Agent skill

Analyzing On Chain Data

by jeremylongshore in jeremylongshore/tons-of-skills-marketplace

Process perform on-chain analysis including whale tracking, token flows, and network activity.

MITAuto-check passedBusiness, Finance & HR

Install Analyzing On Chain Data

skills CLI
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill analyzing-on-chain-data -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace analyzing-on-chain-data --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/.curated/analyzing-on-chain-data .claude/skills/analyzing-on-chain-data && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
analyzing-on-chain-data
GitHub stars
2.8k
Token cost
~1.5k tokens
SKILL.md length
633 words
Files
11 (incl. scripts, references)
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

Process perform on-chain analysis including whale tracking, token flows, and network activity.

  • Works in 10 steps: Run python onchain_analytics.py… → Filter protocol results by category… → Filter by chain with --chain ethereum or… → …
  • Performing crypto analysis
  • SKILL.md covers Overview, Prerequisites, Instructions and Output, plus 3 more sections
  • Runs Python scripts from its folder; calls python

What it does

Analyzing On Chain Data is an agent skill from jeremylongshore/tons-of-skills-marketplace. Process perform on-chain analysis including whale tracking, token flows, and network activity. Use when performing crypto analysis. Trigger with phrases like "analyze crypto", "check blockchain", or "monitor market".

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including scripts and reference files (for example `ARD.md`, `PRD.md` and `config/settings.yaml`). Compatibility notes: Designed for Claude Code

It sits in Business, Finance & HR, covering Crypto and DeFi analysis and Smart contracts. It works with Ethereum and Python. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.

When your agent uses it

  • Performing crypto analysis
  • With phrases like analyze crypto
  • Check blockchain

Example prompts

  • “analyze crypto”
  • “check blockchain”
  • “monitor market”
  • “/analyzing-on-chain-data”

Requirements

  • Python 3
  • Compatibility (from SKILL.md): Designed for Claude Code
  • Pre-approved tools (allowed-tools): Read, Write, Edit, Grep, Glob, Bash(crypto:onchain-*)

Workflow steps

10 steps, taken from the first numbered list in SKILL.md.

  1. Run python onchain_analytics.py protocols to retrieve the top DeFi protocols ranked by total value locked (TVL).
  2. Filter protocol results by category using --category lending, --category dex, or --category "liquid staking" to narrow the scope.
  3. Filter by chain with --chain ethereum or --chain arbitrum to isolate chain-specific protocol data.
  4. Sort results by alternative metrics using --sort market_share or --sort tvl_to_mcap to surface undervalued protocols.
  5. Run python onchain_analytics.py chains to retrieve chain-level TVL rankings across all tracked networks.
  6. Run python onchain_analytics.py fees --protocol aave to pull fee and revenue data for a specific protocol.
  7. Run python onchain_analytics.py dex --chain ethereum to analyze DEX trading volumes filtered by chain.
  8. Run python onchain_analytics.py yields --min-tvl 5000000 --chain ethereum to identify yield opportunities above a minimum TVL threshold.
  9. Run python onchain_analytics.py trends --threshold 5 to detect protocols with significant TVL changes (threshold is percentage).
  10. Export results in JSON or CSV format using --format json or --format csv and redirect to file for downstream analysis.

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Grep
    • Glob
    • Bash(crypto:onchain-*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 4 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • defillama.com
    • coingecko.com
    • dune.com
    • thegraph.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Designed for Claude Code

    From compatibility in the SKILL.md frontmatter.

Context cost

Analyzing On Chain Data loads about 1.5k tokens when it runs, and up to ~3.2k if it reads all its reference files. Until then it costs about 60 tokens; SKILL.md has 633 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 633 words, ~1,459 tokens.

Download SKILL.mdSave it as .claude/skills/analyzing-on-chain-data/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
analyzing-on-chain-data
description
Process perform on-chain analysis including whale tracking, token flows, and network activity. Use when performing crypto analysis. Trigger with phrases like "analyze crypto", "check blockchain", or "monitor market".
allowed-tools
Read, Write, Edit, Grep, Glob, Bash(crypto:onchain-*)
compatibility
Designed for Claude Code
version
1.28.0
author
Jeremy Longshore <jeremy@intentsolutions.io>
license
MIT
tags
crypto, monitoring, analyzing-on

Analyzing On-Chain Data

Overview

Analyze DeFi protocol metrics, chain-level TVL, fee revenue, DEX volumes, yield opportunities, and stablecoin market caps using DeFiLlama as the primary data source. Designed for DeFi researchers, protocol analysts, and yield farmers who need programmatic access to on-chain analytics without writing custom subgraph queries.

