PRODUCTIVITY/效率应用·AUTOMATION

loops

jwangkun/loops

Loop（循环）是一种用于AI编程助手（如 Claude Code、Cursor）的自动化工作流指令集。它通过"执行→检查→修复→重复"的闭环模式，让AI能够自主完成开发任务，直到达到预设目标。

打开仓库Open repository

怎么装：Install: git clone https://github.com/jwangkun/loops.git ~/.claude/skills/loops

02 / 现在的位置02 / Why now

它现在处在什么位置Where it stands right now

首次发现FIRST SEEN

03 OCT 202603 OCT 2026

增长GROWTH

+0.0%+0.0%

124 → 124 stars · 2 个快照124 → 124 stars · 2 snapshots

状态STATUS

持续活跃Active

03 / 它能帮你做什么03 / What it helps you do

它能帮你做成什么What it helps you do

04 / 安装04 / Install

怎么装How to install

GIT-CLONE

$

README 里给出的安装方式。The installation method given in the README.

MANUAL-COPY

$

README 里给出的安装方式。The installation method given in the README.

两种装法选一个即可 —— 上面那条给命令行用户，下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.

05 / 限制与风险05 / Limits and risk

限制与风险Limits and risk

风险不是警告，是可信度的一部分。以下结论只基于文档静态扫描，我们不会执行项目里的任何代码。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.

限制LIMITS

需检查Needs review

01需要 API KeyREQUIRES API KEY: 未在文档中发现Not found in the docs
02需要本地环境NEEDS LOCAL RUNTIME: 未在文档中发现Not found in the docs
03需要 DockerNEEDS DOCKER: 未在文档中发现Not found in the docs
04难度DIFFICULTY: 一键安装One-click install

PROVENANCE · 这些结论的依据是什么Where these conclusions come from

来源 URLSource URL: https://github.com/jwangkun/loops
原始数据哈希Raw data hash: 99f35642c4128062a49e2f32dcc5edd0
解析时间Parsed at: 2026-10-03T23:21:55.876Z
最后一次验证Last verified: 2026-10-04T08:53:33.891Z
增长测量时间Growth measured: 2026-10-03T23:24:59.911Z
发现查询Discovery queries: focus:web:code:seo
分类来源Category source: rules
焦点Focus: web (3)

静态扫描STATIC SCAN

01控制浏览器Controls a browserreadme

| `visual-regression-until-match` | 视觉回归测试通过 | `npx playwright test --grep @visual` | [查看](prompts/zh/visual-regression-until-match.md) | [V

02控制浏览器Controls a browserSKILL.md

| `visual-regression-until-match` | 视觉回归测试通过 | `npx playwright test --grep @visual` | [zh](prompts/zh/visual-regression-until-match.md) · [e

这里只做静态扫描：读 README、SKILL.md 和依赖清单，不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.

完整解析证据 JSONFull parse evidence JSON

{
  "agents": [
    {
      "agent": "claude-code",
      "evidence": "readme: …**Loop（循环）** 是一种用于 AI 编程助手（如 Claude Code、Cursor、Trae、Windsurf、Cline）的自…"
    },
    {
      "agent": "claude-ai",
      "evidence": "readme: …nt 不想装 Skill、或者用的是 ChatGPT / Claude.ai / Gemini / Copilot Chat / 通义…"
    },
    {
      "agent": "codex",
      "evidence": "readme: …### 4.6 Codex（`AGENTS.md`） OpenAI Codex（CLI / IDE 扩展 / Cloud）通过 **`AG…"
    },
    {
      "agent": "cursor",
      "evidence": "readme: …iption` 并执行。 ### 4.3 Cursor（`.cursor/rules/loops.mdc`） > ⚠️ **旧版 `.curs…"
    },
    {
      "agent": "windsurf",
      "evidence": "readme: …程助手（如 Claude Code、Cursor、Trae、Windsurf、Cline）的自动化工作流指令集。它通过\"执行→检查→修复…"
    },
    {
      "agent": "cline",
      "evidence": "readme: …ude Code、Cursor、Trae、Windsurf、Cline）的自动化工作流指令集。它通过\"执行→检查→修复→重复\"的闭…"
    },
    {
      "agent": "copilot",
      "evidence": "readme: …hatGPT / Claude.ai / Gemini / Copilot Chat / 通义 / 文心 等对话框？**直接把某个 Loop 的…"
    }
  ],
  "apiKey": null,
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 0,
      "ai-tools": 0,
      "dev-tools": 2,
      "indie-web": 0,
      "skill-agent": 1,
      "productivity": 3
    },
    "primary": "productivity",
    "secondary": "automation"
  },
  "localRuntime": null,
  "skillMdTotal": 1,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 1,
    "agent": 0,
    "media": 0,
    "design": 0,
    "browser": 0,
    "devtool": 2,
    "security": 0,
    "marketing": 0,
    "productivity": 1
  },
  "classification": [
    {
      "signal": "1 SKILL.md with name + description",
      "weight": 0.95
    },
    {
      "signal": "README describes a Claude / Agent Skill",
      "weight": 0.7
    },
    {
      "signal": "description mentions AI",
      "weight": 0.2
    }
  ],
  "scannedSources": [
    "readme",
    "SKILL.md"
  ],
  "skillMdFetched": 1
}