Communitygithub.com

majiayu000/claude-skill-registry-data

Analyze EVM wallet asset distribution and identify high-risk protocol exposure.

Was ist claude-skill-registry-data?

claude-skill-registry-data is a Claude Code agent skill that analyze EVM wallet asset distribution and identify high-risk protocol exposure.

Funktioniert mit✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/majiayu000/claude-skill-registry-data/tree/HEAD/analysis/pubfi-wallet-portfolio-analysis

In Ihrer bevorzugten KI fragen

Öffnet einen neuen Chat, in dem dieser Agent-Skill bereits geladen ist.

Dokumentation

Wallet Portfolio Analysis

Goal: Provide concise asset distribution analysis and risk assessment for EVM wallets.

Inputs

  • wallet_address (required): EVM address (0x...)

Data Source

Primary: Zerion API via zerion-portfolio.py

# Get all assets
python3 zerion-portfolio.py <address>

# Get only DeFi positions
python3 zerion-portfolio.py <address> --only-defi

Environment: ZERION_API_KEY must be set. If not set, get your API key at: https://www.zerion.io/api

Execution Workflow

Step 1: Validate Input

1. Check address format: 0x + 40 hex characters
2. If invalid format: Exit with error message

Step 2: Fetch Portfolio Data

# Execute Zerion portfolio script
python3 skills/pubfi-wallet-portfolio-analysis/zerion-portfolio.py <address>

Handle Edge Cases:

  • Empty wallet → Report "Empty wallet"
  • API failure → Exit with error, cannot proceed
  • Zero-value positions → Skip

Step 3: Categorize Assets

Group by type:
  Native: ETH, MATIC, BNB, etc.
  Stablecoins: USDC, USDT, DAI, USDS
  DeFi Positions: Has protocol attribute + position_type != 'wallet'
  Other Tokens: Everything else

Track total value per category for distribution percentages

Step 4: Identify DeFi Protocols

For each DeFi position:
  1. Extract protocol name from attributes.protocol
  2. Identify position type (Lending/Staking/LP/etc.)
  3. Record position value and percentage of portfolio
  4. Create list of unique protocols for risk assessment

Step 5: Risk Assessment (DeFi Protocols Only)

For each identified protocol:
  
  A. Fetch Protocol Data (parallel):
     - DefiLlama API: curl "https://api.llama.fi/protocol/{slug}"
     - Extract TVL, chains, audit info, category
  
  B. Check Recent Exploits:
     - Search rekt.news for protocol name
     - Filter last 90 days
     - Record any incidents
  
  C. Calculate Risk Score:
     Risk = Base + Events + Audit + TVL Trend
     
     Factors:
     - No audit: +5
     - Recent exploit (90 days): +5
     - TVL drop >50% (30 days): +3
     - TVL drop 20-50%: +2
     - New protocol (<6 months): +2
     - Single audit: +1
     - Multiple audits: -2
     - Battle-tested (>1 year): -1
  
  D. Assign Risk Level:
     - Score > 7: 🔴 High Risk
     - Score 4-7: 🟡 Medium Risk
     - Score < 4: 🟢 Low Risk
  
  E. Error Handling:
     - DefiLlama fails: Mark TVL as "N/A", continue
     - Rekt.news unavailable: Mark exploits as "Unknown"

Known Safe Protocols (auto 🟢):
  - Aave V2/V3, Uniswap V2/V3, Compound V2/V3
  - Lido, Curve, MakerDAO/Sky

Step 6: Generate Report

Output structured markdown report following the Output Format section below.


Output Format

1) Summary

Portfolio: 0x...
Total Value: $X,XXX USD
Chains: Ethereum, Arbitrum, Base

2) Asset Distribution

Asset Breakdown:
• Native: $XXX (XX%)
• Stablecoins: $XXX (XX%)
• DeFi Positions: $XXX (XX%)
• Other Tokens: $XXX (XX%)

3) Top Positions

Table format showing all positions sorted by value:

Protocol/Wallet | Position Type | Value | % Portfolio
----------------|---------------|-------|------------
Wallet Assets   | Wallet        | $XXX  | XX%
Protocol A      | Lending       | $XXX  | XX%
Protocol B      | LP            | $XXX  | XX%

4) Top Holdings (>2% of portfolio)

Table format:

Chain | Asset | Type | Amount | Value | % Portfolio
------|-------|------|--------|-------|------------

5) DeFi Exposure

For each protocol with 🟡 Medium or 🔴 High risk only (skip 🟢 Low risk):

Protocol Name (Chain)
• Position Value: $XXX (XX% of portfolio)
• Position Type: Lending/Staking/LP/etc.
• Risk: 🟡/🔴
• TVL: $XXX (DefiLlama)
• Audit: Yes/No (auditor names)
• Recent Issues: None / [describe]

