← Back to Skills Marketplace
362
Downloads
1
Stars
0
Active Installs
5
Versions
Install in OpenClaw
/install whitebit
Description
Build, install, update, and use a WhiteBIT trading guidance and training skill through ClawHub (clawhub.ai) for OpenClaw. Use when asked to manage WhiteBIT t...
Usage Guidance
This skill appears coherent and documentation-first. Before installing: ensure the 'clawhub' CLI is installed and you are comfortable using ClawHub for skill lifecycle actions; confirm you have the 'whitebit-docs' MCP connector available if you want accurate API validation; never publish or upload API keys or .env files to ClawHub; treat this skill as training/documentation-only — do not expect it to place live trades unless you separately configure and audit an execution connector that holds your API credentials; note the packaged agent config allows implicit invocation, so review agent invocation policies if you want to restrict autonomous use.
Capability Analysis
Type: OpenClaw Skill
Name: whitebit
Version: 1.0.4
The skill bundle is designed as a training and planning tool for WhiteBIT trading, utilizing the whitebit-docs MCP server (docs.whitebit.com) for API validation. The instructions in SKILL.md and README.md emphasize safety, explicitly prohibiting the agent from executing live trades, handling private API keys, or exceeding simulated bankroll limits. The inclusion of clawhub CLI commands for skill management is consistent with the stated purpose of managing OpenClaw skills via the ClawHub platform, and no indicators of data exfiltration, malicious execution, or obfuscation were found.
Capability Assessment
Purpose & Capability
Name/description (WhiteBIT trading guidance & training) match the runtime instructions and file contents. The only declared runtime dependency is the 'clawhub' CLI, which is appropriate for a skill that manages/publishes itself through ClawHub. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md confines the agent to documentation lookup (whitebit-docs MCP) and training/execution-prep workflows; it explicitly forbids live execution unless a separate execution connector is configured. It does not instruct reading arbitrary system files or exfiltrating secrets. The guidance to check for MCP connectors and to require explicit user confirmation for live trades is consistent with the stated training-only intent.
Install Mechanism
This is an instruction-only skill with no install spec or code to download — lowest-risk install posture. The README and references only recommend using the user-installed 'clawhub' CLI or cloning the repo locally; no remote code fetches or extract operations are present.
Credentials
No required environment variables or credentials are declared. The skill repeatedly states it does not require runtime WhiteBIT API keys and directs keys to be stored in a separate executor if used. Required MCP connector (whitebit-docs) and clawhub CLI are proportionate to the purpose.
Persistence & Privilege
The skill is not always-included (always: false). The included agents/openai.yaml sets allow_implicit_invocation: true which permits implicit invocation behavior at the agent-config level; autonomous invocation is the platform default and is not in itself a problem, but users should be aware implicit invocation is allowed by this skill's packaged agent config.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install whitebit - After installation, invoke the skill by name or use
/whitebit - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.4
- Added explicit support for training and educational workflows alongside execution planning.
- Clarified the skill uses documentation-only access for WhiteBIT; no live trading or real account checks possible.
- Introduced a new "Training Scope" section detailing use cases such as walkthroughs, exercises, and terminology explanations.
- Updated the workflow steps and output format to distinguish between training and execution-prep scenarios.
- Enhanced guardrails to prohibit presenting training outputs as real trade results.
v1.0.3
- Skill now focuses exclusively on WhiteBIT API documentation lookup and execution planning, not live trading.
- Execution capability, API key handling, and runtime account validation steps removed; only `whitebit-docs` MCP connector is required.
- Updated workflow: prepares API call plans, validates parameters, explains order process, but does not send or verify live trades.
- Clear messaging added: if live execution or trading behavior is requested, the skill stops and explains its doc-only mode.
- Guardrails tightened to explicitly prevent any claim of trading actions or account effect from this skill version.
v1.0.2
**Improved MCP connector requirements and stricter risk controls for WhiteBIT trading automation.**
- Added detailed MCP connector checks: requires both `whitebit-docs` (for documentation) and `whitebit-trading` (for execution).
- Implemented mandatory capability verification (`balances`, `place_order`, `order_status`) before executing trades.
- Clarified that trading is not permitted if `whitebit-trading` or any required capability is missing.
- Refined workflow and guardrails: spot `SELL` orders now block if holdings are insufficient, unless margin/shorting is explicitly supported.
- Updated risk control: deployable capital limited to `100 USDT` plus realized profit—unrealized P&L excluded.
- Added README.md for improved documentation.
v1.0.1
- Added a metadata section specifying required environment variables, binaries, and ClawHub/OpenClaw integration info.
- Declared environment variables WHITEBIT_API_KEY and WHITEBIT_API_SECRET as required for skill operation.
- Set metadata fields for primary environment variable, skill key, and homepage.
- Updated ClawHub install/update command examples to use the literal "whitebit" skill key for clarity.
- No functional or workflow changes; documentation improvements only.
v1.0.0
Initial release of the ClawHub WhiteBIT Trading skill.
- Enables building, installing, updating, and running WhiteBIT trading automation via ClawHub for OpenClaw environments.
- Enforces MCP-first validation for all trade executions and risk checks before order placement.
- Implements a structured workflow for verifying environment setup, gathering trade intent, parameter validation, safety checks, and detailed execution reporting.
- Integrates strong guardrails to prevent unconfirmed orders, exposure of sensitive data, and unsafe trading actions.
- Provides a consistent, concise response format for all skill actions and results.
- Includes references and checklists for setup, risk control, and API usage.
Metadata
Frequently Asked Questions
What is whitebit?
Build, install, update, and use a WhiteBIT trading guidance and training skill through ClawHub (clawhub.ai) for OpenClaw. Use when asked to manage WhiteBIT t... It is an AI Agent Skill for Claude Code / OpenClaw, with 362 downloads so far.
How do I install whitebit?
Run "/install whitebit" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is whitebit free?
Yes, whitebit is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does whitebit support?
whitebit is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created whitebit?
It is built and maintained by Alex M (@zonder); the current version is v1.0.4.
More Skills