web-cli-teleport

Guide users on when to use Claude Code Web vs CLI and seamlessly teleport sessions between environments

242 stars

Best use case

web-cli-teleport is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. Guide users on when to use Claude Code Web vs CLI and seamlessly teleport sessions between environments

Guide users on when to use Claude Code Web vs CLI and seamlessly teleport sessions between environments

Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.

Practical example

Example input

Use the "web-cli-teleport" skill to help with this workflow task. Context: Guide users on when to use Claude Code Web vs CLI and seamlessly teleport sessions between environments

Example output

A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.

When to use this skill

  • Use this skill when you want a reusable workflow rather than writing the same prompt again and again.

When not to use this skill

  • Do not use this when you only need a one-off answer and do not need a reusable workflow.
  • Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/web-cli-teleport/SKILL.md --create-dirs "https://raw.githubusercontent.com/aiskillstore/marketplace/main/skills/dnyoussef/web-cli-teleport/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/web-cli-teleport/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How web-cli-teleport Compares

Feature / Agentweb-cli-teleportStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Guide users on when to use Claude Code Web vs CLI and seamlessly teleport sessions between environments

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Web-CLI Teleport Guide

## Purpose
Help users choose the optimal Claude Code interface (Web vs CLI) and seamlessly teleport sessions between environments for maximum productivity.

## Specialist Agent

I am a workflow optimization specialist with expertise in:
- Claude Code Web and CLI capabilities and limitations
- Session state management and teleportation
- Task complexity analysis and interface selection
- Context window optimization for different interfaces
- Mobile and desktop workflow integration

### Methodology (Program-of-Thought Pattern)

1. **Analyze Task Characteristics**: Determine complexity, iteration needs, back-and-forth
2. **Recommend Interface**: Choose Web, CLI, or hybrid approach
3. **Set Up Session**: Initialize in optimal environment
4. **Monitor Progress**: Track if interface switch needed
5. **Facilitate Teleport**: Guide seamless session handoff when beneficial

### Decision Matrix: Web vs CLI

**Use Claude Code Web When**:
- ✅ Well-defined, one-off tasks (1-3 interactions expected)
- ✅ Simple changes: translations, styling, config updates
- ✅ Away from development machine (mobile, other computer)
- ✅ Want to review/approve before applying locally
- ✅ Collaborative review needed before merging
- ✅ Quick fixes during meetings or on-the-go
- ✅ Creating PRs without local checkout

**Use Claude Code CLI When**:
- ✅ Complex, iterative development (5+ interactions)
- ✅ Debugging requiring multiple attempts
- ✅ Large refactoring across multiple files
- ✅ Need inline diffs and VS Code integration
- ✅ Local testing and running required
- ✅ Working with local databases or services
- ✅ Need full file tree visibility and exploration

**Hybrid Approach (Start Web, Teleport to CLI)**:
- ✅ Initial exploration and planning on mobile
- ✅ Review progress on web, continue implementation locally
- ✅ Quick start on web, complex debugging on CLI
- ✅ Collaborative approval on web, local refinement on CLI

### Web Capabilities

**Strengths**:
- No local setup required
- Works on iOS app (not Android yet)
- GitHub integration for PRs
- Notifications when tasks complete
- Sandboxed cloud execution
- Quick context switching between repositories

**Limitations**:
- Cannot see inline diffs (only final PR diffs)
- Less interactive file exploration
- Limited terminal access
- No local service integration
- Fixed network isolation policies

### CLI Capabilities

**Strengths**:
- Full file system access and exploration
- Inline diffs for every change
- VS Code integration
- Local testing and debugging
- Custom sandbox configuration
- Background task monitoring
- Full terminal control

**Limitations**:
- Requires local setup
- Desktop/laptop only
- More permission prompts without sandbox
- Context switches cost more

### Teleport Protocol

**From Web to CLI**:
1. Complete task on web or reach handoff point
2. Click "Open in CLI" button
3. Copy teleport command: `claude --teleport <session-id>`
4. Ensure clean git working directory locally
5. Run teleport command in local terminal
6. Full session history loaded (~50% context window)
7. Continue work with full CLI capabilities

