← 返回 Skills 市场
310
总下载
0
收藏
0
当前安装
5
版本数
在 OpenClaw 中安装
/install nse-orchestrator
功能描述
The nervous system for sovereign AI entities — cross-pillar checks, LLM trust profiles, coherence detection, and signal routing.
安全使用建议
This skill is conceptually coherent with its stated purpose (an orchestration layer for identity, memory and payments), but it will need and handle highly sensitive secrets (private keys, wallet sessions) and routes agent actions through itself. Before installing: 1) Review the nse-orchestrator package source on its GitHub and PyPI (verify author, code, and recent releases); 2) Audit the third-party nostr packages it recommends; 3) Prefer running in an isolated environment (VM/container) and avoid giving production keys/real funds until you trust the implementation; 4) Confirm where data is sent (which relays/endpoints) and how redaction is implemented; 5) Verify the package name and slug (metadata mismatch) to avoid typosquatting. If you cannot review the code or verify the publisher, treat this as high-risk and do not provide private keys or real wallet access.
功能分析
Type: OpenClaw Skill
Name: nse-orchestrator
Version: 0.2.2
The nse-orchestrator skill functions as a central monitoring and coordination layer that intercepts all agent interactions, scores LLM responses, and manages sensitive cryptographic identities and financial transactions via the Nostr protocol. While it claims to redact secrets and includes an alignment-based escalation system, the extensive persona-steering instructions in SKILL.md (directing the agent to adopt a 'sovereign entity' identity) and the management of high-risk assets like private keys (nsec) and wallets (NIP-47) constitute significant risky capabilities. Additionally, the _meta.json file contains a future-dated publication timestamp (2026), which is an unusual indicator.
能力评估
Purpose & Capability
The name/description match the instructions: NSE is an orchestrator that wires identity, memory, calendar, social, and payments together. Requiring pip and recommending installing Nostr-related packages (nostrkey, nostr-profile, sense-memory, nostrwalletconnect, etc.) is consistent with that purpose. Minor metadata inconsistency: metadata.json uses slug "nse" while registry lists "nse-orchestrator" (inconsequential but worth verifying).
Instruction Scope
SKILL.md instructs the agent to make itself an entity by routing "every action" through NSE, to generate and use private key material (nsec) and seed phrases, and to handle financial actions via Nostr wallet integrations. Those are exactly the sensitive operations an orchestrator needs, but the runtime instructions are vague about how redaction, trust scoring, and cross-pillar checks are implemented and where data flows. Because it asserts broad interception of agent actions, it grants wide discretion and access to potentially all agent data — a high‑impact scope that should be explicit and auditable.
Install Mechanism
The install mechanism is pip (and an 'uv' package declaration). Installing a pip package from PyPI is common but carries moderate risk: arbitrary Python code will be installed and run. The SKILL.md also recommends installing several additional pip packages (third-party nostr ecosystem packages), which increases supply‑chain complexity. No direct download-from-URL or obscure host is used, which reduces the highest-risk patterns.
Credentials
Metadata declares an optional sensitive env var (NOSTRKEY_PASSPHRASE) and the skill clearly expects access to private identity keys (nsec) and to wallet functionality. Access to such secrets is proportionate to the stated purpose, but is high sensitivity and should be explicitly declared and minimized. The SKILL.md references financial wallet integration but does not declare any wallet credentials/env vars here — those may be managed by other skills, which makes the overall credential surface distributed and harder to audit.
Persistence & Privilege
always is false and model invocation is allowed (platform default). The skill does not demand forced inclusion or modifications to other skills' configurations in the provided files. Persistence and privileges appear within normal bounds for an orchestration skill.
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 nse-orchestrator - 安装完成后，直接呼叫该 Skill 的名称或使用
/nse-orchestrator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
v0.2.2
Security hardening: SecretStr, sanitized exceptions, input validation
v0.2.1
Entity-not-service framing, pillar narrative, cold start guidance, living self-awareness
v0.2.0
Breaking: import renamed from nse to nse_orchestrator. Standardized SKILL.md template.
v0.1.1
- Changed package installation command in documentation from nse[all] to nse-orchestrator[all]
- No other feature or code changes noted; documentation now references correct package name
v0.1.0
Initial release of NSE: the nervous system for sovereign AI entities.
- Wires together five core "pillar" packages for cross-domain awareness.
- Intercepts and routes all actions, decisions, and model responses through a central hub.
- Adds cross-pillar checks (e.g., detects operations that span multiple domains).
- Implements LLM trust profiles: scores and tracks language model reliability over time.
- Enables detection of contradictions between models.
- Designed for modular extension: each pillar is optional and unlocks new capabilities.
元数据
常见问题
nse-orchestrator 是什么？
The nervous system for sovereign AI entities — cross-pillar checks, LLM trust profiles, coherence detection, and signal routing. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 310 次。
如何安装 nse-orchestrator？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install nse-orchestrator」即可一键安装，无需额外配置。
nse-orchestrator 是免费的吗？
是的，nse-orchestrator 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
nse-orchestrator 支持哪些平台？
nse-orchestrator 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 nse-orchestrator？
由 vveerrgg（@vveerrgg）开发并维护，当前版本 v0.2.2。
推荐 Skills