If all protocols are low risk, output: "All DeFi positions are in low-risk protocols (🟢)"

6) Risk Summary

High Priority:

  • List any 🔴 high-risk positions with recommended actions

Medium Priority:

  • List any 🟡 medium-risk positions with considerations

Overall Assessment:

  • One paragraph summary
  • Risk score: Low/Medium/High

7) Data Sources

  • Zerion API: Portfolio data (timestamp)
  • DefiLlama: Protocol TVL and info
  • Rekt.news: Security incidents
  • [Other sources used]

Quality Standards

Conciseness:

  • Total report: 200-400 words (excluding tables)
  • Focus on actionable insights only
  • No filler or generic statements

Accuracy:

  • All data must have timestamps
  • All values must come from real API calls
  • Risk assessments must cite specific evidence

Usefulness:

  • Highlight positions >5% of portfolio
  • Flag any high-risk exposure immediately
  • Provide clear next actions if needed

Update Frequency

  • Risk database: Update monthly with rekt.news
  • Known protocols: Update as new major protocols launch
  • Audit status: Verify quarterly

Last updated: 2026-02-05

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

majiayu000/claude-skill-registry-data

Edit existing BMAD agents while maintaining compliance

majiayu000/claude-skill-registry-data

Edit existing BMAD agents while maintaining compliance

majiayu000/claude-skill-registry-data

Edit existing BMAD modules while maintaining coherence

majiayu000/claude-skill-registry-data

Edit existing BMAD modules while maintaining coherence

majiayu000/claude-skill-registry-data

Analyzes current state and user query to answer BMad questions or recommend the next workflow or agent. Use when user says what should I do next, what do I do now, or asks a question about BMad

majiayu000/claude-skill-registry-data

Build AI agents with Google ADK Python (Agent Development Kit). Use for multi-agent systems, workflow agents (sequential/parallel/loop), Vertex AI deployment, tool integration, human-in-the-loop.

majiayu000/claude-skill-registry-data

Build AI agents with Google ADK Python (Agent Development Kit). Use for multi-agent systems, workflow agents (sequential/parallel/loop), Vertex AI deployment, tool integration, human-in-the-loop.

majiayu000/claude-skill-registry-data

Portfolio allocation and rebalancing optimizer. Manages asset allocation across stocks/cash/bonds, performs periodic rebalancing, and ensures diversification according to market regime and risk tolerance.

majiayu000/claude-skill-registry-data

Create a hilarious and ultra-realistic video of an anthropomorphic animal acting like a human vlogger in a real-world setting.

majiayu000/claude-skill-registry-data

Speech-to-text transcription and translation via OpenAI Audio API -- models, response formats, timestamps, prompting, streaming, chunking, and diarization

majiayu000/claude-skill-registry-data

This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.

majiayu000/claude-skill-registry-data

小省导购员数字人带货版即梦视频提示词生成系统,基于四大智能体协同(提示词生成师、质量管控师、知识库运维师、跨环节适配师),按照"主体+运动+场景+(镜头语言+光影+氛围)"公式输出中英文双版提示词,适配5s短视频。确保人物一致性、视觉连贯性、情绪连贯性,支持知识库智能复用和跨工具适配(Suno音乐、AI绘画),为数字人带货视频提供高质量提示词生成服务。

majiayu000/claude-skill-registry-data

Upload and manage files using Google Gemini File API via scripts/. Use for uploading images, audio, video, PDFs, and other files for use with Gemini models. Supports file upload, status checking, and file management. Triggers on "upload file", "file API", "upload image", "upload PDF", "upload video", "file management".

majiayu000/claude-skill-registry-data

Analyze images/audio/video with Gemini API (better vision than Claude). Generate images (Imagen 4), videos (Veo 3). Use for vision analysis, transcription, OCR, design extraction, multimodal AI.

majiayu000/claude-skill-registry-data

Analyze images/audio/video with Gemini API (better vision than Claude). Generate images (Imagen 4), videos (Veo 3). Use for vision analysis, transcription, OCR, design extraction, multimodal AI.

majiayu000/claude-skill-registry-data

Skill for discovering and researching autonomous AI agents, tools, and ecosystems using the AgentFolio directory.

majiayu000/claude-skill-registry-data

Conduct domain and industry research. Use when the user says "lets create a research report on [domain or industry]

majiayu000/claude-skill-registry-data

Conduct market research on competition and customers. Use when the user says "create a market research report about [business idea]".

majiayu000/claude-skill-registry-data

Conduct technical research on technologies and architecture. Use when the user says "create a technical research report on [topic]".

majiayu000/claude-skill-registry-data

Builds, edit or validate Agent Skill through conversational discovery. Use when the user requests to "Create an Agent", "Optimize an Agent" or "Edit an Agent".

Verwandte Skills