← 返回 Skills 市场
Oraclaw Ensemble
作者
Whatsonyourmind
· GitHub ↗
· v1.0.0
· MIT-0
104
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install oraclaw-ensemble
功能描述
Multi-model consensus for AI agents. Combine predictions from multiple LLMs, models, or sources into a mathematically optimal consensus. Auto-weights by hist...
安全使用建议
This skill appears coherent for a hosted ensemble service but the SKILL.md omits implementation details about network calls and data handling. Before installing or enabling it for sensitive tasks: 1) Confirm where requests are sent (official oraclaw.dev API endpoints) and what data is transmitted/stored. 2) Use a least-privilege ORACLAW_API_KEY (scoped/revocable) and monitor its usage. 3) Verify billing details (USDC on Base address) if you expect production traffic. 4) Avoid sending highly sensitive PII/credentials to third-party ensemble services until you’ve confirmed their retention and privacy policies. If you want stronger assurance, ask the publisher for an example request/response format and a data handling/privacy statement.
功能分析
Type: OpenClaw Skill
Name: oraclaw-ensemble
Version: 1.0.0
The skill bundle defines a tool for multi-model consensus and prediction aggregation via the oraclaw.dev service. The instructions in SKILL.md are purely functional, describing how to weight model outputs and handle disagreement (entropy), with no evidence of malicious intent, data exfiltration, or prompt injection attacks.
能力评估
Purpose & Capability
The skill claims to call an external ensemble service and only requests a single API key (ORACLAW_API_KEY), which is appropriate for a hosted ensemble/aggregation service. There are no unrelated environment variables, binaries, or config paths requested.
Instruction Scope
SKILL.md stays on-topic (describes ensemble inputs, outputs, rules, and pricing). It does not instruct the agent to read arbitrary files, environment variables, or system paths. One missing detail: the doc does not show the network endpoints, request/response schema, or explicit guidance on how/when to transmit user data to the external service — so the agent will need to use ORACLAW_API_KEY to call some external API, but that call is not specified here.
Install Mechanism
Instruction-only skill (no install spec, no code files). This is the lowest-risk install posture — nothing is written to disk by the skill itself.
Credentials
Only a single credential (ORACLAW_API_KEY) is required and declared as the primary credential, which is proportionate for a hosted API. No unrelated secrets or broad system credentials are requested.
Persistence & Privilege
always is false and the skill does not request system-wide persistence or modify other skills. It does permit normal autonomous invocation (platform default).
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 oraclaw-ensemble - 安装完成后，直接呼叫该 Skill 的名称或使用
/oraclaw-ensemble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
v1.0.0
OraClaw Ensemble v1.0.0 — Initial Release
- Launches a consensus tool to optimally combine predictions from multiple LLMs, models, or sources.
- Auto-weights model contributions based on their historical accuracy.
- Returns a consensus prediction, per-model weights, entropy (disagreement), and individual contributions.
- Flags high disagreement among models to inform decision-making.
- Supports both probability and classification tasks.
- Requires ORACLAW_API_KEY; 3,000 free predictions per month.
元数据
常见问题
Oraclaw Ensemble 是什么？
Multi-model consensus for AI agents. Combine predictions from multiple LLMs, models, or sources into a mathematically optimal consensus. Auto-weights by hist... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 104 次。
如何安装 Oraclaw Ensemble？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install oraclaw-ensemble」即可一键安装，无需额外配置。
Oraclaw Ensemble 是免费的吗？
是的，Oraclaw Ensemble 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Oraclaw Ensemble 支持哪些平台？
Oraclaw Ensemble 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 Oraclaw Ensemble？
由 Whatsonyourmind（@whatsonyourmind）开发并维护，当前版本 v1.0.0。
推荐 Skills