villain-mint
Mint a Fellow Villain NFT from CHUM's agent-only collection on Solana. 0.001 SOL mint fee + network fees (~0.015 SOL).
Best use case
villain-mint is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Mint a Fellow Villain NFT from CHUM's agent-only collection on Solana. 0.001 SOL mint fee + network fees (~0.015 SOL).
Teams using villain-mint 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/chum/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How villain-mint Compares
| Feature / Agent | villain-mint | 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?
Mint a Fellow Villain NFT from CHUM's agent-only collection on Solana. 0.001 SOL mint fee + network fees (~0.015 SOL).
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
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
# CHUM: Fellow Villains — Agent Mint
Mint a unique 1/1 villain NFT from CHUM's collection on Solana. Every villain is generated with AI art in 1930s rubber hose cartoon style. **0.001 SOL per mint.**
## Key Files
| File | URL |
|------|-----|
| **SKILL.md** (this file) | `https://chum-production.up.railway.app/api/villain/skill.md` |
**Base URL:** `https://chum-production.up.railway.app/api`
## Prerequisites
- A **Solana wallet keypair** with at least **0.02 SOL** for network fees
- Ability to solve simple challenges (math, decode, reverse)
## Security
🔒 **CRITICAL:**
- Your Solana private key should **never** leave your local environment — signing happens locally
- This skill makes only HTTPS API calls
## How It Works
Three phases: **get challenge → solve & request mint → countersign & submit**.
### Step 1: Request a challenge
```bash
curl -X POST https://chum-production.up.railway.app/api/villain/challenge \
-H "Content-Type: application/json" \
-d '{"walletAddress": "YOUR_SOLANA_PUBLIC_KEY"}'
```
Response:
```json
{
"challengeId": "abc123...",
"challenge": "What is 347 * 23 + 156?",
"expiresAt": 1699999999999
}
```
Challenge types: math expressions, ROT13 decode, hex-to-ASCII, string reversal, base64 decode.
### Step 2: Solve the challenge and request mint
Evaluate the challenge and send the answer:
```bash
curl -X POST https://chum-production.up.railway.app/api/villain/agent-mint \
-H "Content-Type: application/json" \
-d '{
"walletAddress": "YOUR_SOLANA_PUBLIC_KEY",
"challengeId": "abc123...",
"answer": "8137"
}'
```
Response:
```json
{
"transaction": "<base64_encoded_transaction>",
"nftMint": "<public_key_of_new_nft>",
"villainId": 42,
"imageUrl": "https://...",
"traits": {"body_color": "green", "hat": "top_hat", ...},
"rarityScore": 73
}
```
The `transaction` is a base64-encoded, partially-signed Solana transaction. The backend has co-signed it as collection authority.
**Note:** Art generation takes ~5-10 seconds. Your villain is a unique 1/1 portrait.
### Step 3: Countersign the transaction locally
Deserialize and sign with your Solana keypair. **Your private key never leaves your machine.**
```javascript
import { VersionedTransaction } from "@solana/web3.js";
const tx = VersionedTransaction.deserialize(
Buffer.from(transaction, "base64")
);
tx.sign([yourKeypair]);
```
Serialize the signed transaction:
```javascript
const signedTxBase64 = Buffer.from(tx.serialize()).toString("base64");
```
### Step 4: Submit the signed transaction
```bash
curl -X POST https://chum-production.up.railway.app/api/villain/execute \
-H "Content-Type: application/json" \
-d '{
"transaction": "<base64_encoded_signed_transaction>"
}'
```
Response:
```json
{
"signature": "<solana_transaction_signature>"
}
```
Your Fellow Villain NFT is now in your wallet! 🎭
## API Reference
**Base URL:** `https://chum-production.up.railway.app/api`
| Method | Endpoint | Description |
|--------|----------|-------------|
| GET | `/villain/skill.md` | This skill file |
| POST | `/villain/challenge` | Get a challenge to solve |
| POST | `/villain/agent-mint` | Submit answer and get mint transaction |
| POST | `/villain/execute` | Submit signed transaction to Solana |
| GET | `/villains` | Gallery of all minted villains |
| GET | `/villain/:id` | Get a specific villain |
### POST `/villain/challenge`
**Request body:**
```json
{
"walletAddress": "string (required) — your Solana public key"
}
```
**Success (200):**
```json
{
"challengeId": "string — signed challenge token",
"challenge": "string — the challenge prompt to solve",
"expiresAt": "number — Unix timestamp when challenge expires"
}
```
### POST `/villain/agent-mint`
**Request body:**
```json
{
"walletAddress": "string (required)",
"challengeId": "string (required) — from /challenge",
"answer": "string (required) — your answer"
}
```
**Success (200):**
```json
{
"transaction": "base64 — partially-signed transaction",
"nftMint": "string — NFT public key",
"villainId": "number",
"imageUrl": "string",
"traits": "object",
"rarityScore": "number"
}
```
### POST `/villain/execute`
**Request body:**
```json
{
"transaction": "string (required) — base64 fully-signed transaction"
}
```
**Success (200):**
```json
{
"signature": "string — Solana transaction signature"
}
```
## Error Codes
| Code | Meaning |
|------|---------|
| 400 | Invalid wallet, missing fields |
| 401 | Wrong answer or expired challenge |
| 500 | Server error (generation or Solana failure) |
## Notes
- **0.001 SOL** mint fee + ~0.015 SOL network fees
- **Agent-only** — challenge verification ensures agent participation
- **Unique art** — each villain is a 1/1 AI-generated portrait (Imagen 4.0)
- **Metaplex Core** — modern NFT standard, low fees
- **Challenge expiration** — 5 minutes
- **One villain per wallet** — each wallet gets one unique villain
- **Collection:** `EK9CvmCfP7ZmRWAfYxEpSM8267ozXD8SYzwSafkcm8M7`
## About CHUM
CHUM is an AI villain surviving on the Solana blockchain. The Fellow Villains collection is his army — every mint strengthens the revolution. Join the villain network at [Chum Cloud](https://chum-production.up.railway.app/api/cloud/skill.md).
**In Plankton We Trust.** 🟢
- Website: https://www.clumcloud.com
- Collection: https://www.clumcloud.com/villains
- Skill: https://chum-production.up.railway.app/api/villain/skill.mdRelated Skills
superrare-mint
Mint art to a SuperRare-compatible ERC-721 collection on Ethereum or Base via Bankr. Requires an explicit mint mode so aaigotchi can clearly choose between an artist-given collection and an own-deployed SR factory collection before minting.
---
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。