← Back to Skills Marketplace
868
Downloads
2
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install switchboard-data-operator
Description
Autonomous operator for Switchboard on-demand feeds, Surge streaming, and randomness. Designs jobs, simulates via Crossbar, and deploys/updates/reads feeds across Solana/SVM, EVM, Sui, and other Switchboard-supported chains—with user-controlled security, spend limits, and allow/deny lists.
Usage Guidance
This skill is internally consistent for operating Switchboard feeds, but treat it like any tool that can sign on-chain transactions: only use it if you trust the skill's author/source. Before granting signing authority or providing keys: (1) prefer hardware wallets or a remote signer (never paste seed phrases or full key files into chat), (2) start in read_only or plan_only mode and test on devnet/testnet, (3) set strict spend limits and allowlists in the OperatorPolicy, (4) avoid persisting secrets and prefer secret managers, and (5) review any concrete transaction steps the agent proposes before approving. If the skill’s origin remains unknown, exercise extra caution and avoid supplying mainnet signing keys.
Capability Analysis
Type: OpenClaw Skill
Name: switchboard-data-operator
Version: 1.0.0
The skill bundle defines an autonomous agent for Switchboard oracle operations, involving high-risk capabilities such as signing blockchain transactions, moving funds, deploying contracts, and executing shell commands (e.g., `npm install`, `docker-compose`). While the `SKILL.md` includes extensive and explicit security instructions (e.g., `OperatorPolicy` for user-controlled permissions, mandatory secret handling rules forbidding exfiltration), the inherent power and complexity of these operations, combined with the agent's ability to design oracle jobs that could include `llmTask` (a potential prompt injection vector against the oracle's LLM) or `secretsTask` (accessing external secret servers), elevate the risk beyond benign. The skill itself does not exhibit malicious intent, but the broad capabilities and the potential for vulnerabilities in an autonomous system handling financial and on-chain operations warrant a 'suspicious' classification.
Capability Assessment
Purpose & Capability
The name/description match the instructions: the SKILL.md describes designing, simulating, deploying, updating, and reading Switchboard feeds across multiple chains and references appropriate SDKs and patterns. There are no unexpected external credentials, binaries, or config paths requested that would be unrelated to on-chain operator tasks.
Instruction Scope
The instructions are relatively scoped and security-conscious: they require obtaining an explicit OperatorPolicy before signing/moving funds, never printing secrets, and preferring keystores/secret managers. The skill does describe reading keys from file paths, env vars, or remote signers if the user specifies them — which is expected for a blockchain operator, but this is the primary area where user caution is required (ensure the agent only accesses keys you explicitly allow).
Install Mechanism
Instruction-only skill with no install spec or code files. No code is downloaded or written to disk as part of the skill itself, which reduces installation risk. The SKILL.md recommends npm packages/CLI tools for developer workflows, but the skill does not attempt to install them automatically.
Credentials
The skill declares no required environment variables or primary credential. It documents possible key sources (file, keystore, env var, remote signer) as user-configurable options; that is proportionate to its function. There are no unrelated secrets requested.
Persistence & Privilege
The skill is not always-enabled and does not request elevated platform persistence. It allows autonomous invocation (the platform default), but the SKILL.md requires explicit OperatorPolicy and user consent for signing/execution. If the user grants 'full_autonomy' and provides keys, the agent could act on chain—this is expected behaviour but requires user caution.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install switchboard-data-operator - After installation, invoke the skill by name or use
/switchboard-data-operator - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: Autonomous operator for Switchboard on-demand feeds, Surge streaming, and randomness across Solana/SVM, EVM, Sui, and more.
Metadata
Frequently Asked Questions
What is Switchboard Skills?
Autonomous operator for Switchboard on-demand feeds, Surge streaming, and randomness. Designs jobs, simulates via Crossbar, and deploys/updates/reads feeds across Solana/SVM, EVM, Sui, and other Switchboard-supported chains—with user-controlled security, spend limits, and allow/deny lists. It is an AI Agent Skill for Claude Code / OpenClaw, with 868 downloads so far.
How do I install Switchboard Skills?
Run "/install switchboard-data-operator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Switchboard Skills free?
Yes, Switchboard Skills is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Switchboard Skills support?
Switchboard Skills is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Switchboard Skills?
It is built and maintained by oakencore (@oakencore); the current version is v1.0.0.
More Skills