Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问许可证需确认审计提醒

iii-http-middlewareiii http 中间件

Agent Skill

iii-http-middleware 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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

250

周安装

10

GitHub Stars

15,333

下载量

81
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:iii-http-middleware(iii http 中间件)
来源仓库:https://github.com/iii-hq/iii
仓库路径:skills/iii-http-middleware
安装命令:
npx skills add https://github.com/iii-hq/iii --skill iii-http-middleware
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/iii-hq/iii --skill iii-http-middleware

简介

iii-http-middleware 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。

  • 它能帮助 Agent 基于输入条件匹配内容、过滤无关项或组织检索结果。
  • 通过 npx skills add 命令从指定仓库安装,具体用法请参考原始 README。
  • 使用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。
  • 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

HTTP Middleware

Comparable to: Express middleware, Fastify hooks, Django middleware

Key Concepts

Use the concepts below when they fit the task. Not every middleware setup needs all of them.

  • Middleware functions are registered like normal functions but return {action: 'continue'} or {action: 'respond', response} instead of a normal response
  • Middleware is attached to HTTP triggers via middleware_function_ids in the trigger config
  • The engine executes middleware in order — first middleware runs first, then the next, then the handler
  • Middleware receives a MiddlewareFunctionInput with phase, request (path_params, query_params, headers, method), and context from auth
  • Returning {action: 'respond'} short-circuits the chain — the handler never runs
  • Returning {action: 'continue'} passes to the next middleware or the handler

Architecture

HTTP request
  → iii-http (port 3111)
    → Middleware 1 (continue / respond)
      → Middleware 2 (continue / respond)
        → registerFunction handler
          → { status_code, body, headers } response

iii Primitives Used

PrimitivePurpose
registerFunction(id, handler)Define a middleware function
registerTrigger({config: {middleware_function_ids}})Attach middleware to an HTTP trigger
{action: 'continue'}Pass to next middleware or handler
{action: 'respond', response: {status_code, body}}Short-circuit and return response immediately
req.request.headersAccess request headers in middleware
req.contextAccess auth context from RBAC auth function

Reference Implementation

See ../references/http-middleware.js for the full working example — auth and logging middleware protecting HTTP endpoints.

Common Patterns

Code using this pattern commonly includes, when relevant:

  • iii.registerFunction('middleware::auth', async (req) => {...}) — auth middleware checking headers
  • iii.registerFunction('middleware::rate-limit', async (req) => {...}) — rate limiting middleware
  • iii.registerFunction('middleware::request-logger', async (req) => {...}) — request logging
  • req.request?.headers?.authorization — reading auth tokens
  • return {action: 'respond', response: {status_code: 401, body: {error: 'Unauthorized'}}} — reject request
  • return {action: 'continue'} — allow request through
  • config: {middleware_function_ids: ['middleware::auth', 'middleware::logger']} — attach to trigger

Adapting This Pattern

Use the adaptations below when they apply to the task.

  • Chain multiple middleware for layered concerns (logging before auth before rate-limiting)
  • Use middleware for cross-cutting concerns shared across multiple endpoints
  • Combine with RBAC auth functions for role-based access control — auth context flows to middleware via req.context
  • Keep middleware functions focused on one concern each for reusability

Pattern Boundaries

  • If the task is just exposing HTTP endpoints without middleware, prefer iii-http-endpoints.
  • If auth needs are complex (RBAC with function discovery control), combine this with RBAC worker auth functions.
  • Stay with iii-http-middleware when the primary need is pre-handler processing for HTTP routes.

When to Use

  • Use this skill when the task is primarily about iii-http-middleware in the iii engine.
  • Triggers when the request directly asks for this pattern or an equivalent implementation.

Boundaries

  • Never use this skill as a generic fallback for unrelated tasks.
  • You must not apply this skill when a more specific iii skill is a better fit.
  • Always verify environment and safety constraints before applying examples from this skill.

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

37.2%
按下载量换算30

Claude

31.73%
按下载量换算26

Cursor

18.85%
按下载量换算15

Gemini CLI

9.16%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。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