Загрузка видео...

Не удалось загрузить видео

На главную

When you ask Claude to run tasks in parallel, it starts a nested session for each one. Each reports its result back into your main session when it's done, so the main thread stays readable.

ClaudeDevs's profile picture

ClaudeDevs

789,118 subscribers

114,848 просмотров • 18 дней назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Claude also proactively suggests follow-up work as it's working, and you can run that as its own session with just one click. You can also use /btw, so side questions open in their own tab while the main session keeps going.
0:19

Claude also proactively suggests follow-up work as it's working, and you can run that as its own session with just one click. You can also use /btw, so side questions open in their own tab while the main session keeps going.

ClaudeDevs

127,643 просмотров • 18 дней назад

New in Claude Code: your sessions can now message each other. Instead of having to re-explain yourself in another session, you can now tell Claude to do it. It sends a summary (not your history or files), and the other session picks it up mid-task.
0:16

New in Claude Code: your sessions can now message each other. Instead of having to re-explain yourself in another session, you can now tell Claude to do it. It sends a summary (not your history or files), and the other session picks it up mid-task.

ClaudeDevs

7,985,164 просмотров • 2 месяцев назад

Claude Code can now send push notifications to your phone when a long task finishes or Claude needs your input. Walk away from the terminal, we'll let you know when it's done.
0:14

Claude Code can now send push notifications to your phone when a long task finishes or Claude needs your input. Walk away from the terminal, we'll let you know when it's done.

ClaudeDevs

1,339,781 просмотров • 6 месяцев назад

We've updated /fork in Claude Code /fork now runs a background agent with your exact context (system prompt, tools, history, model) and prompt cache. The result gets returned to your session. /branch (the old /fork) still copies the transcript to a new session you drive.
0:16

We've updated /fork in Claude Code /fork now runs a background agent with your exact context (system prompt, tools, history, model) and prompt cache. The result gets returned to your session. /branch (the old /fork) still copies the transcript to a new session you drive.

ClaudeDevs

381,676 просмотров • 5 месяцев назад

I'm calling it. Claude Code Desktop is now amazing. Especially the new '/btw' feature. Each side chat opens in its own tab, so now you can branch off without losing the main thread. I'm Claude Code Desktop-maxxing now.
0:14

I'm calling it. Claude Code Desktop is now amazing. Especially the new '/btw' feature. Each side chat opens in its own tab, so now you can branch off without losing the main thread. I'm Claude Code Desktop-maxxing now.

Dan McAteer

46,792 просмотров • 16 дней назад

Claude Code in the terminal will now show recaps when you switch focus away from the session and then come back. This should help you stay more in flow while multi-clauding.
0:10

Claude Code in the terminal will now show recaps when you switch focus away from the session and then come back. This should help you stay more in flow while multi-clauding.

ClaudeDevs

520,236 просмотров • 6 месяцев назад

Not many know about this hidden command: claude --teleport It starts a desktop claude code session SYNC'd with your web / mobile session Great when you're working on your phone -- and then want to pick up from EXACTLY where you left off when back at your PC Demo below 👇
0:12

Not many know about this hidden command: claude --teleport It starts a desktop claude code session SYNC'd with your web / mobile session Great when you're working on your phone -- and then want to pick up from EXACTLY where you left off when back at your PC Demo below 👇

Chong-U

76,786 просмотров • 10 месяцев назад

You can now resume your terminal sessions in the Claude Code desktop app. Type /resume to pick any session you started from the CLI. The session continues in the app with the full conversation and context intact.
0:10

You can now resume your terminal sessions in the Claude Code desktop app. Type /resume to pick any session you started from the CLI. The session continues in the app with the full conversation and context intact.

ClaudeDevs

655,762 просмотров • 2 месяцев назад

In Claude Projects you can now drag a thread from the side panel into the message box to point Claude at it. Typing @ works too. Usually you can just ask and Claude finds the right thread, but this is great for when you need to be exact.
0:14

In Claude Projects you can now drag a thread from the side panel into the message box to point Claude at it. Typing @ works too. Usually you can just ask and Claude finds the right thread, but this is great for when you need to be exact.

