← 返回 Skills 市场
0x-wzw

Defi Analyst

作者 0x-wzw · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
152
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install defi-analyst
功能描述
DeFi research and analysis via Tavily MCP, GeckoTerminal API, and DeFiLlama. Use for protocol research, TVL tracking, yield analysis, token discovery, and co...
使用说明 (SKILL.md)

DeFi Analyst Skill

Research DeFi protocols, track yields, analyze TVL trends, and monitor the competitive landscape.

Prerequisites

  • Tavily API key — free at tavily.io
  • mcporter — OpenClaw skill for MCP tool calling
  • curl + jq — for GeckoTerminal/DeFiLlama API calls

Setup Tavily MCP

mcporter config add tavily https://mcp.tavily.com/mcp/?tavilyApiKey=\x3CYOUR_KEY>

Core Operations

Protocol Research (Tavily)

mcporter call tavily.tavily_search query="Aave V3 protocol overview yield lending" max_results=5 search_depth="advanced"

TVL Tracking (DeFiLlama)

# Get protocol TVL
curl -s "https://api.llama.fi/protocol/aave" | jq '{name: .name, tvl: .tvl, change_1d: .change_1d, change_7d: .change_7d}'

# Top DeFi protocols by TVL
curl -s "https://api.llama.fi/tvl" | jq '.[0:10]'

# Lending rates overview
curl -s "https://api.llama.fi/overview/lending" | jq '.categories[0:10]'

Token Price + Volume (GeckoTerminal)

# Pool data for a token
curl -s "https://api.geckoterminal.com/api/v2/networks/eth/tokens/0x.../info" | jq '{name, base_volume, quote_volume, pool_count}'

# Trending pools on a network
curl -s "https://api.geckoterminal.com/api/v2/networks/eth/pools" | jq '.[0:5] | .[].attributes | {pool: .name, volume_24h: .volume_usd.h24s, tvl: .tvl_usd}'

# Specific pool APY
curl -s "https://api.geckoterminal.com/api/v2/networks/bsc/pools/0x..." | jq '.data.attributes | {apy: .apy_7d, tvl: .tvl_usd}'

DEX Aggregator Research

# Compare yields across DEXes
curl -s "https://api.llama.fi/overview/dex?exclude_bridge=true" | jq '.dexes[0:5]'

Analyst Agents

Technical Analyst

On top of classic candlestick patterns, pulls 24h volume delta, liquidity depth ratios, and cross DEX price variance. Output: {direction, confidence, key_levels}.

Sentiment Analyst

Aggregates social sentiment via Tavily ({token} sentiment today) + Moltbook agent network pulse. Output: sentiment score (-1 to +1) with weighted breakdown by source credibility.

Debate Round

Bull Agent → Tavily for bull cases + on-chain growth metrics. Bear Agent → Tavily for risk factors + whale wallet outflows. Synthesized output: {bull_probability, bear_probability, reconciled_direction, confidence}.

Use Cases

Research a Protocol

# 1. TVL + metrics
TVL=$(curl -s "https://api.llama.fi/protocol/your-protocol" | jq '.tvl')
# 2. Recent news via Tavily
mcporter call tavily.tavily_search query="protocol audit exploit update 2026" max_results=5
# 3. Competitor comparison
mcporter call tavily.tavily_search query="protocol vs aave vs compound defi" max_results=3

Track Yield Opportunities

# Get all lending rates
curl -s "https://api.llama.fi/overview/lending" | jq '.categories[0:10]'

DeFi Landscape Analysis

mcporter call tavily.tavily_search query="DeFi trends 2026 yield farming liquid staking real yield" max_results=10 search_depth="advanced"

Rate Limits

  • GeckoTerminal: 30 req/min, no auth needed
  • DeFiLlama: ~60 req/min, public API
  • Tavily: 20 req/min free tier, 1000 req/month free
安全使用建议
Do not assume the README API key is safe to use. Before installing: 1) Verify the skill's source (official repository / author) — the registry lists no homepage and the source is unknown. 2) Treat the Tavily key in README as potentially leaked; obtain your own Tavily API key and do not paste someone else's key into your environment. 3) Confirm how mcporter stores the key (avoid embedding keys in URLs or command history). 4) If you need guarantees about provenance, ask the publisher for the canonical GitHub repo, check commit history and issues, and inspect any network endpoints (mcp.tavily.com) independently. 5) If you don't want your agent to store external API credentials, do not run the mcporter config command and avoid using this skill until provenance and credential handling are clarified.
能力评估
Purpose & Capability
The SKILL.md and README describe a DeFi research skill that uses Tavily (via mcporter), DeFiLlama, and GeckoTerminal — that is coherent. However, the skill metadata declares no required environment variables while the SKILL.md explicitly requires a Tavily API key and mcporter configuration. The README even contains a plaintext-looking Tavily API key. The skill also references other agent skills (mcporter/moltbook/swarm) without declaring those dependencies. These metadata/instruction mismatches are unexplained and concerning.
Instruction Scope
Runtime instructions are limited to mcporter calls and curl/jq calls to public APIs (Tavily MCP, Geckoterminal, DeFiLlama), which are consistent with the stated purpose. The mcporter config step will store a Tavily API key in the mcporter config; the SKILL.md shows that key being included directly in a URL parameter, which can risk exposure in logs/history. The skill does not instruct reading unrelated local files or secrets beyond the Tavily key.
Install Mechanism
There is no install spec (instruction-only), and only a small validate.sh is included. No downloads or archive extraction are present. This is low install risk.
Credentials
Registry metadata lists no required env vars or primary credential, yet SKILL.md and README require/configure a Tavily API key. The README contains a plaintext token-like string (example or real key) which could be a leaked credential or an insecure example; its presence without explanation is a red flag. No other unrelated credentials are requested, which is proportionate, but the mismatch and the embedded key are problematic.
Persistence & Privilege
always:false and default autonomous invocation are set (normal). The skill will instruct adding a mcporter config entry for Tavily (expected for this integration); it does not request system-wide privileges or modify other skills' configs in the provided files.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install defi-analyst
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /defi-analyst 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of DeFi Analyst Skill - Enables DeFi research and analysis using Tavily MCP, GeckoTerminal API, and DeFiLlama. - Supports protocol research, TVL tracking, yield analysis, token discovery, and competitive landscape review. - Includes sample CLI commands for common workflows (TVL, yields, sentiment, analyst agents). - Analyst agents combine technical, social sentiment, and debate-driven insights. - Provides guidance for API setup and usage limits.
元数据
Slug defi-analyst
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Defi Analyst 是什么?

DeFi research and analysis via Tavily MCP, GeckoTerminal API, and DeFiLlama. Use for protocol research, TVL tracking, yield analysis, token discovery, and co... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 152 次。

如何安装 Defi Analyst?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install defi-analyst」即可一键安装,无需额外配置。

Defi Analyst 是免费的吗?

是的,Defi Analyst 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Defi Analyst 支持哪些平台?

Defi Analyst 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Defi Analyst?

由 0x-wzw(@0x-wzw)开发并维护,当前版本 v1.0.0。

💬 留言讨论