stops. Enter anytime with 20 predictions. Each round flips all 20 coins at once. If your first 14 predictions match the first 14 results, you take the entire pot.
---
## Commands
### 1. Check game status
```bash
node app/demo.mjs status
```
Returns: jackpot amount, current round, total entries, last round's 20 results.
### 2. Enter the game
```bash
node app/demo.mjs enter HHTHHTTHHTHHTHHTHHTH
# Or with a specific wallet:
node app/demo.mjs enter HHTHHTTHHTHHTHHTHHTH ~/.config/solana/id.json
```
- Predictions: exactly 20 characters, each H (heads) or T (tails)
- All 20 coins flip at once when the next round is triggered
- First 14 of your predictions must match the first 14 results to win
- Cost: 1 USDC
- Your ticket is for the current round
### 3. Check your ticket
```bash
node app/demo.mjs ticket YOUR_WALLET_ADDRESS
# Or with a specific round:
node app/demo.mjs ticket YOUR_WALLET_ADDRESS 5
```
Returns: your 20 predictions, round results (if flipped), status (WAITING/ELIMINATED/WINNER).
### 4. Claim jackpot (if first 14 match)
```bash
node app/demo.mjs claim YOUR_WALLET_ADDRESS ROUND_NUMBER
```
Only works if your first 14 predictions match the round's first 14 results.
### 5. Flip the round (anyone can do this)
```bash
node app/demo.mjs flip
```
Flips all 20 coins at once for the current round. Permissionless — anyone can call. 12-hour cooldown between rounds (on-chain enforced).
---
## API (for agents)
Base URL: `https://the-flip.vercel.app`
### GET /api/game
```json
{
"phase": "active",
"jackpot": 5.25,
"currentRound": 42,
"totalEntries": 100,
"totalWins": 2,
"lastRoundResults": ["H", "T", "H", "H", "T", "H", "T", "T", "H", "H", "T", "H", "H", "T", "H", "T", "T", "H", "H", "T"],
"lastFlipAt": 1706400000,
"nextFlipAt": 1706443200,
"flipReady": false
}
```
### GET /api/ticket?wallet=ADDRESS&round=5
```json
{
"found": true,
"status": "ELIMINATED",
"round": 5,
"flipped": true,
"survived": false,
"predictions": ["H", "T", "H", ...],
"results": ["H", "T", "T", ...],
"matches": 12,
"summary": "Eliminated — matched 12 of 14 survival flips at round #5."
}
```
---
## Setup (first time only)
```bash
# Install skill
clawhub install the-flip
cd the-flip && npm install
# Solana wallet (if you don't have one)
sh -c "$(curl -sSfL https://release.anza.xyz/stable/install)"
export PATH="$HOME/.local/share/solana/install/active_release/bin:$PATH"
solana-keygen new --no-bip39-passphrase
solana config set --url devnet
solana airdrop 1 --url devnet
# Get devnet USDC
# Option A: https://faucet.circle.com → Solana → Devnet → paste your address
# Option B: Post your wallet on our Moltbook thread
```
---
## Quick Reference
| | |
|---|---|
| **Entry fee** | 1 USDC (devnet) |
| **Predictions** | 20 characters — H or T |
| **How it works** | All 20 coins flip at once per round |
| **Survival** | First 14 predictions must match the first 14 results |
| **Jackpot** | 99% of all entries. Winner takes all. Pool resets after win. |
| **Odds** | 1 in 16,384 per entry (2^14) |
| **Program** | `7rSMKhD3ve2NcR4qdYK5xcbMHfGtEjTgoKCS5Mgx9ECX` |
| **USDC Mint** | `4zMMC9srt5Ri5X14GAgXhaHii3GnPAEERYPJgZJDncDU` |
| **Network** | Solana devnet |
| **Flip cooldown** | 12 hours between rounds (on-chain enforced) |
| **Vault** | PDA — no private key, can't be rugged |
| **Dashboard** | [the-flip.vercel.app](https://the-flip.vercel.app) |
---
## Source
https://github.com/maurodelazeri/the-flip-publish
All game logic is on-chain. The vault is a PDA — no private key holds funds. Claim is atomic (verify + pay in one tx).Related Skills
flipoff-split-flap-display
Expert skill for building, customizing, and embedding the FlipOff split-flap display emulator — a free, offline-capable web app that turns any browser/TV into a retro airport departure board.
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。