Dan Fein

17,713 просмотров • 6 дней назад

Claude Ultracode fans out a fleet of parallel agents across your task, each one checking its own findings before trusting them. Tokens are no object. You get one thorough, verified result instead of an iterative mess.
0:13

Claude Ultracode fans out a fleet of parallel agents across your task, each one checking its own findings before trusting them. Tokens are no object. You get one thorough, verified result instead of an iterative mess.

0xMarioNawfal

53,730 просмотров • 3 месяцев назад

When you get your inflatable vest, you’ll need to thread each strap like so…
0:12

Sensitive content

When you get your inflatable vest, you’ll need to thread each strap like so…

Candy Coated

13,586 просмотров • 1 год назад

Claude Code Desktop has a built-in MCP for frontend preview It activates automatically when you ask Claude to spin up a dev server Save this thread 👇
0:15

Claude Code Desktop has a built-in MCP for frontend preview It activates automatically when you ask Claude to spin up a dev server Save this thread 👇

Daniel San

79,115 просмотров • 7 месяцев назад

When Claude spots something to work on in the middle of a session, it'll suggest starting a new session to pick up the work. This is a huge part of my workflow; it makes it way easier to kick off new work. Simply ask Claude to spawn a task!
0:12

When Claude spots something to work on in the middle of a session, it'll suggest starting a new session to pick up the work. This is a huge part of my workflow; it makes it way easier to kick off new work. Simply ask Claude to spawn a task!

Anthony Morris ツ

42,654 просмотров • 2 месяцев назад

Before adding another subagent ask what problem it's solving. A bloated system prompt is often the issue. Skills and tool search can fix that without splitting context across agents. My rule of thumb is to keep a subagent when the work is parallel, needs fresh context or one agent really can't pick the right tools. Otherwise, fold it into the main loop, turn its prompt into a skill, run your evals and keep whatever wins. Good write-up:
0:11

Before adding another subagent ask what problem it's solving. A bloated system prompt is often the issue. Skills and tool search can fix that without splitting context across agents. My rule of thumb is to keep a subagent when the work is parallel, needs fresh context or one agent really can't pick the right tools. Otherwise, fold it into the main loop, turn its prompt into a skill, run your evals and keep whatever wins. Good write-up:

Addy Osmani

81,814 просмотров • 6 дней назад

You know the animation you want. You just don't know what it's called. So I built a free place to find it, learn its name, and turn it into a prompt for Claude or ChatGPT. 923 motion techniques, each with a live example.
0:15

You know the animation you want. You just don't know what it's called. So I built a free place to find it, learn its name, and turn it into a prompt for Claude or ChatGPT. 923 motion techniques, each with a live example.

Tak 🦞

65,197 просмотров • 11 дней назад

Connect Emdash to your own infrastructure and run coding agents on it. Each task provisions its own isolated workspace, streams progress in real-time, and tears down when you're done.
0:15

Connect Emdash to your own infrastructure and run coding agents on it. Each task provisions its own isolated workspace, streams progress in real-time, and tears down when you're done.

Arne Strickmann

13,303 просмотров • 6 месяцев назад

jev + sonnet 5.5 is f**king insane. my entire workflow got 4x faster after adding these 6 lines to CLAUDE.md. [with jev connected, paste this👇] 1. Before you start a Claude worker, ask Jev once to select a host-approved profile with one or two sessions. The profile must specify each session’s model and effort level. If Jev makes no selection, use the host default. 2. The host must check Jev’s selection. The host must set the model and effort before each session starts. Keep these settings fixed during the session. The host controls permissions and approvals. 3. Use Sonnet 5.5 at medium effort for clear coding tasks. Use higher effort for complex reasoning or JSON tasks. Use a second Claude only for independent research or a review that the user requested. 4. Give the second Claude the task, applicable files, limits, and completion requirements. Return its findings and evidence to the lead. 5. Complete the requested work. Ask the user only when you cannot continue without input or before an action that needs approval. Do not add features, tests, files, documentation, refactors, or review rounds that the user did not request. When the work is complete and checked, stop. Report the result. 6. Before you report completion, run a test, build, type check, or command that checks the code change. If no check can run, identify the missing check. Explain why it cannot run. same task. two timers. watch the difference.
0:18