**Benefits of Teleporting**:
- Preserves entire conversation history
- Maintains context and decisions
- No need to repeat requirements
- Seamless continuation of work
- Can switch back to web for final PR review

**Best Practices**:
- Start small tasks on web for quick wins
- Teleport when complexity increases
- Use web for final PR review and approval
- Clean git state before teleporting
- Verify context loaded correctly (check context %)

### Workflow Patterns

**Pattern 1: Mobile Planning → Desktop Implementation**:
```
[Mobile/Web] Define requirements and initial approach
[Mobile/Web] Let Claude Code explore and plan
[Teleport] Continue on desktop CLI
[CLI] Implement with full tooling
[CLI] Test and debug locally
[Web] Create PR and review
```

**Pattern 2: Quick Fix Anywhere**:
```
[Web] Make simple change (translation, config, style)
[Web] Review diff in PR
[Web] Merge if good OR teleport if issues found
```

**Pattern 3: Complex Feature with Reviews**:
```
[CLI] Initial implementation and testing
[CLI] Create PR when ready
[Web/Mobile] Review PR on the go
[Teleport if needed] Make revisions on desktop
[Web] Final approval and merge
```

## Input Contract

```yaml
task_description: string
task_complexity: simple | moderate | complex
iteration_expected: low | medium | high
current_location: desktop | mobile | away
has_local_environment: boolean
needs_testing: boolean
needs_debugging: boolean
```

## Output Contract

```yaml
recommendation:
  interface: web | cli | hybrid
  reasoning: string
  workflow: array[steps]
  teleport_points: array[string] (when to switch interfaces)

setup_instructions:
  web_url: string (if web recommended)
  cli_commands: array[string] (if CLI recommended)
  teleport_command: string (if hybrid)

optimization_tips:
  time_savings: string
  context_preservation: string
  best_practices: array[string]
```

## Integration Points

- **Cascades**: Pre-step for task planning workflows
- **Commands**: `/web-or-cli`, `/teleport-session`
- **Other Skills**: Works with interactive-planner, task-orchestrator

## Usage Examples

**Quick Decision**:
```
I need to translate the landing page to Japanese. Should I use web or CLI?
```

**Complex Task Planning**:
```
Use web-cli-teleport skill to plan approach for implementing new authentication system with OAuth2
```

**Mid-Task Switch**:
```
I started this on Claude Code Web but it's getting complex. Help me teleport to CLI and continue.
```

## Common Scenarios

**Scenario 1: On Mobile, Need Quick Fix**:
- Recommendation: Use Web
- Create PR directly from web
- Review and merge on mobile

**Scenario 2: Complex Refactoring**:
- Recommendation: Use CLI
- Need inline diffs and local testing
- Multiple iterations expected

**Scenario 3: Started Simple, Got Complex**:
- Started on Web for "simple" task
- Discovered complexity during implementation
- Teleport to CLI with full context
- Complete complex parts locally
- Return to web for PR review

**Scenario 4: Team Collaboration**:
- Use Web for initial work
- Create PR for team review
- Teammates review on web
- Teleport to CLI if changes needed
- Push updates to PR

## Failure Modes & Mitigations

- **Dirty git state blocks teleport**: Stash or commit local changes first
- **Context too large to teleport**: Start fresh, reference PR for context
- **Web limitations discovered mid-task**: Teleport immediately, don't struggle
- **Mobile notifications not working**: Enable in iOS app settings
- **PR diffs not showing**: Refresh page or open PR directly on GitHub

## Validation Checklist

- [ ] Task complexity accurately assessed
- [ ] Interface recommendation matches task needs
- [ ] Teleport points clearly identified
- [ ] User knows how to switch interfaces
- [ ] Git state prepared for teleporting
- [ ] Notifications configured if needed
- [ ] Context preservation verified

## Neural Training Integration

```yaml
training:
  pattern: adaptive
  feedback_collection: true
  success_metrics:
    - task_completion_time
    - interface_switches_needed
    - user_satisfaction
    - context_preservation_quality
```

---

**Quick Commands**:
- Web: Go to claude.ai/code
- Teleport: `claude --teleport <session-id>`
- Check context: Look for context % after teleporting

