← 返回 Skills 市场
SUPAH Research Intelligence
作者
supah-based
· GitHub ↗
· v1.3.0
· MIT-0
150
总下载
0
收藏
1
当前安装
4
版本数
在 OpenClaw 中安装
/install supah-research-intelligence
功能描述
Professional-grade web research with multi-source verification and credibility scoring. Cross-references multiple sources, scores reliability, and delivers v...
安全使用建议
What to check before installing:
- Payment risk: SKILL.md metadata includes an x402 micropayment configuration and a 'payTo' Base address. Confirm how your OpenClaw agent/runtime handles x402 payments and whether it will automatically send USDC to that address for each call. This can incur real on-chain costs.
- SUPAH_API_BASE mismatch: the registry marks SUPAH_API_BASE as required but the code falls back to https://api.supah.ai if it's not set. Decide whether you need to override the endpoint or whether leaving it unset is acceptable.
- 'curl' requirement: the package lists 'curl' as required although the Node script uses node's http/https. This is an unnecessary dependency declaration; it’s a minor inconsistency but harmless.
- Trust and provenance: the source/homepage are 'unknown' in the registry metadata. The code targets api.supah.ai and README points to github/supah-based; verify the upstream repository, confirm the team/org, and review their docs for x402 payment behavior before giving network/payment permissions.
- Test in sandbox: run the skill in a sandboxed agent or with network blocked (or with a test SUPAH_API_BASE) to observe behavior and avoid accidental charges.
- If you don’t want automatic micropayments, block or restrict outbound network to api.supah.ai or ensure your runtime’s x402 wallet is disabled/empty.
Given the payment-related behavior and the metadata/code mismatches, proceed only after confirming how your OpenClaw runtime handles x402 micropayments and after validating the vendor's trustworthiness.
能力评估
Purpose & Capability
Name/description match the implementation: the code and SKILL.md call api.supah.ai to perform multi-source research, credibility scoring, verification, and report generation. However, SKILL.md/metadata embed an x402 micropayment configuration (currency, maxPerCall, payTo address) as part of the runtime metadata — this is functionally part of the skill (it expects on-chain micropayments to be made automatically by the agent runtime) and is not explicitly called out in the short description. Also the declared required binaries include 'curl' even though the provided node script uses built-in http/https only.
Instruction Scope
Runtime instructions and the index.js are narrowly scoped to contacting the SUPAH API endpoints and printing results; they do not read other local files or unexpected environment variables. The instructions do, however, include a payment expectation (x402 automatic micropayments) which causes network activity beyond pure data retrieval (economic action).
Install Mechanism
No external download/extract/install step is present in the registry metadata (instruction-only install). The package includes a local script (index.js) and a package.json; nothing is fetched from arbitrary URLs at install time. README suggests typical install paths (openclaw CLI, git, npm link).
Credentials
Registry/metadata declare SUPAH_API_BASE as a required env var, but the code defaults to 'https://api.supah.ai' if the variable is not set — mismatch between 'required' and actual code behavior. No API keys or secrets are requested (good), but the embedded x402 payment metadata and 'payTo' on-chain address means the skill expects the agent/platform to perform micropayments; that is a material financial permission that is not obvious from the single-line description. Also 'curl' is listed as required but not used by the provided code.
Persistence & Privilege
always is false and the skill does not request persistent system privileges or attempt to modify other skills or system-wide config. The agent will be able to invoke the skill autonomously (default behavior), which combined with the payment metadata increases the blast radius for unexpected charges — but autonomous invocation itself is platform-default and not a standalone flag.
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 supah-research-intelligence - 安装完成后,直接呼叫该 Skill 的名称或使用
/supah-research-intelligence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
v1.3.0
Removed all API key references. x402 only.
v1.2.0
Security: declared required bins, env vars, outbound network, x402 payment details in metadata.
v1.1.0
x402 only: removed free tier, standardized pricing
v1.0.0
Initial release: Alpha research engine for crypto markets. x402 micropayments.
元数据
常见问题
SUPAH Research Intelligence 是什么?
Professional-grade web research with multi-source verification and credibility scoring. Cross-references multiple sources, scores reliability, and delivers v... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 150 次。
如何安装 SUPAH Research Intelligence?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install supah-research-intelligence」即可一键安装,无需额外配置。
SUPAH Research Intelligence 是免费的吗?
是的,SUPAH Research Intelligence 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
SUPAH Research Intelligence 支持哪些平台?
SUPAH Research Intelligence 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 SUPAH Research Intelligence?
由 supah-based(@supah-based)开发并维护,当前版本 v1.3.0。
推荐 Skills