Token导航 LogoToken导航

Agent Skill · 研究检索

smart-reopen-detector(智能重新打开探测器)

smart-reopen-detector 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。

smart-reopen-detector 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,权限为接触敏感数据;许可证为 MIT,暂无第三方扫描结果,按安装量在研究检索类的 73,675 个 Skill 里排第 58,786。

总安装 404周安装 17GitHub Stars 127下载 141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:smart-reopen-detector(智能重新打开探测器)
来源仓库:https://github.com/anton-abyzov/specweave
仓库路径:skills/smart-reopen-detector
安装命令:
npx skills add https://github.com/anton-abyzov/specweave --skill smart-reopen-detector
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/anton-abyzov/specweave --skill smart-reopen-detector

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。

smart-reopen-detector 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。适用于根据关键词或任务场景筛选候选结果的研究检索场景。通过 npx skills add 命令从指定 GitHub 仓库安装并使用。

安装前需确认权限范围和维护状态,注意可能触发联网或文件访问。建议结合原始 README 了解具体搜索范围和输出格式。

来源仓库内路径:skills/smart-reopen-detector

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/anton-abyzov/specweave --skill smart-reopen-de…;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

    它需要接触敏感数据,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

smart-reopen-detector 怎么安装?

在终端执行 npx skills add https://github.com/anton-abyzov/specweave --skill smart-reopen-detector。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

smart-reopen-detector 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。

smart-reopen-detector 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

smart-reopen-detector 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。

smart-reopen-detector 用的人多吗?

公开数据是累计安装 404 次,近一周安装 17 次,下载 141 次,GitHub 127 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。

smart-reopen-detector 安全吗?

没有查到第三方扫描结果,安全性无法从公开资料判断,安装前请自行审查源码、依赖和命令行为。

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

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 没有第三方扫描结果,安全性只能靠自己读源码判断。
  • 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

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 要求有安全扫描结论才肯安装的团队。
  • 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
smart-reopen-detector

智能重新打开探测器 · 本页

404127接触敏感数据MIT未收录

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

Smart Reopen Detector

Purpose

When you report an issue with recently completed work, I'll automatically:

  1. 🔍 Scan your recent work (active + completed in last 7 days)
  2. 🎯 Identify related items using keyword matching
  3. 💡 Suggest what to reopen with relevance scoring
  4. ⚠️ Check WIP limits before suggesting reopen

When I Activate

I automatically activate when you mention these keywords:

  • Not working: "not working", "broken", "failing", "error", "crash"
  • Quality issues: "bug", "issue", "problem", "wrong", "incorrect", "missing"
  • Regressions: "still broken", "regression", "broken again", "came back"

How I Help

Example 1: Issue Report

User: "The GitHub sync isn't working, it was just completed yesterday"

I'll respond with:

🔍 Scanning recent work...

Found 2 related item(s) in recent work:

📦 INCREMENT: 0031-external-tool-status-sync
   Increment: 0031-external-tool-status-sync
   Completed: 2 days ago
   Relevance: 15 points
   Matched: github, sync

✓ TASK: T-003 GitHub Content Sync
   Increment: 0031-external-tool-status-sync
   Completed: 1 day ago
   Relevance: 14 points
   Matched: github, sync

💡 Suggested action:
   /sw:reopen 0031-external-tool-status-sync --reason "GitHub sync not working"

Would you like me to:
1. Reopen the entire increment (checks WIP limits)
2. Reopen just task T-003 (targeted fix)
3. Show me the WIP status first

Example 2: Specific Feature Broken

User: "The authentication is broken after the recent deployment"

I'll respond with:

🔍 Scanning recent work...

Found 3 related item(s) in recent work:

✓ TASK: T-012 Authentication Service
   Increment: 0025-user-auth
   Completed: 3 days ago
   Relevance: 10 points
   Matched: authentication

✓ TASK: T-014 JWT Token Validation
   Increment: 0025-user-auth
   Completed: 3 days ago
   Relevance: 7 points
   Matched: authentication

💡 Suggested action:
   /sw:reopen 0025-user-auth --task T-012 --reason "Authentication broken after deployment"

⚠️  Note: Increment 0025 was completed 3 days ago. Consider checking deployment config first.

Example 3: No Recent Work Found

User: "The payment flow is not working"

I'll respond with:

🔍 Scanning recent work...

