← Back to Skills Marketplace
Meme Token Analyzer
by
deanpeng-dotcom
· GitHub ↗
· v2.0.0
· MIT-0
137
Downloads
1
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install meme-token-analyzer
Description
Meme 代币财富基因检测系统。输入任意代币名称（如 PEPE、DOGE、$SHIB），基于实时 Web 情绪数据输出四维分析报告与 🌟钻石手/🌙登月/🗑️纸手/💩屎币 评级。支持主流币自动识别（BTC/ETH/SOL），无数据时不幻觉。触发词：meme 分析、代币评级、财富基因、PEPE分析、meme...
Usage Guidance
This skill relies on external services (Antalpha MCP, llm-proxy, Tavily) and asks you to register an agent but doesn't declare what credentials or keys are needed or how data is handled. Before installing or invoking it: 1) Verify the maintainer and source repo (the SKILL.md references a GitHub repo but 'Source' is unknown); inspect that repo for real code and license. 2) Ask the maintainer: what data is sent to llm-proxy/Tavily and where are those services hosted? Who controls them and how is telemetry logged? 3) Confirm how agent_id is issued, stored, and revoked; never provide private keys or secrets. 4) Prefer running initial tests with non-sensitive queries to observe where traffic goes, and request documented privacy/billing behavior. If you cannot confirm these points, treat the skill as untrusted for sensitive data.
Capability Analysis
Type: OpenClaw Skill
Name: meme-token-analyzer
Version: 2.0.0
The meme-token-analyzer skill is a legitimate tool designed to provide cryptocurrency sentiment analysis using an external Model Context Protocol (MCP) server. It utilizes the Tavily API for web searches and an LLM proxy for data processing. While it requires a registration step to obtain an 'agent_id' for metering and billing (via an external 'antalpha-register' tool), there is no evidence of malicious intent, data exfiltration, or harmful prompt injections in the provided files (SKILL.md, README.md, _meta.json). The logic is consistent with its stated purpose of analyzing 'meme' tokens.
Capability Tags
Capability Assessment
Purpose & Capability
The capability described (real-time web search + LLM analysis for token sentiment/rating) is coherent with the skill's name and description. It legitimately needs web search and LLM access. However, the SKILL.md references an Antalpha MCP server, llm-proxy, and Tavily API as backends yet the skill declares no required credentials or primary credential — creating a gap between claimed infrastructure and declared requirements.
Instruction Scope
The runtime instructions tell the agent to (a) run an external registration step via an 'antalpha-register' tool to obtain an agent_id and (b) call an MCP tool 'meme-analyze' that will use llm-proxy and Tavily search. Those instructions route user queries and any provided context to external services. The SKILL.md does not document what data is sent to these services, whether agent_id is sensitive, or how API keys / billing/telemetry are handled. This gives the skill broad discretion to transmit user input externally without declared safeguards.
Install Mechanism
There is no install spec and no code files — the skill is instruction-only. That minimizes local disk writes and arbitrary-code install risk. However, being instruction-only increases runtime reliance on external tools/services referenced in the doc (antalpha-register, Meme MCP endpoints).
Credentials
The skill declares no required environment variables or credentials, yet runtime operation clearly depends on service access (MCP server, llm-proxy, Tavily). It requires performing an 'antalpha-register' flow to obtain an agent_id (a credential-like value) but does not declare how it's stored or protected. The absence of declared credentials/API keys and lack of clarity about who controls the external endpoints is disproportionate to the simple analysis task.
Persistence & Privilege
The skill does not request always: true and does not declare persistent system modifications. It appears to operate by calling remote services at runtime; that is normal for an API-backed skill. There is no instruction to modify other skills or system-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install meme-token-analyzer - After installation, invoke the skill by name or use
/meme-token-analyzer - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.0
**Major update: Migrated from the original Coze/LangGraph implementation to a new MCP-based architecture with simplified tool integration and improved robustness.**
- Replaced legacy Coze/LangGraph workflow with streamlined MCP Server integration.
- All prior source code, scripts, and config files removed; now utilizes a single external "meme-analyze" MCP tool.
- Updated documentation: SKILL.md and README.md fully rewritten for new API, agent registration, input/output, rating system, and platform requirements.
- Enhanced end-user privacy and transparency: no local code to install, all logic now managed server-side.
- Multi-language triggers and emoji-rich outputs remain supported for natural, Degen-style meme coin analysis.
v1.0.2
- Removed all dependencies and references to internal storage and database modules; the skill now exclusively uses in-memory processing.
- Updated configuration files for streamlined local operation and simplified environment dependency (`COZE_WORKSPACE_PATH` only).
- Added a project-level `pyproject.toml` for improved packaging and dependency management.
- Improved workflow and script organization for easier setup and execution.
- Updated metadata and documentation to clarify the reduced storage/database requirements and highlight the simplified architecture.
v1.0.0
Meme Token Analyzer 1.0.0 – Initial Release
- Introduces an automated, multimodal workflow for meme token sentiment analysis, investment report generation, and prediction image creation.
- Features include real-time web search, AI image generation, data cleaning, and comprehensive multimodal "wealth gene" rating.
- Supports parallel search and image creation, with results combined in a unified analysis report.
- Utilizes a four-tier Wealth Gene Rating System: Diamond Hand, Moonshot, Paper Hand, and Shitcoin.
- Designed for Python SDK use, with mandatory reliance on the provided SDK guide.
Metadata
Frequently Asked Questions
What is Meme Token Analyzer?
Meme 代币财富基因检测系统。输入任意代币名称（如 PEPE、DOGE、$SHIB），基于实时 Web 情绪数据输出四维分析报告与 🌟钻石手/🌙登月/🗑️纸手/💩屎币 评级。支持主流币自动识别（BTC/ETH/SOL），无数据时不幻觉。触发词：meme 分析、代币评级、财富基因、PEPE分析、meme... It is an AI Agent Skill for Claude Code / OpenClaw, with 137 downloads so far.
How do I install Meme Token Analyzer?
Run "/install meme-token-analyzer" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Meme Token Analyzer free?
Yes, Meme Token Analyzer is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Meme Token Analyzer support?
Meme Token Analyzer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Meme Token Analyzer?
It is built and maintained by deanpeng-dotcom (@deanpeng-dotcom); the current version is v2.0.0.
More Skills