Token导航 LogoToken导航

Agent Skill · 研究检索

ru(茹)

ru 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。

ru 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为执行命令;许可证为 MIT,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 42,402。

总安装 1,077周安装 44GitHub Stars 63下载 348核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

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:ru(茹)
来源仓库:https://github.com/dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations
仓库路径:skills/ru
安装命令:
npx skills add https://github.com/dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations --skill ru
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations --skill ru

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

ru 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。适用于信息调研、资料搜集和线索筛选等研究类任务场景。通过 npx skills add 命令从指定 GitHub 仓库安装并使用。

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。ru 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/ru

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/dicklesworthstone/agent_flywheel_clawdbot_skil…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要执行命令,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

ru 怎么安装?

在终端执行 npx skills add https://github.com/dicklesworthstone/agent_flywheel_clawdbot_skills_and_int…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

ru 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

ru 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations --skill ru;npx skills add dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations --skill "ru" 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

ru 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

ru 用的人多吗?

公开数据是累计安装 1,077 次,近一周安装 44 次,下载 348 次,GitHub 63 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

ru 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。

先想清楚的地方

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 不能接受 Skill 在你机器上执行命令的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
ru

茹 · 本页

1,07763执行命令MIT未通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

RU - Repo Updater

A comprehensive Bash CLI for synchronizing dozens or hundreds of GitHub repositories. Beyond basic sync, RU includes a full AI-assisted code review system and agent-sweep capability for automatically processing uncommitted changes across your entire projects directory.

Why This Exists

When you work with 47+ repos (personal projects, forks, dependencies), keeping them synchronized manually is tedious. But synchronization is just the beginning—RU also orchestrates AI coding agents to review issues, process PRs, and commit uncommitted work at scale.

The problem it solves:

  • Manual cd ~/project && git pull for each repo
  • Missing updates that accumulate into merge conflicts
  • Dirty repos that never get committed
  • Issues and PRs that pile up across repositories
  • No coordination for AI agents working across repos

Critical Concepts

Git Plumbing, Not Porcelain

RU uses git plumbing commands exclusively—never parses human-readable output:

# WRONG: Locale-dependent, version-fragile
git pull 2>&1 | grep "Already up to date"

# RIGHT: Machine-readable plumbing
git rev-list --left-right --count HEAD...@{u}
git status --porcelain
git rev-parse HEAD

Stream Separation

Human-readable output goes to stderr; data to stdout:

ru sync --json 2>/dev/null | jq '.summary'
# Progress shows in terminal, JSON pipes to jq

No Global cd

All git operations use git -C. Never changes working directory.

Essential Commands

Sync (Primary Use Case)

# Sync all configured repos
ru sync

# Parallel sync (much faster)
ru sync -j8

# Dry run - see what would happen
ru sync --dry-run

# Resume interrupted sync
ru sync --resume

# JSON output for scripting
ru sync --json 2>/dev/null | jq '.summary'

Status (Read-Only Check)

# Check all repos without modifying
ru status

# JSON output
ru status --json

Repo Management

# Initialize configuration
ru init

# Add repos to sync list
ru add owner/repo
ru add https://github.com/owner/repo
ru add owner/repo@branch as custom-name

# Remove from list
ru remove owner/repo

# List configured repos
ru list

# Detect orphaned repos (in projects dir but not in list)
ru prune           # Preview
ru prune --delete  # Actually remove
ru prune --archive # Move to archive directory

Diagnostics

ru doctor      # System health check
ru self-update # Update ru itself

AI-Assisted Review System

RU includes a powerful review orchestration system for managing AI-assisted code review across your repositories.

Two-Phase Review Workflow

Phase 1: Discovery (--plan)

  • Queries GitHub for open issues and PRs across all repos
  • Scores items by priority using label analysis and age
  • Creates isolated git worktrees for safe review
  • Spawns Claude Code sessions in terminal multiplexer

Phase 2: Application (--apply)

  • Reviews proposed changes from discovery phase
  • Runs quality gates (ShellCheck, tests, lint)
  • Optionally pushes approved changes (--push)
# Discover and plan reviews
ru review --plan

# After reviewing AI suggestions
ru review --apply --push

Priority Scoring Algorithm

FactorPointsLogic
Type0-20PRs: +20, Issues: +10, Draft PRs: -15
Labels0-50security/critical: +50, bug/urgent: +30
Age (bugs)0-50>60 days: +50, >30 days: +30
Recency0-15Updated <3 days: +15, <7 days: +10
Staleness-20Recently reviewed: -20

Priority levels: CRITICAL (≥150), HIGH (≥100), NORMAL (≥50), LOW (<50)