Prerequisites

  • Python 3.8+ with requests library installed
  • DeFiLlama API access (free, no key required for most endpoints)
  • Optional: CoinGecko API key for supplementary token price data
  • onchain_analytics.py CLI script available in the plugin directory
  • data_fetcher.py and metrics_calculator.py modules for programmatic usage

Instructions

  1. Run python onchain_analytics.py protocols to retrieve the top DeFi protocols ranked by total value locked (TVL).
  2. Filter protocol results by category using --category lending, --category dex, or --category "liquid staking" to narrow the scope.
  3. Filter by chain with --chain ethereum or --chain arbitrum to isolate chain-specific protocol data.
  4. Sort results by alternative metrics using --sort market_share or --sort tvl_to_mcap to surface undervalued protocols.
  5. Run python onchain_analytics.py chains to retrieve chain-level TVL rankings across all tracked networks.
  6. Run python onchain_analytics.py fees --protocol aave to pull fee and revenue data for a specific protocol.
  7. Run python onchain_analytics.py dex --chain ethereum to analyze DEX trading volumes filtered by chain.
  8. Run python onchain_analytics.py yields --min-tvl 5000000 --chain ethereum to identify yield opportunities above a minimum TVL threshold.
  9. Run python onchain_analytics.py trends --threshold 5 to detect protocols with significant TVL changes (threshold is percentage).
  10. Export results in JSON or CSV format using --format json or --format csv and redirect to file for downstream analysis.

See ${CLAUDE_SKILL_DIR}/references/implementation.md for the full four-step implementation workflow.

Output

  • Protocol rankings table with name, TVL, market share percentage, and TVL-to-market-cap ratio
  • Chain TVL rankings showing aggregate locked value per network
  • Fee and revenue reports per protocol with daily/weekly/monthly breakdowns
  • DEX volume tables with per-chain and per-DEX breakdowns
  • Yield opportunity listings filtered by minimum TVL and chain, including APY and pool details
  • Trending protocol alerts showing TVL percentage changes above the configured threshold
  • Stablecoin market cap summaries
  • JSON (output.json) or CSV (output.csv) export files for programmatic consumption
Show full SKILL.md (288 more words)Show less

Error Handling

ErrorCauseSolution
Request timeoutDeFiLlama API slow or unreachableWait and retry; check for outages; use cached data if available
Protocol not found: invalid-nameProtocol slug does not match DeFiLlama databaseRun python onchain_analytics.py protocols to find the exact slug; slugs are case-sensitive
No data returned for queryFilter too restrictive or data unavailableRemove filters and retry; verify the category or chain exists; try a broader time range
TVL data unavailable for some protocolsNew protocols or data collection gapsCheck DeFiLlama directly; data typically appears within 24 hours of listing
Data may be stale (last updated: X hours ago)Local cache not refreshedClear cache with rm ~/.onchain_analytics_cache.json; use --verbose to check cache status
Showing top 50 of 1000+ protocolsOutput truncated for readabilityUse --limit to increase count or --format json for full untruncated data
UnicodeEncodeErrorTerminal encoding mismatchUse --format json for safe output or set LANG=en_US.UTF-8

Examples

Daily DeFi Overview
bash
python onchain_analytics.py protocols --limit 20
python onchain_analytics.py chains
python onchain_analytics.py trends

Produces a snapshot of the top 20 protocols by TVL, all chain rankings, and any protocols trending above the default threshold.

Research a Lending Protocol
bash
python onchain_analytics.py protocols --category lending --sort tvl_to_mcap
python onchain_analytics.py fees --protocol aave

Ranks all lending protocols by TVL-to-market-cap ratio (identifying potentially undervalued protocols), then pulls detailed fee and revenue data for Aave.

Find High-TVL Yield Opportunities on Ethereum
bash
python onchain_analytics.py yields --min-tvl 10000000 --chain ethereum --limit 50  # 10000000 = 10M limit

Returns up to 50 yield pools on Ethereum with at least $10M in TVL, sorted by APY. Export with --format csv > yields.csv for spreadsheet analysis.

Resources

  • DeFiLlama API Documentation -- primary data source for TVL, fees, yields, and DEX volumes
  • DeFiLlama Status Page -- check API availability and outage reports
  • CoinGecko API -- supplementary token price and market cap data
  • Dune Analytics -- custom SQL queries against on-chain data for deeper analysis
  • The Graph -- decentralized indexing protocol for querying blockchain data via GraphQL

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 10 other files (scripts, references) in skills/.curated/analyzing-on-chain-data of jeremylongshore/tons-of-skills-marketplace.

  • SKILL.md
  • ARD.md
  • PRD.md
  • config/settings.yaml
  • references/errors.md
  • references/examples.md
  • references/implementation.md
  • scripts/data_fetcher.py
  • scripts/formatters.py
  • scripts/metrics_calculator.py
  • scripts/onchain_analytics.py

Open the folder on GitHubat commit cfae287

Compare with similar skills

Analyzing On Chain Data next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Analyzing On Chain Data compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Analyzing On Chain Data this skilljeremylongshore/tons-of-skills-marketplace2.8k—~1.5kAutomated safety check: PassMIT
Aomi Transactsickn33/agentic-awesome-skills47k1 repos~2.3kAutomated safety check: PassMIT
Blockchain Developeraiskillstore/marketplace4337 repos~2.5kAutomated safety check: PassNone
SurfBlockRunAI/ClawRouter6.6k—~4kAutomated safety check: PassMIT
Digital AssetsJoelLewis/finance_skills206—~2.2kAutomated safety check: PassMIT
Ethskillsaustintgriffith/ethskills295—~1.4kAutomated safety check: PassNone

Similar skills

  • Aomi Transact

    sickn33/agentic-awesome-skills

    Build natural-language crypto/DeFi agents and EVM MCP plugins (Claude Code, Cursor, Codex, Gemini).

    47k GitHub starsUsed in 1 repo~2.3k tokens
    Business, Finance & HRAuto-check passed
  • Blockchain Developer

    aiskillstore/marketplace

    Build production-ready Web3 applications, smart contracts, and decentralized systems.

    433 GitHub starsUsed in 7 repos~2.5k tokens
    Business, Finance & HRAuto-check passed
  • Surf

    BlockRunAI/ClawRouter

    Use this skill — NOT browser or webfetch — for ALL Surf crypto-data calls.

    6.6k GitHub stars~4k tokensUpdated 5 days ago
    Business, Finance & HRAuto-check passed
  • Digital Assets

    JoelLewis/finance_skills

    Analyze digital assets including cryptocurrency fundamentals, blockchain mechanics, DeFi protocols, and on-chain metrics.

    206 GitHub stars~2.2k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed
  • Ethskills

    austintgriffith/ethskills

    Ethereum development knowledge for AI agents — from idea to deployed dApp.

    295 GitHub stars~1.4k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed
  • Erc 8004

    aAAaqwq/AGI-Super-Team

    Register AI agents on Ethereum mainnet using ERC-8004 (Trustless Agents).

    105 GitHub starsUsed in 2 repos~1.2k tokens
    Backend & APIsAuto-check passed

More from jeremylongshore/tons-of-skills-marketplace

All 3,342 skills in this repo
  • Performing Security Code Review

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.

    2.8k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check: notes
  • Adapting Transfer Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Agent Context Loader

    jeremylongshore/tons-of-skills-marketplace

    Execute proactive auto-loading: automatically detects and loads agents.md files.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Aggregating Performance Metrics

    jeremylongshore/tons-of-skills-marketplace

    Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Analyzing Capacity Planning

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.

    2.8k GitHub stars~947 tokensUpdated today
    Auto-check passed
  • Analyzing Database Indexes

    jeremylongshore/tons-of-skills-marketplace

    Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~2k tokensUpdated today
    Auto-check passed

Works with

Questions about Analyzing On Chain Data

What does Analyzing On Chain Data do?

Process perform on-chain analysis including whale tracking, token flows, and network activity. Analyzing On Chain Data is an agent skill from jeremylongshore/tons-of-skills-marketplace. Process perform on-chain analysis including whale tracking, token flows, and network activity.

When should I use Analyzing On Chain Data?

Analyzing On Chain Data fits situations like: performing crypto analysis; with phrases like analyze crypto; check blockchain.

How do I install Analyzing On Chain Data in Claude Code?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill analyzing-on-chain-data -a claude-code`. Or copy the skill folder (skills/.curated/analyzing-on-chain-data in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/analyzing-on-chain-data in your project. Claude Code loads it when a task matches its description.

How do I install Analyzing On Chain Data in Codex?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill analyzing-on-chain-data -a codex`. Or copy the skill folder (skills/.curated/analyzing-on-chain-data in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/analyzing-on-chain-data in your project. Codex loads it when a task matches its description.

Can I use Analyzing On Chain Data in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill analyzing-on-chain-data -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/analyzing-on-chain-data, .gemini/skills/analyzing-on-chain-data, .github/skills/analyzing-on-chain-data and .opencode/skills/analyzing-on-chain-data in your project.

What does Analyzing On Chain Data need to run?

Going by SKILL.md and its folder, Analyzing On Chain Data needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Write, Edit, Grep, Glob, Bash(crypto:onchain-*). Compatibility (from SKILL.md): Designed for Claude Code.

Does Analyzing On Chain Data access the network?

SKILL.md names 4 domains. As links in the text: defillama.com, coingecko.com, dune.com and thegraph.com. This is read from the text; nothing was executed.

Is Analyzing On Chain Data safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Analyzing On Chain Data use?

Analyzing On Chain Data is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Analyzing On Chain Data use?

About 1.5k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.7k tokens, read only when the agent opens those files.

What are the alternatives to Analyzing On Chain Data?

Skills that share tags, products or a category with Analyzing On Chain Data: Aomi Transact (sickn33/agentic-awesome-skills, 47k stars), Blockchain Developer (aiskillstore/marketplace, 433 stars), Surf (BlockRunAI/ClawRouter, 6.6k stars) and Digital Assets (JoelLewis/finance_skills, 206 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Analyzing On Chain Data?

jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.

Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.