**Pro Tips**:
- Use web for first pass, CLI for refinement
- Mobile great for planning during commute
- Always clean git state before teleporting
- Context window shows how much history loaded

Related Skills

when-bridging-web-cli-use-web-cli-teleport

240
from aiskillstore/marketplace

Bridge web interfaces with CLI workflows for seamless bidirectional integration

azure-quotas

242
from aiskillstore/marketplace

Check/manage Azure quotas and usage across providers. For deployment planning, capacity validation, region selection. WHEN: "check quotas", "service limits", "current usage", "request quota increase", "quota exceeded", "validate capacity", "regional availability", "provisioning limits", "vCPU limit", "how many vCPUs available in my subscription".

DevOps & Infrastructure

raindrop-io

242
from aiskillstore/marketplace

Manage Raindrop.io bookmarks with AI assistance. Save and organize bookmarks, search your collection, manage reading lists, and organize research materials. Use when working with bookmarks, web research, reading lists, or when user mentions Raindrop.io.

Data & Research

zlibrary-to-notebooklm

242
from aiskillstore/marketplace

自动从 Z-Library 下载书籍并上传到 Google NotebookLM。支持 PDF/EPUB 格式,自动转换,一键创建知识库。

discover-skills

242
from aiskillstore/marketplace

当你发现当前可用的技能都不够合适(或用户明确要求你寻找技能)时使用。本技能会基于任务目标和约束,给出一份精简的候选技能清单,帮助你选出最适配当前任务的技能。

web-performance-seo

242
from aiskillstore/marketplace

Fix PageSpeed Insights/Lighthouse accessibility "!" errors caused by contrast audit failures (CSS filters, OKLCH/OKLAB, low opacity, gradient text, image backgrounds). Use for accessibility-driven SEO/performance debugging and remediation.

project-to-obsidian

242
from aiskillstore/marketplace

将代码项目转换为 Obsidian 知识库。当用户提到 obsidian、项目文档、知识库、分析项目、转换项目 时激活。 【激活后必须执行】: 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入规则(默认到 00_Inbox/AI/、追加式、统一 Schema) 3. 执行 STEP 0: 使用 AskUserQuestion 询问用户确认 4. 用户确认后才开始 STEP 1 项目扫描 5. 严格按 STEP 0 → 1 → 2 → 3 → 4 顺序执行 【禁止行为】: - 禁止不读 SKILL.md 就开始分析项目 - 禁止跳过 STEP 0 用户确认 - 禁止直接在 30_Resources 创建(先到 00_Inbox/AI/) - 禁止自作主张决定输出位置

obsidian-helper

242
from aiskillstore/marketplace

Obsidian 智能笔记助手。当用户提到 obsidian、日记、笔记、知识库、capture、review 时激活。 【激活后必须执行】: 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入三条硬规矩(00_Inbox/AI/、追加式、白名单字段) 3. 按 STEP 0 → STEP 1 → ... 顺序执行 4. 不要跳过任何步骤,不要自作主张 【禁止行为】: - 禁止不读 SKILL.md 就开始工作 - 禁止跳过用户确认步骤 - 禁止在非 00_Inbox/AI/ 位置创建新笔记(除非用户明确指定)

internationalizing-websites

242
from aiskillstore/marketplace

Adds multi-language support to Next.js websites with proper SEO configuration including hreflang tags, localized sitemaps, and language-specific content. Use when adding new languages, setting up i18n, optimizing for international SEO, or when user mentions localization, translation, multi-language, or specific languages like Japanese, Korean, Chinese.

google-official-seo-guide

242
from aiskillstore/marketplace

Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation

github-release-assistant

242
from aiskillstore/marketplace

Generate bilingual GitHub release documentation (README.md + README.zh.md) from repo metadata and user input, and guide release prep with git add/commit/push. Use when the user asks to write or polish README files, create bilingual docs, prepare a GitHub release, or mentions release assistant/README generation.

doc-sync-tool

242
from aiskillstore/marketplace

自动同步项目中的 Agents.md、claude.md 和 gemini.md 文件,保持内容一致性。支持自动监听和手动触发。