analyzing-on-chain-data
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".
Best use case
analyzing-on-chain-data is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
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".
Teams using analyzing-on-chain-data 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/analyzing-on-chain-data/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How analyzing-on-chain-data Compares
| Feature / Agent | analyzing-on-chain-data | 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?
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".
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.
SKILL.md Source
# 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
## Error Handling
| Error | Cause | Solution |
|-------|-------|----------|
| `Request timeout` | DeFiLlama API slow or unreachable | Wait and retry; check https://status.llama.fi/ for outages; use cached data if available |
| `Protocol not found: invalid-name` | Protocol slug does not match DeFiLlama database | Run `python onchain_analytics.py protocols` to find the exact slug; slugs are case-sensitive |
| `No data returned for query` | Filter too restrictive or data unavailable | Remove filters and retry; verify the category or chain exists; try a broader time range |
| `TVL data unavailable for some protocols` | New protocols or data collection gaps | Check DeFiLlama directly; data typically appears within 24 hours of listing |
| `Data may be stale (last updated: X hours ago)` | Local cache not refreshed | Clear cache with `rm ~/.onchain_analytics_cache.json`; use `--verbose` to check cache status |
| `Showing top 50 of 1000+ protocols` | Output truncated for readability | Use `--limit` to increase count or `--format json` for full untruncated data |
| `UnicodeEncodeError` | Terminal encoding mismatch | Use `--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](https://defillama.com/docs/api) -- primary data source for TVL, fees, yields, and DEX volumes
- [DeFiLlama Status Page](https://status.llama.fi/) -- check API availability and outage reports
- [CoinGecko API](https://www.coingecko.com/en/api/documentation) -- supplementary token price and market cap data
- [Dune Analytics](https://dune.com/) -- custom SQL queries against on-chain data for deeper analysis
- [The Graph](https://thegraph.com/) -- decentralized indexing protocol for querying blockchain data via GraphQLRelated Skills
College Football Data (CFB)
Before writing queries, consult `references/api-reference.md` for endpoints, conference IDs, team IDs, and data shapes.
College Basketball Data (CBB)
Before writing queries, consult `references/api-reference.md` for endpoints, conference IDs, team IDs, and data shapes.
validating-database-integrity
Process use when you need to ensure database integrity through comprehensive data validation. This skill validates data types, ranges, formats, referential integrity, and business rules. Trigger with phrases like "validate database data", "implement data validation rules", "enforce data integrity constraints", or "validate data formats".
forecasting-time-series-data
This skill enables Claude to forecast future values based on historical time series data. It analyzes time-dependent data to identify trends, seasonality, and other patterns. Use this skill when the user asks to predict future values of a time series, analyze trends in data over time, or requires insights into time-dependent data. Trigger terms include "forecast," "predict," "time series analysis," "future values," and requests involving temporal data.
analyzing-system-throughput
This skill enables Claude to analyze and optimize system throughput. It is triggered when the user requests throughput analysis, performance improvements, or bottleneck identification. The skill uses the `throughput-analyzer` plugin to assess request throughput, data throughput, concurrency limits, queue processing, and resource saturation. Use this skill when the user mentions "analyze throughput", "optimize performance", "identify bottlenecks", or asks about system capacity. It helps determine limiting factors and evaluate scaling strategies.
generating-test-data
This skill enables Claude to generate realistic test data for software development. It uses the test-data-generator plugin to create users, products, orders, and custom schemas for comprehensive testing. Use this skill when you need to populate databases, simulate user behavior, or create fixtures for automated tests. Trigger phrases include "generate test data", "create fake users", "populate database", "generate product data", "create test orders", or "generate data based on schema". This skill is especially useful for populating testing environments or creating sample data for demonstrations.
test-data-builder
Test Data Builder - Auto-activating skill for Test Automation. Triggers on: test data builder, test data builder Part of the Test Automation skill category.
splitting-datasets
Process split datasets into training, validation, and testing sets for ML model development. Use when requesting "split dataset", "train-test split", or "data partitioning". Trigger with relevant phrases based on skill purpose.
analyzing-text-sentiment
This skill enables Claude to analyze the sentiment of text data. It identifies the emotional tone expressed in text, classifying it as positive, negative, or neutral. Use this skill when a user requests sentiment analysis, opinion mining, or emotion detection on any text, such as customer reviews, social media posts, or survey responses. Trigger words include "sentiment analysis", "analyze sentiment", "opinion mining", "emotion detection", and "polarity".
analyzing-security-headers
This skill analyzes HTTP security headers of a given domain to identify potential vulnerabilities and misconfigurations. It provides a detailed report with a grade, score, and recommendations for improvement. Use this skill when the user asks to "analyze security headers", "check HTTP security", "scan for security vulnerabilities", or requests a "security audit" of a website. It will automatically activate when security-related keywords are used in conjunction with domain names or URLs.
scanning-database-security
Process use when you need to work with security and compliance. This skill provides security scanning and vulnerability detection with comprehensive guidance and automation. Trigger with phrases like "scan for vulnerabilities", "implement security controls", or "audit security".
analyzing-query-performance
This skill enables Claude to analyze and optimize database query performance. It activates when the user discusses query performance issues, provides an EXPLAIN plan, or asks for optimization recommendations. The skill leverages the query-performance-analyzer plugin to interpret EXPLAIN plans, identify performance bottlenecks (e.g., slow queries, missing indexes), and suggest specific optimization strategies. It is useful for improving database query execution speed and resource utilization.