Token导航 LogoToken导航TokenDH.com
开发只读github未标认证来源可访问许可证需确认审计通过

architect-nostr-intent-router架构师 nostr 意图路由器

Agent Skill

architect-nostr-intent-router 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

188

周安装

8

GitHub Stars

公开资料未说明

下载量

66
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:architect-nostr-intent-router(架构师 nostr 意图路由器)
来源仓库:https://github.com/ajrlewis/ai-skills
仓库路径:skills/architect-nostr-intent-router
安装命令:
npx skills add https://github.com/ajrlewis/ai-skills --skill architect-nostr-intent-router
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/ajrlewis/ai-skills --skill architect-nostr-intent-router

简介

architect-nostr-intent-router 用于 Nostr 协议项目的意图识别和 NIP 模块路由选择。

  • 适用于 Codex、Claude、Cursor、Gemini CLI 中构建去中心化社交应用的基础设施层。
  • 通过 GitHub 安装,使用 npx skills add 命令添加技能,需配合其他基础设施技能使用。
  • 安装前建议确认权限范围,注意是否会触发外部协议连接或密钥管理操作。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Architect: Nostr Intent Router

Use this skill when a project needs Nostr features and you must detect protocol requirements, select NIPs, and route to the right reusable skills.

This is a protocol control-plane architect skill. It should be combined with exactly one infrastructure base architect (for example architect-nextjs-bun-app).

Compatibility

  • Best with architect-stack-selector.
  • Usually paired with addon-nostr-client-nextjs and addon-nostr-nip-profile-selector.
  • Optional pairings based on intent: addon-nostr-key-custody, addon-nostr-nip23-longform, addon-nostr-nip-sync-lock.

Inputs

Collect:

  • NOSTR_INTENTS: capabilities requested by user (for example login, feed, publish, longform, dm, relay-policy, key-custody).
  • NIP_CONSTRAINTS: explicit required/forbidden NIPs if provided.
  • CLIENT_MODE: social-client | longform-publisher | dm-client | custom.
  • LEGACY_COMPAT: yes | no (default no).
  • NIP_LOCK_POLICY: required | optional (default required in production-default).

Intent To NIP Routing

Use this mapping as the starting point and justify deviations:

  • identity and baseline events: 1, 19
  • extension signer login: 7
  • relay list policy and relay preferences: 65
  • short note threading/replies: 10
  • reactions: 25
  • URI addressing / sharing: 21
  • long-form articles: 23
  • encrypted DM mode: 17, 44, 59

Legacy rule:

  • Exclude legacy cryptography NIPs by default unless LEGACY_COMPAT=yes with documented reason.

Skill Routing Rules

  1. Always add:
  • addon-nostr-client-nextjs
  • addon-nostr-nip-profile-selector
  1. Add by detected intent:
  • longform or kind 30023 -> addon-nostr-nip23-longform
  • key-custody, private keys, local signing fallback -> addon-nostr-key-custody
  • sync latest nips, nip lockfile, spec pinning -> addon-nostr-nip-sync-lock
  1. Client mode defaults:
  • social feed/timeline intent -> social-client
  • publishing essays/journals intent -> longform-publisher
  • direct message intent -> dm-client
  • mixed or unusual protocol requirement -> custom with explicit NIP set
  1. If NIP requirements are ambiguous:
  • choose minimal profile first
  • mark ambiguous capabilities in decision log
  • require explicit human confirmation before adding risky legacy or weakly specified protocol features

Required Outputs

Produce:

docs/nostr/NIP_REQUIREMENTS.md
docs/nostr/NIP_DECISIONS.md

NIP_REQUIREMENTS.md must contain:

  • detected intents
  • required NIPs
  • optional NIPs
  • excluded NIPs and why
  • selected client mode

NIP_DECISIONS.md must contain:

  • decision IDs
  • alternatives considered
  • tradeoffs and residual risks
  • resulting skill composition

Output Template

Detected intents:
- <intent>

Selected client mode:
- <social-client|longform-publisher|dm-client|custom>

Selected NIPs:
- required: <list>
- optional: <list>
- excluded: <list + rationale>

Selected skills (ordered):
1) <base architect>
2) architect-nostr-intent-router
3) addon-nostr-client-nextjs
4) addon-nostr-nip-profile-selector
5) <other nostr add-ons as needed>

Justification summary:
- <why each non-trivial NIP/skill decision was chosen>

Guardrails

  • Documentation contract for generated code:

- Python: write module docstrings and docstrings for public classes, methods, and functions. - Next.js/TypeScript: write JSDoc for exported components, hooks, utilities, and route handlers. - Add concise rationale comments only for non-obvious logic, invariants, or safety constraints. - Apply this contract even when using template snippets below; expand templates as needed.

  • Do not guess broad NIP support without explicit product intent.
  • Keep NIP set minimal and capability-driven.
  • Treat legacy compatibility as explicit risk acceptance.
  • Ensure NIP profile docs, code profile, and lockfile strategy are consistent.

Validation Checklist

  • Confirm generated code includes required docstrings/JSDoc and rationale comments for non-obvious logic.
test -f docs/nostr/NIP_REQUIREMENTS.md
test -f docs/nostr/NIP_DECISIONS.md
rg -n "Selected client mode|required|optional|excluded" docs/nostr/NIP_REQUIREMENTS.md
rg -n "DEC-|tradeoff|risk|composition" docs/nostr/NIP_DECISIONS.md

Decision Justification Rule

  • Every non-trivial decision must include a concrete justification.
  • Capture the alternatives considered and why they were rejected.
  • State tradeoffs and residual risks for the chosen option.
  • If justification is missing, treat the task as incomplete and surface it as a blocker.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

35.92%
按下载量换算24

Claude

27.18%
按下载量换算18

Cursor

18.31%
按下载量换算12

Gemini CLI

9.93%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills