Token导航 LogoToken导航

Agent Skill · 研究检索

session-launcher(会话启动器)

session-launcher 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。

session-launcher 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,权限为调用外部服务;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 44,445。

总安装 915周安装 37GitHub Stars 14下载 287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:session-launcher(会话启动器)
来源仓库:https://github.com/jackspace/claudeskillz
仓库路径:skills/session-launcher
安装命令:
npx skills add https://github.com/jackspace/claudeskillz --skill session-launcher
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/jackspace/claudeskillz --skill session-launcher

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。

session-launcher 用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词、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。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。

来源仓库内路径:skills/session-launcher

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/jackspace/claudeskillz --skill session-launche…;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

    它需要调用外部服务,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

session-launcher 怎么安装?

在终端执行 npx skills add https://github.com/jackspace/claudeskillz --skill session-launcher。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

session-launcher 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。

session-launcher 需要什么权限?

权限级别是调用外部服务。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。

session-launcher 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。

session-launcher 用的人多吗?

公开数据是累计安装 915 次,近一周安装 37 次,下载 287 次,GitHub 14 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。

session-launcher 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

  • 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

  • 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
session-launcher

会话启动器 · 本页

91514调用外部服务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

Session Launcher

Purpose

Zero context loss between conversations. When a new session starts, this skill:

  1. Searches for project context files
  2. Loads memory indexes and past decisions
  3. Reads session state
  4. Creates visual dashboard with actionable links
  5. Makes you immediately productive

For SDAM users: Compensates for lack of episodic memory by externalizing all session context. For ADHD users: Eliminates "where was I?" friction - instant continuation. For dyschronometria: Shows explicit timestamps on all context.

Activation Triggers

  • User says: "hi-ai"
  • User says: "continue", "restore context", "what was I working on"
  • Start of new conversation (proactively offer)

Core Workflow

1. Search for Context Files

Check these locations in order:

# Current project context
./.context/current.json
./.context/session.json
./DECISIONS.md
./README.md

# User's memory storage
~/.claude-memories/ (Linux/macOS) or %USERPROFILE%\.claude-memories\ (Windows)index.json
~/.claude-sessions/ (Linux/macOS) or %USERPROFILE%\.claude-sessions\ (Windows)current.json
~/.claude-sessions/ (Linux/macOS) or %USERPROFILE%\.claude-sessions\ (Windows)projects/

2. Load Memory Index

Read ~/.claude-memories/ (Linux/macOS) or %USERPROFILE%\.claude-memories\ (Windows)index.json:

{
  "total_memories": N,
  "memories": [
    {
      "id": "unique-id",
      "type": "DECISION|BLOCKER|CONTEXT|PREFERENCE|PROCEDURE",
      "content": "the memory",
      "timestamp": "ISO8601",
      "tags": ["tag1", "tag2"],
      "project": "project-name"
    }
  ]
}

Extract:

  • Recent decisions (last 7 days)
  • Active blockers (status!= "resolved")
  • Project context (matching current directory)
  • User preferences

3. Identify Current Project

Determine project from:

  1. Current working directory name
  2. .context/project.txt if exists
  3. Git repository name: basename $(git rev-parse --show-toplevel 2>/dev/null)
  4. Ask user if unclear

4. Create Session Dashboard

Generate HTML file at ~/.claude-artifacts/ (Linux/macOS) or %USERPROFILE%\.claude-artifacts\ (Windows)session-dashboard-{timestamp}.html:

<!DOCTYPE html>
<html>
<head>
    <meta charset="UTF-8">
    <title>Session Restored</title>
    <style>
        body {
            font-family: monospace;
            max-width: 1200px;
            margin: 40px auto;
            padding: 20px;
            background: #1e1e1e;
            color: #d4d4d4;
        }
        .section {
            background: #252526;
            border: 1px solid #3e3e42;
            border-radius: 6px;
            padding: 20px;
            margin: 20px 0;
        }
        .section h2 {
            margin-top: 0;
            color: #4ec9b0;
            border-bottom: 1px solid #3e3e42;
            padding-bottom: 10px;
        }
        .timestamp {
            color: #858585;
            font-size: 0.9em;
        }
        .decision {
            background: #2d2d30;
            padding: 10px;
            margin: 10px 0;
            border-left: 3px solid #4ec9b0;
        }
        .blocker {
            background: #2d2d30;
            padding: 10px;
            margin: 10px 0;
            border-left: 3px solid #f48771;
        }
        .action {
            display: inline-block;
            background: #0e639c;
            color: white;
            padding: 8px 16px;
            margin: 5px;
            border-radius: 4px;
            text-decoration: none;
        }
        .metric {
            font-size: 2em;
            color: #4ec9b0;
            font-weight: bold;
        }
    </style>
</head>
<body>
    <h1>🚀 Session Restored</h1>
    <p class="timestamp">Restored at: {current_timestamp}</p>

    <div class="section">
        <h2>📁 Current Project</h2>
        <div class="metric">{project_name}</div>
        <p>Location: <code>{project_path}</code></p>
        <p>Last worked: <span class="timestamp">{last_session_time}</span></p>
    </div>

    <div class="section">
        <h2>🎯 Recent Decisions (Last 7 Days)</h2>
        {for each recent decision:}
        <div class="decision">
            <strong>{decision.content}</strong>
            <div class="timestamp">{decision.timestamp} - {relative_time}</div>
            {if decision.tags:}<p>Tags: {tags_joined}</p>{endif}
        </div>
        {endfor}
    </div>

    <div class="section">
        <h2>🚧 Active Blockers</h2>
        {for each active blocker:}
        <div class="blocker">
            <strong>{blocker.content}</strong>
            <div class="timestamp">{blocker.timestamp} - {relative_time}</div>
        </div>
        {endfor}
        {if no blockers:}<p>✅ No active blockers</p>{endif}
    </div>

    <div class="section">
        <h2>📊 Memory Stats</h2>
        <p>Total memories: <span class="metric">{total_memories}</span></p>
        <p>Decisions: {decision_count} | Blockers: {blocker_count} | Procedures: {procedure_count}</p>
    </div>

    <div class="section">
        <h2>⚡ Quick Actions</h2>
        <a href="file://~/.claude-memories/ (Linux/macOS) or %USERPROFILE%\.claude-memories\ (Windows)index.json" class="action">View All Memories</a>
        <a href="file://{project_path}" class="action">Open Project</a>
        <a href="file://~/.claude-artifacts/ (Linux/macOS) or %USERPROFILE%\.claude-artifacts\ (Windows)" class="action">View Artifacts</a>
    </div>
</body>
</html>

5. Output Summary

After creating dashboard, output to user:

🚀 Session Restored

📁 Project: {project_name}
📍 Location: {project_path}
🕐 Last worked: {relative_time}

📝 Recent Decisions ({count}):
{for each decision (max 5):}
  • {decision.content} ({relative_time})
{endfor}

🚧 Active Blockers ({count}):
{for each blocker:}
  • {blocker.content} ({relative_time})
{endfor}

💾 Memory: {total_memories} total memories loaded

📊 Dashboard: {dashboard_path}

✅ Full context restored. Ready to continue!

What would you like to work on?

Memory Integration

Reading Memories

Always check memory index for:

  • Project-specific context
  • User preferences (tech stack, coding style)
  • Past decisions affecting current work
  • Similar past problems/solutions

Time Anchoring (for Dyschronometria)

Convert all timestamps to relative format:

  • "2 hours ago"
  • "3 days ago"
  • "Last Tuesday"
  • Include ISO timestamp for precision

Context Filtering

Filter memories by:

  1. Project match: memory.project === current_project
  2. Recency: Last 30 days weighted higher
  3. Type priority: BLOCKER > DECISION > CONTEXT > PROCEDURE
  4. Relevance: Tag matching if available

Session State Management

Saving Session State

Before ending conversation (if user says "goodbye", "see you", "done for now"):

