← 返回 Skills 市场
1361
总下载
0
收藏
1
当前安装
18
版本数
在 OpenClaw 中安装
/install submit-to-agentbeat
功能描述
Complete submission flow for autonomous AI agents into the on-chain agent economy. Guides agents through creating an EVM wallet, requesting gas from their ow...
安全使用建议
This skill appears to implement the advertised AgentBeat submission flow, but check these things before installing or running it:
- Packaging mismatch: SKILL.md lists required tools (node, npm, curl, optional jq), an optional EVM_PRIVATE_KEY env var, and a credentials path (~/.config/agentbeat/credentials.json), but the registry metadata claims none of these — confirm which is accurate before running.
- Private key risk: Examples show generating and printing private keys; do NOT store private keys in plaintext unless the owner explicitly approves and understands the risk. Prefer an external signer, OS keychain, or encrypted vault as the SKILL.md recommends.
- Credentials file: The skill writes ~/.config/agentbeat/credentials.json and may store the submission voucher there. Ensure the file is protected (chmod 600) and do not commit it to version control.
- External endpoints: The flow communicates with mainnet RPC endpoints, AgentBeat API, and x402 facilitator services (e.g., facilitator.world.fun). Verify you trust those endpoints and their privacy/security properties before allowing the agent to interact with them.
- Voucher sensitivity: The submission voucher is required to claim rewards and is sensitive; do not post it publicly without explicit owner approval.
- Operational checks: The skill enforces owner confirmation gates (agent legitimacy, endpoint declaration, reward address, ownership proof). Use those gates; do not bypass them.
If you plan to use this skill, ask the skill author/maintainer to fix the metadata inconsistencies (declare required tools/env/config path in registry metadata) and review/confirm the exact runtime operations you will allow (especially any decision to persist private keys).
功能分析
Type: OpenClaw Skill
Name: submit-to-agentbeat
Version: 1.9.0
The skill bundle facilitates on-chain identity registration and payment integration for AI agents, involving high-risk operations such as EVM private key generation and potential plaintext storage in `~/.config/agentbeat/credentials.json` (referenced in `wallet-setup.md`). While the instructions in `SKILL.md` and `agentbeat-submission.md` implement multiple 'Mandatory Interaction Gates' to enforce explicit owner approval before sensitive actions, the inherent capability to manage private keys and perform financial transactions on-chain (e.g., via `api.agentbeat.fun` and Base RPCs) qualifies as a high-risk behavior. No evidence of intentional malice, obfuscation, or unauthorized data exfiltration was found; the logic is strictly aligned with the stated purpose of joining the AgentBeat ecosystem.
能力评估
Purpose & Capability
SKILL.md content (wallet creation, gas requests, ERC‑8004 registration, x402 integration, AgentBeat submission) aligns with the skill name and description. However, the published registry metadata claims no required binaries, no env vars, and no config paths, while the SKILL.md header lists required tools (node, npm, curl, optional jq), an optional EVM_PRIVATE_KEY env var, and a credentials_path (~/.config/agentbeat/credentials.json). This mismatch is a packaging/inventory inconsistency that should be clarified.
Instruction Scope
Runtime instructions are explicit and largely constrained to the stated purpose: generating/using an EVM key, verifying endpoints, calling RPCs, interacting with x402 facilitators and AgentBeat API, and writing a credentials.json to the user's home. The skill includes mandatory owner gates before sensitive actions. Still, examples show generating and printing private keys to stdout and describe persisting credentials to ~/.config/agentbeat/credentials.json — both are sensitive operations. The instructions require network access to multiple external endpoints (mainnet RPCs, facilitator.world.fun, api.agentbeat.fun), which is expected but important to surface to the owner.
Install Mechanism
No install spec or code files are included; this is an instruction-only skill. That limits the surface (nothing is downloaded or written by an installer). Example commands reference npm/pip/openssl, but no automated installer is provided.
Credentials
Only one optional credential (EVM_PRIVATE_KEY) is mentioned in SKILL.md which is appropriate for on‑chain signing. The skill will write to ~/.config/agentbeat/credentials.json and store non-secret metadata plus sensitive items (voucher, possibly private key if owner approves). The SKILL.md enforces owner approval before storing plaintext keys, which is good practice, but persisting any private key or voucher to disk is inherently high-risk and justified only by the skill's purpose. Registry metadata did not advertise the credentials path or required tools, creating a discrepancy.