🔍 No related work found in recent activity (last 7 days)

The payment functionality might be:
1. From an older increment (>7 days ago)
2. Not yet implemented
3. Part of external dependencies

Would you like me to:
1. Search all increments (not just recent)
2. Create a new bug increment for investigation
3. Check the backlog for related work

What I Do

Step 1: Extract Keywords

From your message, I extract relevant keywords:

  • Feature names (authentication, github, payment)
  • Action words (sync, deploy, validate)
  • Component names (api, database, frontend)

Step 2: Scan Recent Work

I scan:

  • ✅ Active increments (currently being worked on)
  • ✅ Recently completed (last 7 days)
  • ✅ All tasks from these increments

Step 3: Score Matches

I assign relevance scores using:

  • +10 points: Exact match in title/ID
  • +7 points: Partial match in title
  • +5 points: Match in increment ID
  • +3 points: Match in description/AC

Step 4: Suggest Actions

I provide:

  • Top matches (up to 5)
  • Relevance scores
  • Suggested /sw:reopen command
  • WIP limit warnings (if applicable)

Smart Suggestions

For Increments

# Reopen entire increment
/sw:reopen 0031-external-tool-status-sync --reason "GitHub sync failing"

# Check WIP limits first (recommended)
/sw:status

For Specific Tasks

# Reopen single task (surgical fix)
/sw:reopen 0031 --task T-003 --reason "GitHub API 500 error"

# Reopen multiple related tasks
/sw:reopen 0031 --user-story US-001 --reason "All GitHub features broken"

Force Reopen (Bypass WIP Limits)

# Use --force for critical production issues
/sw:reopen 0031 --force --reason "Production down, critical fix needed"

WIP Limit Awareness

Before suggesting increment reopen, I check:

  • ✅ Current active increment count
  • ✅ Type-specific limits (feature: 2, refactor: 1, etc.)
  • ⚠️ Warn if reopening will exceed limits

Example Warning:

⚠️  WIP LIMIT WARNING:
   Current active: 2 features
   Limit: 2 features
   Reopening 0031-external-tool-status-sync will EXCEED the limit!

   Options:
   1. Pause another feature first: /sw:pause 0030
   2. Complete another feature: /sw:done 0029
   3. Force reopen (not recommended): --force

Integration with Commands

I work seamlessly with:

  • /sw:reopen - Execute reopen action
  • /sw:status - Check WIP limits
  • /sw:progress - See increment progress
  • /sw:pause - Pause another increment to make room

When NOT to Use

I don't activate for:

  • ❌ General questions about code
  • ❌ Feature requests (use /sw:increment)
  • ❌ Documentation questions
  • ❌ Status inquiries (use /sw:status)

I only activate when you explicitly report something is broken/not working.

Technical Implementation

Core Logic:

  • Uses RecentWorkScanner to find matches
  • Keyword extraction from user message
  • Relevance scoring algorithm
  • WIP limit validation before suggestions

Smart Features:

  • Deduplication (same increment from active + recent)
  • Recency bias (prefer more recent completions)
  • Contextual hints (deployment, config, dependencies)

Examples of Activation

✅ Will Activate

  • "GitHub sync not working"
  • "Authentication is broken"
  • "Tests are failing after the last commit"
  • "Deployment crashed"
  • "API returns 500 error"
  • "Still broken after the fix"

❌ Won't Activate

  • "How does GitHub sync work?"
  • "Can you add authentication?"
  • "What's the status of increment 0031?"
  • "Show me the progress"
  • "Create a new feature for payments"

Success Metrics

I'm successful when:

  • ✅ You find the related work quickly (<30 seconds)
  • ✅ The suggested reopen command is correct
  • ✅ No false positives (only relevant matches)
  • ✅ WIP limits are respected
  • ✅ Clear next steps provided

Auto-loads when: You report issues with recently completed work Commands: /sw:reopen, /sw:status Related Skills: increment-planner, tdd-workflow

Project-Specific Learnings

Before starting work, check for project-specific learnings:

# Check if skill memory exists for this skill
cat .specweave/skill-memories/smart-reopen-detector.md 2>/dev/null || echo "No project learnings yet"

Project learnings are automatically captured by the reflection system when corrections or patterns are identified during development. These learnings help you understand project-specific conventions and past decisions.

平台分布

Claude Code

28.95%
按下载量换算41

Antigravity

26.41%
按下载量换算37

Cursor

17%
按下载量换算24

Gemini CLI

13.06%
按下载量换算18

OpenCode

7.27%
按下载量换算10

Codex

3.53%
按下载量换算5

安全审计

暂无安全审计结果可展示。

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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。

继续浏览同类 Skills