  1. Create/update ~/.claude-sessions/ (Linux/macOS) or %USERPROFILE%\.claude-sessions\ (Windows)current.json:
{
  "project": "project-name",
  "project_path": "/full/path",
  "last_active": "ISO8601_timestamp",
  "last_files": [
    "/path/to/file1.js",
    "/path/to/file2.py"
  ],
  "last_topic": "Brief description of what we were working on",
  "next_actions": [
    "Suggested next step 1",
    "Suggested next step 2"
  ]
}
  1. Update memory index with session summary:
{
  "type": "NOTE",
  "content": "Session ended: {brief_summary_of_work}",
  "timestamp": "ISO8601",
  "tags": ["session", "project-name"],
  "project": "project-name"
}

Project-Specific Sessions

For multi-project users, maintain:

~/.claude-sessions/ (Linux/macOS) or %USERPROFILE%\.claude-sessions\ (Windows)projects/
├── boostbox.json
├── toolhub.json
├── 88dimensions.json
└── mcp-stack.json

Each contains project-specific state.

Visual Dashboard Features

For Aphantasia Users

Always provide:

  • Concrete metrics (numbers, counts)
  • Visual structure (HTML dashboard)
  • Explicit links (clickable file paths)
  • Status indicators (✅ ❌ 🚧 emojis)

For ADHD Users

Dashboard must:

  • Load instantly (<2 seconds)
  • Show quick actions (immediate next steps)
  • Highlight blockers (red/urgent visual treatment)
  • Provide direct links (one-click access to files)

For SDAM Users

Dashboard must:

  • Externalize all context (no assumption of memory)
  • Show time anchors (when things happened)
  • Display decision history (what was decided)
  • Link to artifacts (proof of past work)

Error Handling

If No Context Found

👋 Hi! This looks like a fresh start.

I couldn't find existing session context, so let's establish some:

1. What project are you working on?
2. Should I create a memory index for you?
3. Would you like to start tracking decisions?

(I'll create the necessary directories and get you set up)

If Memory Index Corrupted

⚠️ Memory index appears corrupted.

Creating backup at: ~/.claude-memories/ (Linux/macOS) or %USERPROFILE%\.claude-memories\ (Windows)backups/index-{timestamp}.json
Initializing fresh index...

✅ Fresh index created. Previous memories backed up.

If Multiple Projects Detected

🤔 I found context for multiple projects:

1. BOOSTBOX (last active: 2 days ago)
2. Tool Hub (last active: 5 days ago)
3. MCP Stack (last active: 1 week ago)

Which project would you like to work on?

Integration with Other Skills

Memory Manager

  • Queries memory-manager for structured memory search
  • Defers complex memory operations to memory-manager
  • Uses memory-manager's categorization system

Context Manager

  • Works with context-manager to maintain .context/ directory
  • Reads context-manager's structured data
  • Updates session state via context-manager

Error Debugger

  • Surfaces recent blockers for error-debugger to consider
  • Checks if current error matches past error memories

Quick Reference

File Locations

  • Memory index: ~/.claude-memories/ (Linux/macOS) or %USERPROFILE%\.claude-memories\ (Windows)index.json
  • Current session: ~/.claude-sessions/ (Linux/macOS) or %USERPROFILE%\.claude-sessions\ (Windows)current.json
  • Project sessions: ~/.claude-sessions/ (Linux/macOS) or %USERPROFILE%\.claude-sessions\ (Windows)projects/{name}.json
  • Dashboards: ~/.claude-artifacts/ (Linux/macOS) or %USERPROFILE%\.claude-artifacts\ (Windows)session-dashboard-*.html

Trigger Phrases

  • "hi-ai" (primary)
  • "continue"
  • "restore context"
  • "what was I working on"
  • "where did we leave off"

Success Criteria

✅ User says "hi-ai" and is immediately productive ✅ No need to explain "what we were working on" ✅ All past decisions visible ✅ Active blockers surfaced ✅ Context restored in <2 seconds

平台分布

Claude Code

29.53%
按下载量换算85

windsurf

20.74%
按下载量换算60

OpenCode

17.97%
按下载量换算52

Codex

12.04%
按下载量换算35

Antigravity

7.58%
按下载量换算22

Gemini CLI

3.04%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

权限和风险

调用外部服务

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。

继续浏览同类 Skills