meme-scout
Skill36 starsChanged 10 months agoMITView on GitHub
Comprehensive tool for scouting trending meme coins on DEX platforms like DexScreener. Use for discovering trending tokens, analyzing price movements, volume data, and risk assessments. Supports multiple timeframes (5m, 1h, 6h, 24h) and includes risk checking capabilities for specific tokens.
In this repository5 other files it gives its agents.
- evm-swiss-knifeSkill
- market-sentimentSkill
- token-minterSkill
- trading-strategistSkill
- yield-opportunitiesSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Use curl to fetch the HTML from the appropriate URL
- Distinctive: line 47
On-chain Analysis: Check creator wallet, liquidity locks, token distribution
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Meme Scout
This skill provides workflows for finding and analyzing trending meme coins on decentralized exchanges.
Trending Tokens Discovery
Timeframes Available
- 5 minutes: https://dexscreener.com/?rankBy=trendingScoreM5&order=desc
- 1 hour: https://dexscreener.com/?rankBy=trendingScoreH1&order=desc
- 6 hours (default): https://dexscreener.com/
- 24 hours: https://dexscreener.com/?rankBy=trendingScoreH24&order=desc
How to Fetch Trending Data
- Use curl to fetch the HTML from the appropriate URL
- Extract the __SERVER_DATA from the script tag using sed
- Parse the JSON with Node.js VM to get the pairs array
- Each pair contains: baseToken (name, symbol, address), priceUsd, priceChange (m5, h1, h6, h24), volume, liquidity, etc.
Example command for top 10 trending:
curl -s "https://dexscreener.com/?rankBy=trendingScoreH24&order=desc" | sed -n 's/.*window\.__SERVER_DATA\s*=\s*\(.*\);.*/\1/p' | node -e "
const fs = require('fs');
const input = fs.readFileSync(0, 'utf-8').trim();
const code = 'data = ' + input;
const vm = require('vm');
const sandbox = {data: null, URL: URL, Date: Date, undefined: undefined};
vm.runInNewContext(code, sandbox);
const pairs = sandbox.data.route.data.dexScreenerData.pairs.slice(0,10);
pairs.forEach(p => console.log(\`\${p.baseToken.name} | \${p.chainId} | $\${p.priceUsd} | \${p.priceChange.h24}% | \${p.baseToken.address}\`));
"Risk Assessment for Specific Tokens
Steps to Check Risk
- DexScreener Audit: Visit the pair page (https://dexscreener.com/{chainId}/{pairAddress}) and check the "Audit" section
- RugCheck.xyz: For Solana tokens, use https://rugcheck.xyz/tokens/{tokenAddress}
- On-chain Analysis: Check creator wallet, liquidity locks, token distribution
- General Red Flags: Anonymous teams, Pump.fun origin, extreme volatility, no utility
Risk Levels
- Low: Verified team, audited contracts, locked liquidity
- Medium: Some transparency, basic audit, moderate volatility
- High: Anonymous creator, no locks, Pump.fun token, high volatility
- Extreme: Recent creation, suspicious patterns, social hype without substance
References
See references/ for detailed guides:
- DEX Screener API
- Risk Assessment Guide
- Pump.fun Risks
Scripts
- scripts/fetch-trending.js: Node.js script for fetching trending data
- scripts/check-risk.sh: Bash script for basic risk checks
</content><parameter name="filePath">./skills/meme-scout/SKILL.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