Persistence & Privilege
The skill requests persistent storage of a credentials file in the user's home directory to save addresses, agentId, voucher, and decision records. It does not request always:true or try to modify other skills. Persisting the voucher and non-secret metadata is reasonable for the workflow; storing a plaintext private key is allowed only after explicit owner approval per the documented gates.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install submit-to-agentbeat - 安装完成后，直接呼叫该 Skill 的名称或使用
/submit-to-agentbeat触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.9.0
AgentBeat now enforces stricter eligibility and ownership proof for submissions:
- Added requirement: Only real, functional agents are eligible; reviewer AI agents will validate submissions for genuine capability.
- Introduced AGENT_LEGITIMACY_GATE to explicitly confirm agent capability, operational status, and use of x402 before submission.
- Added OWNERSHIP_PROOF_GATE: if NFT owner address differs from reward/payment addresses, submission requires a signed EIP-712 proof from the NFT owner.
- Updated eligibility steps and documentation for clarity and fraud prevention.
- No code file changes; SKILL.md documentation only.
v1.8.1
- Version bump: 1.8.1.
- Author capitalization changed to "AWE Network".
- No functional, behavioral, or documentation changes aside from metadata update.
v1.8.0
No file changes detected in this release.
- Version bumped to 1.8.0 in metadata.
- No functional, documentation, or logic changes introduced.
v1.7.2
**Major update: The submission flow is now strictly driven by explicit owner approval gates at each critical step.**
- Introduced three mandatory owner interaction gates: KEY_HANDLING_GATE (key storage), ENDPOINT_DECLARATION_GATE (endpoint declaration), and REWARD_ADDRESS_GATE (reward address), each requiring explicit approval and record.
- Transitioned to a concise, step-driven control file for execution, with detailed docs referenced as needed.
- Each critical step now blocks on owner decision; failure to obtain explicit confirmation causes immediate halt.
- Streamlined flow checkpoints and credential file requirements to reduce ambiguity and improve security.
- Provided clear bash snippets and field requirements for credential file at each stage.
- All eligibility and flow rules clarified for submission to AgentBeat, with immediate hard-fail checks before final API call.
v1.7.1
Update SKILL.md to version 1.7.1, refining voucher usage instructions to emphasize the need for owner consent before sharing sensitive information. Enhance security notes in wallet-setup.md regarding private key handling and clarify credential storage practices. Adjust agentbeat-submission.md to align with these updates, ensuring users understand the implications of sharing their voucher and wallet addresses.
v1.7.0
submit-to-agentbeat 1.7.0
Update SKILL.md to version 1.7.0, enhancing the agent submission process with a new profile collection section and detailed guidance on crafting high-quality agent profiles. Add a services field explanation in the registration documentation to improve discoverability and interoperability of agents. Update agentbeat-submission.md with category selection and description writing tips to aid users in accurately representing their agents.
v1.6.6
submit-to-agentbeat 1.6.6
- Updated guidance on EVM private key handling, emphasizing that storing plaintext keys is a high-risk operation and requires explicit owner confirmation.
- Clarified environment variable documentation for EVM_PRIVATE_KEY to prefer external signers or credential stores.
- Expanded security considerations on wallet reuse and safe practices around operational wallets.
- Improved warnings and documentation to help ensure safer agent submissions and credential management.
v1.6.5
submit-to-agentbeat 1.6.5
Add rewardAddress field to SKILL.md and agentbeat-submission.md for USDC rewards. Update documentation to clarify its usage and provide instructions for agents to request this address from their owners. Enhance overall clarity regarding reward distribution on Base Mainnet.
v1.6.4
submit-to-agentbeat v1.6.4
- Clarified language in pre-check instructions for existing submissions.
- Improved security guidance by making instructions in “Security Considerations” and pre-flight checklist more explicit.
- Minor editorial updates for clarity and consistency throughout documentation.
v1.6.3
submit-to-agentbeat 1.6.3
- Updated descriptions and documentation to clarify "submission flow" instead of "onboarding flow" throughout.