Session Drivers

DriverDescriptionBest For
autoAuto-detect best availableDefault
ntmNamed Tmux Manager integrationMulti-agent workflows
localDirect tmux sessionsSimple setups
ru review --mode=ntm --plan
ru review -j 4 --plan  # Parallel sessions

Cost Budgets

ru review --max-repos=10 --plan
ru review --max-runtime=30 --plan  # Minutes
ru review --skip-days=14 --plan    # Skip recently reviewed
ru review --analytics              # View past review stats

Agent Sweep (Automated Dirty Repo Processing)

The ru agent-sweep command orchestrates AI coding agents to automatically process repositories with uncommitted changes.

Basic Usage

# Process all repos with uncommitted changes
ru agent-sweep

# Dry run - preview what would be processed
ru agent-sweep --dry-run

# Process 4 repos in parallel
ru agent-sweep -j4

# Filter to specific repos
ru agent-sweep --repos="myproject*"

# Include release step after commit
ru agent-sweep --with-release

# Resume interrupted sweep
ru agent-sweep --resume

# Start fresh
ru agent-sweep --restart

Three-Phase Agent Workflow

Phase 1: Planning (--phase1-timeout, default 300s)

  • Claude Code analyzes uncommitted changes
  • Determines which files should be staged (respecting denylist)
  • Generates structured commit message

Phase 2: Commit (--phase2-timeout, default 600s)

  • Validates the plan (file existence, denylist compliance)
  • Stages approved files, creates commit
  • Runs quality gates
  • Optionally pushes to remote

Phase 3: Release (--phase3-timeout, default 300s, requires --with-release)

  • Analyzes commit history since last tag
  • Determines version bump (patch/minor/major)
  • Creates git tag and optionally GitHub release

Execution Modes

--execution-mode=agent  # Full AI-driven workflow (default)
--execution-mode=plan   # Phase 1 only: generate plan, stop
--execution-mode=apply  # Phase 2+3: execute existing plan

Preflight Checks

Each repo is validated before spawning an agent:

CheckSkip Reason
Is git repositorynot_a_git_repo
Git email configuredgit_email_not_configured
Not a shallow cloneshallow_clone
No rebase in progressrebase_in_progress
No merge in progressmerge_in_progress
Not detached HEADdetached_HEAD
Has upstream branchno_upstream_branch
Not divergeddiverged_from_upstream

Security Guardrails

File Denylist - Never committed regardless of agent output:

CategoryPatterns
Secrets.env, *.pem, *.key, id_rsa*, credentials.json
Build artifactsnode_modules, __pycache__, dist, build, target
Logs/temp*.log, *.tmp, *.swp, .DS_Store
IDE files.idea, .vscode, *.iml

Secret Scanning:

--secret-scan=none   # Disable
--secret-scan=warn   # Warn but continue (default)
--secret-scan=block  # Block push on detection

Exit Codes

CodeMeaning
0All repos processed successfully
1Some repos failed (agent error, timeout)
2Quality gate failures (secrets, tests)
3System error (ntm, tmux missing)
4Invalid arguments
5Interrupted (use --resume)

Configuration

XDG-Compliant Directory Structure

~/.config/ru/
├── config               # Main config file
└── repos.d/
    ├── public.list      # Public repos (one per line)
    └── private.list     # Private repos (gitignored)

~/.local/state/ru/
├── logs/
│   └── YYYY-MM-DD/
├── agent-sweep/
│   ├── state.json
│   └── results.ndjson
└── review/
    ├── digests/
    └── results/

Repo List Format

# ~/.config/ru/repos.d/public.list
owner/repo
another-owner/another-repo@develop
private-org/repo@main as local-name
https://github.com/owner/repo.git

Layout Modes

LayoutExample Path
flat/data/projects/repo
owner-repo/data/projects/owner_repo
full/data/projects/github.com/owner/repo
ru config --set LAYOUT=owner-repo

Per-Repo Configuration

# ~/.../your-repo/.ru-agent.yml
agent_sweep:
  enabled: true
  max_file_size: 5242880  # 5MB
  extra_context: "This is a Python project using FastAPI"
  pre_hook: "make lint"
  post_hook: "make test"
  denylist_extra:
    - "*.backup"
    - "internal/*"

ntm Integration

When ntm (Named Tmux Manager) is available, RU uses its robot mode API:

FunctionPurpose
ntm --robot-spawnCreate Claude Code session in new tmux pane
ntm --robot-sendSend prompts with chunking for long messages
ntm --robot-waitBlock until session completes with timeout
ntm --robot-activityQuery real-time session state
ntm --robot-statusGet status of all managed sessions
ntm --robot-interruptSend Ctrl+C to interrupt long operations

