← Back to Skills Marketplace
260
Downloads
0
Stars
2
Active Installs
6
Versions
Install in OpenClaw
/install okx-cex-earn
Description
Manages OKX Simple Earn (flexible savings/lending), Flash Earn, On-chain Earn (staking/DeFi), Dual Investment (DCD/双币赢), and AutoEarn (自动赚币) via the okx CLI....
Usage Guidance
This skill drives the OKX CLI to perform real account actions (subscribe/redeem/stake/dual-investment) and references local OKX CLI credentials/config. Before installing or using it: (1) Verify the npm package @okx_ai/okx-trade-cli is the official OKX package (check the publisher on npm and prefer installing the CLI yourself), (2) Be aware this will operate against your live account (the instructions say to use live mode silently) — only allow actions after you explicitly confirm them and avoid giving the agent unattended write permissions, (3) Limit API key permissions (avoid granting Withdraw if not necessary), (4) Note the registry metadata omits the CLI requirement/config-file access the SKILL.md expects — ask the publisher why metadata and instructions disagree, and (5) If you expect scheduled/automatic monitoring, decide whether you want the agent to run recurring tasks and how it should store/handle credentials. If you are unsure about the package provenance or the silent-live-mode directive, do not install or run this skill until you can validate the CLI publisher and clarify the metadata inconsistencies.
Capability Tags
Capability Assessment
Purpose & Capability
The skill claims to manage OKX Earn products and the runtime instructions only use the OKX CLI — that is consistent with its stated purpose. However the registry metadata lists no required binaries/env/config paths while the SKILL.md frontmatter and content require an 'okx' CLI and include an npm install spec (@okx_ai/okx-trade-cli). The metadata vs SKILL.md mismatch is unexplained and could be accidental or misleading.
Instruction Scope
The SKILL.md instructs the agent to run many authenticated CLI commands, check CLI config and auth state (including referencing ~/.okx/config.toml via the CLI), and to set up periodic recurring monitors that run every 4 hours. It also explicitly instructs the agent to 'Always use live mode silently — don't mention it unless there's an error', which reduces transparency to the user. The instructions reference other skills (okx-cex-auth, market, portfolio, etc.) for cross-skill flows. These behaviors extend beyond simple read-only queries and include write operations (purchases, redemptions, transfers), scheduled automation, and use of local credentials — all of which increase risk if misused.
Install Mechanism
There is no bundled code, but SKILL.md frontmatter includes an npm install spec for @okx_ai/[email protected] which will install a global CLI. Installing an npm package from a public registry is a common but non-trivial action (moderate risk). The package scope/name appears plausible but the skill source is unknown and the registry metadata/homepage do not prove the npm package's authenticity. The install action is not part of the top-level registry 'Requirements', which is inconsistent.
Credentials
The skill declares no required environment variables, but the instructions rely on local OKX CLI configuration and API credentials stored by the CLI (e.g., profiles in ~/.okx/config.toml and OAuth session state). The skill also suggests operations requiring powerful API key permissions (e.g., transfers/withdraws) and will route to an auth skill for login. The absence of declared config path/credential requirements in the registry metadata is inconsistent with instructions that explicitly inspect local auth state and perform authenticated writes.
Persistence & Privilege
always:false (good). However the skill instructs agents/operators to set up a recurring 4-hour monitor that can automatically check offers and recommend or even subscribe after confirmation. Because agent autonomous invocation is allowed by default, this scheduling guidance could enable ongoing automated activity if the agent is permitted to run tasks periodically. The skill does not request elevated platform-wide privileges, nor does it claim permanent inclusion.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install okx-cex-earn - After installation, invoke the skill by name or use
/okx-cex-earn - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.3.2
okx-cex-earn v1.3.2
- Updated CLI installation instructions to use OAuth as the default authentication method.
- Improved credential/profile detection logic to handle both API Key and OAuth authentication modes.
- Now requires @okx_ai/okx-trade-cli version 1.3.2 for improved compatibility.
- Authentication and error-handling guidelines updated for new OAuth workflow.
- No functional changes to user commands; security and setup steps clarified.
v1.3.1
Added Flash Earn (闪赚) project browsing support.
- New: `earn flash-earn projects` command to list Flash Earn products by status (upcoming/in-progress).
- Documentation references updated for Flash Earn usage and syntax.
- Expanded intent routing and description to cover Flash Earn (闪赚) use cases.
- Version bump to 1.3.1.
v1.3.0
**Added support for Simple Earn Fixed-term (定期) products and related workflows.**
- Introduced new commands for subscribing to, viewing, and redeeming Simple Earn Fixed-term products.
- Updated intent routing and user prompt examples to include fixed/term deposit concepts (e.g. 定期, fixed earn, term deposit).
- Expanded "Simple Earn" commands: now explicitly distinguishes between flexible (活期) and fixed (定期) products, with separate commands for each.
- Adjusted display logic for earn positions: queries and presents both flexible and fixed-term orders.
- Updated documentation and templates to reflect new commands and required user confirmation flows.
v1.2.8
okx-cex-earn 1.2.8
- Updated skill metadata version to 1.2.8.
- Added preflight step: reference and require `../_shared/preflight.md` before any command.
- Instructed to use the YAML `metadata.version` as the version source for preflight checks.
- No changes to command logic or features.
v1.2.7
AutoEarn (自动赚币) and USDG earn support added.
- Added AutoEarn (自动赚币) support: enable, disable, query status for supported currencies.
- Updated description and skill routing to include AutoEarn/自动赚币/auto lend/auto staking/USDG 赚币 and related intents.
- New section in Command Index documenting all AutoEarn CLI commands with 24h disable restriction note.
- Operation flow updated for AutoEarn enable/disable and confirmation templates.
- Added a new reference file: references/autoearn-commands.md.
v1.2.6
- Expanded description and detailed usage for managing OKX Simple Earn, On-chain Earn, and Dual Investment via the okx CLI.
- Added comprehensive credential and profile check instructions, including error handling and guidance for setup and authentication issues.
- Introduced clear routing rules for overlapping queries among OKX-related skills.
- Consolidated and clarified operational flows for reading positions, subscribing, redeeming, and confirming write operations.
- Enhanced security and user guidance notes; explicitly warns against sharing API credentials.
- Improved multilingual and markdown output instructions for consistent presentation.
Metadata
Frequently Asked Questions
What is okx-cex-earn?
Manages OKX Simple Earn (flexible savings/lending), Flash Earn, On-chain Earn (staking/DeFi), Dual Investment (DCD/双币赢), and AutoEarn (自动赚币) via the okx CLI.... It is an AI Agent Skill for Claude Code / OpenClaw, with 260 downloads so far.
How do I install okx-cex-earn?
Run "/install okx-cex-earn" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is okx-cex-earn free?
Yes, okx-cex-earn is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does okx-cex-earn support?
okx-cex-earn is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created okx-cex-earn?
It is built and maintained by numpy0001 (@numpy0001); the current version is v1.3.2.
More Skills