← Back to Skills Marketplace
Portfolio Copilot
by
Sergey Vidyuk
· GitHub ↗
· v1.0.0
· MIT-0
95
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install paradex-portfolio-copilot
Description
Conversational portfolio briefings for Paradex accounts and vaults. Unifies account summary, positions, fills, balances, market data, and funding into natura...
Usage Guidance
This skill appears internally consistent and low-risk: it only formats and presents Paradex account and market data. Before installing, confirm two things with your platform/operator: (1) the MCP tools referenced are read-only (they should only return account/market data and not execute trades or expose unrelated credentials), and (2) any credentials the platform supplies to those MCP tools are scoped minimally (read-only, limited to the specific Paradex account). If you want extra caution, test the skill with a non-production or demo Paradex account so you can confirm the outputs and that no unexpected actions occur.
Capability Analysis
Type: OpenClaw Skill
Name: paradex-portfolio-copilot
Version: 1.0.0
The paradex-portfolio-copilot skill is a legitimate conversational interface designed to summarize Paradex trading account data. It provides structured instructions (SKILL.md) and formatting templates (briefing-formats.md) for the AI agent to process data from specific MCP tools like paradex_vault_positions and paradex_vault_balance. There is no evidence of data exfiltration, malicious execution, or harmful prompt injection.
Capability Assessment
Purpose & Capability
Name/description request portfolio summaries and the SKILL.md only refers to Paradex-specific MCP tools (account_summary, positions, balances, market_summaries, funding, transfers). There are no unrelated environment variables, binaries, or install steps requested — the requested capabilities match the stated purpose.
Instruction Scope
All runtime instructions are limited to reading Paradex portfolio and market data and formatting briefings. The SKILL.md does not instruct reading local files, environment secrets, or contacting external endpoints outside of the listed MCP tools. Recommendation: confirm that the referenced MCP tools are read-only and do not themselves have side effects (e.g., placing orders) or return unrelated account data.
Install Mechanism
No install spec and no code files — instruction-only skill. Nothing is downloaded or written to disk, which minimizes installation risk.
Credentials
The skill declares no required environment variables, secrets, or config paths. This is proportionate for a read-only briefing skill. Verify on your platform whether access to the MCP tools requires separate credentials and that those credentials are scoped appropriately.
Persistence & Privilege
always is false and model invocation is allowed (normal). The skill does not request permanent presence or claim to modify other skills or system settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install paradex-portfolio-copilot - After installation, invoke the skill by name or use
/paradex-portfolio-copilot - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release
Metadata
Frequently Asked Questions
What is Portfolio Copilot?
Conversational portfolio briefings for Paradex accounts and vaults. Unifies account summary, positions, fills, balances, market data, and funding into natura... It is an AI Agent Skill for Claude Code / OpenClaw, with 95 downloads so far.
How do I install Portfolio Copilot?
Run "/install paradex-portfolio-copilot" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Portfolio Copilot free?
Yes, Portfolio Copilot is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Portfolio Copilot support?
Portfolio Copilot is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Portfolio Copilot?
It is built and maintained by Sergey Vidyuk (@sv); the current version is v1.0.0.
More Skills