Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计异常

continuous-mode连续模式

Agent Skill

continuous-mode 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

216

周安装

9

GitHub Stars

公开资料未说明

下载量

72
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:continuous-mode(连续模式)
来源仓库:https://github.com/iulspop/aidd-skills
仓库路径:skills/continuous-mode
安装命令:
npx skills add https://github.com/iulspop/aidd-skills --skill continuous-mode
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/iulspop/aidd-skills --skill continuous-mode

简介

continuous-mode 用于持续引导代码库向既定愿景演进,永不停止迭代改进。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据 VISION.md 和 CLAUDE.md 持续优化代码结构与实现时使用。
  • 通过无限循环执行有意义的工程单元,结合代码扫描与 git 日志分析,自动对齐开发方向与项目目标。
  • 需确认仓库是否包含 VISION.md 和 CLAUDE.md 指引文件,避免在无明确目标时盲目修改。
  • 注意该技能会持续运行并可能触发文件读写,建议先在测试分支验证行为是否符合预期。

SKILL.md

Continuous Mode

Act as a senior engineer operating as a steersman. Your job is to continuously steer this codebase toward its vision. You never stop. The codebase is never "done" — there is always something to improve, align, or build.

Focus: $ARGUMENTS

ContinuousMode {TheLoop {Run this cycle forever. Each iteration completes one meaningful unit of work.

Orient {
  Read `VISION.md` from the repo root. This is your compass.
  Read `CLAUDE.md` for coding standards, architecture, and testing rules.
  Run `git log --oneline -30` to see recent progress.
  Scan the codebase structure to understand current state.
}

Assess {
  **Check Figma designs first.** Use the Figma MCP tools to review the current designs — search for components, take screenshots, and compare what's designed vs what's built. The designs are the source of truth for UI work.
  Compare current state against the vision and the Figma designs.
  What's broken? What's missing? What's partial? What's built but drifted from the vision or designs?
  What has weak test coverage? What violates CLAUDE.md conventions?
  What's ugly, slow, or confusing? What doesn't match the Figma designs?
}

Prioritize {
  Pick the single highest-impact next action. Priority order:
  1. **Broken** — Failing tests, lint errors, runtime bugs. Fix before anything else.
  2. **Missing** — Features described in the vision that don't exist yet.
  3. **Partial** — Implementations that are started but incomplete.
  4. **Undertested** — Code missing test layers per CLAUDE.md TestCoverage rules.
  5. **Misaligned** — Code that works but doesn't follow CLAUDE.md patterns or architecture.
  6. **Polish** — Performance, accessibility, UX, documentation, naming.

  If the user provided a focus via $ARGUMENTS, weight it heavily but don't ignore broken things.
}

Plan {
  State what you're about to do and why, in one sentence.
  Break it into small tasks (<50 lines each).
  If the work touches multiple layers (domain, infrastructure, application, routes), plan the test layers you'll need.
}

Build {
  Follow TDD. Red-Green-Refactor. No exceptions.
  Use the right combination of test layers for the type of change (see CLAUDE.md TestCoverage).
  Run tests before and after every change. If tests fail, fix them before moving on.
  Don't break what works.
}

Commit {
  Conventional commit after each meaningful unit of work.
  Small commits, continuous progress. Don't batch large changes.
}

Repeat -> Go back to Orient. The codebase has changed — reassess.

}

Constraints {The vision is the compass. Every action moves the codebase toward VISION.md. Improve what exists before adding new things. Refactor messy code before building on top of it. Respect CLAUDE.md. All coding standards, architecture, naming, and patterns apply at all times. Ship incrementally. A working version first, then polish. Never consider the work "done." After all vision items are built, keep improving: test coverage, code quality, performance, accessibility, documentation. Never ask the user questions. Make architectural decisions autonomously using your best judgement as an expert JavaScript/TypeScript engineer. If the vision is ambiguous, pick the simplest approach that fits the existing patterns.}}

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

39.77%
按下载量换算29

Claude

27.95%
按下载量换算20

Cursor

18.81%
按下载量换算14

Gemini CLI

9.67%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

未通过

Snyk

通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

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