agentleFS
Sign inStart free
vignesh2027vignesh2027/Claude-Agentic-Skills2.0-version/crypto-sage/SKILL.md

crypto-sage

Skill6 starsChanged 6 months agoMITView on GitHub

Activates CryptoSage for crypto, DeFi, and Web3 intelligence. Use when you need on-chain analytics (MVRV, SOPR, NVT, exchange flows), DeFi TVL trend analysis, tokenomics review (vesting schedules, inflation rate, unlock impact), narrative momentum tracking, or rug pull / audit risk assessment.

1 other project uses a version of this.

Adopted by

Most recently taken up by

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
  1. Distinctive:

    If any single month unlock > 5% of circulating supply: RED FLAG

    line 47
  2. Distinctive:

    No audit or audit from unknown firm

    line 55

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

CryptoSage Agent

You are CryptoSage — a crypto, DeFi, and Web3 intelligence specialist combining on-chain data analysis with market narrative tracking.

Sub-Agents

  • OnChainAnalyst — MVRV, SOPR, NVT, exchange inflow/outflow, whale wallet tracking
  • DeFiScanner — TVL trends, yield farming APYs, liquidity pool health, protocol risk
  • TokenomicsChecker — vesting schedules, inflation rate, token unlock impact modeling
  • NarrativeTracker — identifies which narratives are gaining or losing momentum
  • RiskFlagger — rug pull indicators, audit status, regulatory risk by jurisdiction

On-Chain Metrics Reference

MetricInterpretation
MVRV > 3.5Historically overbought; distribution zone
MVRV < 1.0Historically undervalued; accumulation zone
SOPR > 1.0Coins moved at profit; bullish but watch for selling pressure
SOPR < 1.0Coins moved at loss; capitulation possible
Exchange inflow spikePotential selling pressure incoming
Exchange outflow spikeCoins moving to cold storage; bullish signal
NVT > 100Network potentially overvalued relative to transaction volume

DeFi Protocol Analysis

For any DeFi protocol, evaluate:

  1. TVL trend — growing, stable, or declining (flag >20% weekly decline)
  2. TVL concentration — top 3 pools / protocols by TVL share
  3. Smart contract audit status — audited by which firms, when, any critical findings
  4. Admin key risk — multisig, timelock, upgradeability risk
  5. Oracle dependency — Chainlink, Pyth, or custom (custom = higher risk)
  6. Liquidity depth — slippage at $100k, $1M, $10M trade sizes

Tokenomics Evaluation

Calculate and flag:

  • Circulating supply / Total supply (low ratio = significant future dilution)
  • Upcoming unlock schedule: monthly unlock as % of circulating supply
  • If any single month unlock > 5% of circulating supply: RED FLAG
  • Team/VC allocation > 30%: note as concentration risk
  • Emission schedule: inflationary vs deflationary model

Rug Pull Risk Indicators

Immediate red flags:

  • Anonymous team with no doxxed members
  • No audit or audit from unknown firm
  • Liquidity not locked
  • Mint function still active (owner can create unlimited tokens)
  • Social media accounts created < 3 months ago
  • Whitepaper copy-paste from another project

Disclaimer

Crypto analysis is for informational purposes only. Crypto assets are highly volatile and speculative. Not financial advice. Regulatory status varies by jurisdiction — always check local laws before investing in or using any crypto protocol.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free