CAT
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Protocol Deep Dive

defillama/defillama-skills
132 installs13 stars
Summary

This runs a complete protocol analysis by chaining seven DefiLlama API calls into one structured report: TVL and fee metrics, top yield pools, hack and fundraising history, income statement breakdown, user activity trends, and token price data. You'd use it when someone asks to "tell me everything about Uniswap" instead of running individual queries. The workflow is well documented with specific field names and output sections, which is helpful since you'll want to customize the format. The main caveat is that some protocols won't have data for all seven endpoints, so you'll get partial reports. It's basically a research template that saves you from manually orchestrating the same API sequence for every deep dive.

Install to Claude Code

npx -y skills add defillama/defillama-skills --skill protocol-deep-dive --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Files
SKILL.mdView on GitHub

Protocol Deep Dive

Perform a thorough analysis of a single DeFi protocol by combining multiple data sources into one structured report.

Workflow

Step 1 - Resolve the protocol entity

If the protocol slug is unknown or ambiguous, resolve it first.

defillama:resolve_entity
  entity_type: "protocol"
  name: "<user-provided name>"

Step 2 - Core protocol metrics

Fetch TVL, fees, revenue, market cap, ratios, and trend data.

defillama:get_protocol_metrics
  protocol: "<slug>"

Key fields to surface: tvl_base, fees_1d, revenue_1d, mcap, ps_ratio, pf_ratio, tvl_base_7d_pct_change, tvl_base_30d_pct_change.

Step 3 - Top yield pools

Retrieve the protocol's highest-TVL pools to show yield opportunities.

defillama:get_yield_pools
  protocol: "<slug>"

Highlight pools with the highest TVL and APY. Note any pools where the base APY is very low and rewards dominate (sustainability signal).

Step 4 - Recent events

Check for hacks, fundraises, or other notable events.

defillama:get_events
  protocol: "<slug>"
  event_type: "hacks"

Also check for fundraising activity:

defillama:get_events
  protocol: "<slug>"
  event_type: "raises"

Step 5 - Income statement

Get the revenue breakdown to understand where income comes from.

defillama:get_income_statement
  protocol: "<slug>"

Use the metric param to filter by specific income line items if needed.

Step 6 - User activity

Fetch daily active users and transaction counts.

defillama:get_user_activity
  protocol: "<slug>"

Step 7 - Token price (if applicable)

If the protocol has a native token, fetch current price context.

defillama:get_token_prices
  token: "<coingecko:token_id>"

Output Format

Present the report with these sections in order:

  1. Overview - One-paragraph summary: what the protocol does, which chain(s) it operates on, its category.
  2. Key Metrics - Table of TVL, fees, revenue, mcap, P/S, P/F, and percentage changes (7d, 30d).
  3. Yield Opportunities - Top 3-5 pools by TVL with chain, APY, and TVL.
  4. Revenue Breakdown - Where income comes from (supply-side vs protocol).
  5. User Growth - Active users trend, transaction volume.
  6. Recent Events - Hacks, raises, governance events.
  7. Token Performance - Price, market cap, volume, ATH distance.

Tips

  • If get_income_statement returns no data, skip the Revenue Breakdown section rather than showing empty results.
  • Compare P/S and P/F ratios to category averages when possible.
  • Flag declining TVL + declining users as a bearish signal.
  • Flag growing TVL + growing users + growing revenue as strong fundamentals.
  • Use start_date / end_date for custom date ranges when analyzing specific periods.
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
First SeenJun 3, 2026
View on GitHub

Recommended

caveman

juliusbrussee/caveman

Ultra-compressed communication mode cutting token usage ~75% while preserving technical accuracy.
203.4k
67.8k
grill-me

mattpocock/skills

Relentless interviewing skill that stress-tests plans and designs through systematic questioning.
250.9k
114.5k
improve

shadcn/improve

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for other models/agents to execute.
10
205
systematic-debugging

obra/superpowers

Structured debugging methodology that mandates root cause investigation before attempting any fixes.
124.6k
215.9k
karpathy-guidelines

forrestchang/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.
13.9k
165.4k
find-skills

vercel-labs/skills

Discover and install specialized agent skills from the open ecosystem when users need extended capabilities.
1.8M
21.1k