Output Modes

JSON Mode (--json)

ru sync --json 2>/dev/null
{
  "version": "1.2.0",
  "timestamp": "2025-01-03T14:30:00Z",
  "summary": {
    "total": 47,
    "cloned": 8,
    "updated": 34,
    "current": 3,
    "conflicts": 2
  },
  "repos": [...]
}

NDJSON Results Logging

{"repo":"mcp_agent_mail","action":"pull","status":"updated","duration":2}
{"repo":"beads_viewer","action":"clone","status":"cloned","duration":5}

jq Examples

# Get paths of all cloned repos
ru sync --json 2>/dev/null | jq -r '.repos[] | select(.action=="clone") | .path'

# Count by status
cat ~/.local/state/ru/logs/latest/results.ndjson | jq -s 'group_by(.status) | map({status: .[0].status, count: length})'

Update Strategies

ru sync                        # Default: ff-only (safest)
ru sync --rebase               # Rebase local commits
ru sync --autostash            # Auto-stash before pull
ru sync --force                # Force update (use with caution)
StrategyBehavior
ff-onlyFast-forward only; fails if diverged
rebaseRebase local commits on top of remote
mergeCreate merge commit if needed

Quality Gates

Before applying changes, RU runs automated quality gates:

Auto-detection by project type:

Project TypeTest CommandLint Command
npm/yarnnpm testnpm run lint
Cargo (Rust)cargo testcargo clippy
Gogo test./...golangci-lint run
Pythonpytestruff check
Makefilemake testmake lint
Shell scripts(none)shellcheck *.sh

Rate Limiting

RU includes an adaptive parallelism governor:

ConditionAction
GitHub remaining < 100Reduce parallelism to 1
GitHub remaining < 500Reduce parallelism by 50%
Model 429 detectedPause new sessions for 60s
Error rate > 50%Open circuit breaker

Exit Codes (Sync)

CodeMeaning
0Success - all repos synced or current
1Partial failure - some repos failed
2Conflicts exist
3Dependency error (gh missing, auth failed)
4Invalid arguments
5Interrupted (use --resume)

Environment Variables

VariableDescriptionDefault
RU_PROJECTS_DIRBase directory for repos/data/projects
RU_LAYOUTPath layoutflat
RU_PARALLELParallel workers1
RU_TIMEOUTNetwork timeout (seconds)30
RU_UPDATE_STRATEGYPull strategyff-only
GH_TOKENGitHub token(from gh CLI)

Troubleshooting

Common Issues

IssueFix
gh: command not foundbrew install gh && gh auth login
gh: auth requiredgh auth login or set GH_TOKEN
Cannot fast-forwardUse --rebase or push first
dirty working treeCommit changes or use --autostash
diverged_from_upstreamgit fetch && git rebase origin/main

Debug Mode

# View latest run log
cat ~/.local/state/ru/logs/latest/run.log

# View specific repo log
cat ~/.local/state/ru/logs/latest/repos/mcp_agent_mail.log

# Run with verbose output
ru agent-sweep --verbose --debug

Preflight Failure Debugging

# View why repos were skipped
ru agent-sweep --json 2>/dev/null | jq '.repos[] | select(.status == "skipped")'

Installation

# One-liner
curl -fsSL https://raw.githubusercontent.com/Dicklesworthstone/repo_updater/main/install.sh | bash

# Verify
ru doctor

Architecture Notes

  • ~17,700 LOC pure Bash, no external dependencies beyond git, curl, gh
  • Work-stealing queue for parallel sync with atomic dequeue
  • Portable locking via mkdir (works on all POSIX systems)
  • Path security validation prevents traversal attacks
  • Retry with exponential backoff for network operations

Integration with Flywheel

ToolIntegration
Agent MailNotify agents when repos are updated; coordinate reviews
BVTrack repo sync as recurring beads
CASSSearch past sync sessions and agent-sweep logs
NTMRobot mode API for session orchestration
DCGRU runs inside DCG sandbox protection

平台分布

Claude Code

27.52%
按下载量换算96

Gemini CLI

21.54%
按下载量换算75

OpenCode

17.52%
按下载量换算61

Antigravity

12.34%
按下载量换算43

Codex

7.1%
按下载量换算25

windsurf

3.47%
按下载量换算12

安全审计

Gen Agent Trust Hub

未通过

Socket

通过

Snyk

未通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations --skill ru;npx skills add dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations --skill "ru" 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。

继续浏览同类 Skills