← Back to Skills Marketplace
Openclaw Skill
by
vlprosvirkin
· GitHub ↗
· v2.0.5
294
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install probtrade
Description
Polymarket prediction markets: analytics, trading, hot markets, price movements, top traders, and market search. Powered by prob.trade.
Usage Guidance
This skill appears coherent and implements local HMAC signing of requests to api.prob.trade. Before installing: 1) Confirm you trust the prob.trade service and the skill source (homepage and ClawHub links). 2) Store API keys only in the indicated config file or environment variables and avoid placing highly privileged credentials there; use account-level key controls (scopes/limits) if available. 3) Review the included files (lib/api_client.py and scripts/probtrade.py) yourself if you want extra assurance—they are small and readable. 4) If keys are ever exposed or you stop using the skill, revoke them from the prob.trade dashboard. If you require stronger isolation, run the skill in a sandboxed environment or separate account.
Capability Analysis
Type: OpenClaw Skill
Name: probtrade
Version: 2.0.5
The probtrade skill bundle is a legitimate tool for Polymarket prediction market analytics and trading via the prob.trade API. The code (scripts/probtrade.py and lib/api_client.py) uses Python's standard library to perform authenticated HMAC-SHA256 requests to a specific, documented endpoint (api.prob.trade) and correctly handles API keys from environment variables or a local configuration file. No evidence of data exfiltration, malicious execution, or prompt injection was found.
Capability Assessment
Purpose & Capability
Name/description (prob.trade analytics & trading) align with required binaries (python3), required env vars (PROBTRADE_API_KEY, PROBTRADE_API_SECRET), and the provided scripts. Requested files and config path (~/.openclaw/skills/probtrade/config.yaml) are appropriate for storing API credentials.
Instruction Scope
SKILL.md instructs only running the included Python scripts and placing API keys in the declared config file. The included code performs only HTTP calls to api.prob.trade and local config/env reading; it does not attempt to read unrelated system paths or transmit data to unexpected endpoints.
Install Mechanism
Install spec is a brew formula for python@3 to provide python3. No downloads from untrusted hosts, no archive extraction, and the code uses only the Python standard library (urllib, hmac, hashlib).
Credentials
The skill requires exactly two credentials (PROBTRADE_API_KEY and PROBTRADE_API_SECRET) which are reasonable and necessary for trading. The code checks those env vars and a single config path; no unrelated secrets or additional service credentials are requested.
Persistence & Privilege
always is false and the skill does not request persistent platform-wide privileges or modify other skills. Its behavior is limited to running the included scripts when invoked.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install probtrade - After installation, invoke the skill by name or use
/probtrade - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.5
Fix HMAC signature body format, add post_public() for analyze command
Metadata
Frequently Asked Questions
What is Openclaw Skill?
Polymarket prediction markets: analytics, trading, hot markets, price movements, top traders, and market search. Powered by prob.trade. It is an AI Agent Skill for Claude Code / OpenClaw, with 294 downloads so far.
How do I install Openclaw Skill?
Run "/install probtrade" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Openclaw Skill free?
Yes, Openclaw Skill is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Openclaw Skill support?
Openclaw Skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Openclaw Skill?
It is built and maintained by vlprosvirkin (@vlprosvirkin); the current version is v2.0.5.
More Skills