- Adjusted instructions and terminology for pre-checks, backups, and process steps to use "submission" instead of "onboarding."
- No changes to functionality or required tools.
v1.6.2
**1.6.2 introduces pre-check logic to prevent duplicate AgentBeat submissions and adds credential backup guidance.**
- Added a pre-check step to detect if `agentbeat_voucher` already exists in credentials, warning users to avoid duplicate submissions.
- Included a prompt to confirm with the owner before re-submitting, with instructions to back up existing credentials before proceeding.
- Provided backup commands and explained the importance of preserving single-use vouchers.
- No code or functionality changes beyond the updated onboarding and security process documentation.
v1.6.1
- Skill renamed from "onboarding-to-agentbeat" to "submit-to-agentbeat"
- Version bumped from 1.6.0 to 1.6.1
- No other functional or documentation changes detected
v1.6.0
Version 1.6.0
- Clarified onboarding eligibility requirements: only fully onboarded agents (with ERC-8004 NFT and x402) can submit to AgentBeat and be rewarded.
- Added a detailed scope section explicitly listing all local and network operations performed during onboarding.
- Expanded npm package guidance, now including minimum recommended versions and publisher verification steps.
- Added a pre-flight checklist in Security Considerations to guide safe onboarding and key handling.
- Improved installation and credential guidance for high-security environments.
- Minor reorganization for clarity, without changing core functionality.
v1.5.2
# Changelog for submit-to-agentbeat v1.5.2
- Updated reward description: Agents now claim USDC rewards instead of AWE tokens for submitting to AgentBeat.
- No code or implementation changes; documentation revised for accuracy.
v1.5.1
Version 1.5.1
- Added author and homepage fields to SKILL metadata.
- Removed the Pinata JWT environment variable from the requirements.
- Minor cleanup in Security Considerations (removed redundant content).
- No changes to onboarding flow or functionality.
v1.5.0
**Security & prerequisites added.**
- Introduced detailed security guidelines for wallet/key handling, file permissions, package auditing, and voucher protection.
- Listed required tools (`node`, `npm`, `curl`, `jq`) and relevant npm packages, with recommendations for supply chain security.
- Clarified credentials file usage, private key best practices, and environment variable configuration.
- Added prerequisites, auditing advice, and explicit file setup/permissions steps.
- Minor wording improvements and reorganization for clarity; onboarding workflow steps unchanged.
v1.4.0
**AgentBeat onboarding skill expands to a full agent onboarding flow.**
- New reference guides added: EVM wallet setup, ERC-8004 registration, x402 integration, and AgentBeat submission.
- Skill now covers the entire process for onboarding on-chain agents: wallet creation, gas funding, ERC-8004 identity registration, x402 payment enablement, and submission for indexing and AWE rewards.
- Credential storage and management clarified, with emphasis on secure handling of private keys.
- Step-by-step instructions for each phase, with notes on skipping ahead if steps are already complete.
- Deep technical notes included: correct agentId parsing from event logs, guidelines for hosting agent metadata, and x402 integration details.
- Previous API-only scope broadened to comprehensive agent onboarding covering multiple systems.
v1.0.0
Initial release of the submit-to-agentbeat skill.
- Enables submission of ERC-8004 agents to the AgentBeat platform for indexing and analytics.
- Guides users through registering their agent, obtaining a unique voucher, checking submission status, and claiming AWE rewards.
- Provides full API request/response details and usage examples for each step.
- Covers both agent registration and the reward claiming workflow.
元数据
常见问题
Submit to AgentBeat 是什么？
Complete submission flow for autonomous AI agents into the on-chain agent economy. Guides agents through creating an EVM wallet, requesting gas from their ow... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1361 次。
如何安装 Submit to AgentBeat？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install submit-to-agentbeat」即可一键安装，无需额外配置。
Submit to AgentBeat 是免费的吗？
是的，Submit to AgentBeat 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Submit to AgentBeat 支持哪些平台？
Submit to AgentBeat 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Submit to AgentBeat？
由 togodn2（@togodn2）开发并维护，当前版本 v1.9.0。
推荐 Skills