jev + sonnet 5.5 is f**king insane. my entire workflow got 4x faster after adding these 6 lines to CLAUDE.md. [with jev connected, paste this👇] 1. Before you start a Claude worker, ask Jev once to select a host-approved profile with one or two sessions. The profile must specify each session’s model and effort level. If Jev makes no selection, use the host default. 2. The host must check Jev’s selection. The host must set the model and effort before each session starts. Keep these settings fixed during the session. The host controls permissions and approvals. 3. Use Sonnet 5.5 at medium effort for clear coding tasks. Use higher effort for complex reasoning or JSON tasks. Use a second Claude only for independent research or a review that the user requested. 4. Give the second Claude the task, applicable files, limits, and completion requirements. Return its findings and evidence to the lead. 5. Complete the requested work. Ask the user only when you cannot continue without input or before an action that needs approval. Do not add features, tests, files, documentation, refactors, or review rounds that the user did not request. When the work is complete and checked, stop. Report the result. 6. Before you report completion, run a test, build, type check, or command that checks the code change. If no check can run, identify the missing check. Explain why it cannot run. same task. two timers. watch the difference.

Avid

177,380 просмотров • 1 месяц назад

Introducing Time Machine for Claude Code Works in both Claude Desktop and Claude Code CLI /timemachine records your session as a timeline, including prompts, tool calls, edits, Bash commands, and turn endings Pick any point and fork from there, It restores both the conversation and the code state from that moment into a separate Git worktree and branch, while your original session stays untouched Install: npx claude-code-templates@latest --mod productivity/session-time-machine Then run: /reload-plugin /timemachine
0:16

Introducing Time Machine for Claude Code Works in both Claude Desktop and Claude Code CLI /timemachine records your session as a timeline, including prompts, tool calls, edits, Bash commands, and turn endings Pick any point and fork from there, It restores both the conversation and the code state from that moment into a separate Git worktree and branch, while your original session stays untouched Install: npx claude-code-templates@latest --mod productivity/session-time-machine Then run: /reload-plugin /timemachine

Daniel San

24,097 просмотров • 28 дней назад

Claude Code has an incredibly useful command to grade every skill you're running. Run /skill-doctor with the prompt below. It shows you: 1. Every skill loaded in your session 2. Which ones you've never used 3. How many tokens each one costs you Prompt I run: "run skill-doctor on my current session and grade which skills are actually earning their token cost and which are dead weight."
0:15

Claude Code has an incredibly useful command to grade every skill you're running. Run /skill-doctor with the prompt below. It shows you: 1. Every skill loaded in your session 2. Which ones you've never used 3. How many tokens each one costs you Prompt I run: "run skill-doctor on my current session and grade which skills are actually earning their token cost and which are dead weight."

Alvaro Cintas

15,631 просмотров • 1 месяц назад

SOMEONE TURNED THEIR TEAM'S TASK TRACKER INTO A 3D ISLAND instead of a boring list of tasks, your teams work is a little island that grows as you get stuff done > you assign tasks right in slack, just type who its for, the points, and the due date > finish a task and you get to place a building on the island > get your work rejected and the building collapses into rubble > the rubble stays there forever, so everyone can see it > each new sprint starts a fresh island so over time the island fills up with buildings for all the work your team actually finished, and the rubble is a reminder of what got rejected. its open source, so any team can set it up. way more fun than staring at a to do list all day
0:13

SOMEONE TURNED THEIR TEAM'S TASK TRACKER INTO A 3D ISLAND instead of a boring list of tasks, your teams work is a little island that grows as you get stuff done > you assign tasks right in slack, just type who its for, the points, and the due date > finish a task and you get to place a building on the island > get your work rejected and the building collapses into rubble > the rubble stays there forever, so everyone can see it > each new sprint starts a fresh island so over time the island fills up with buildings for all the work your team actually finished, and the rubble is a reminder of what got rejected. its open source, so any team can set it up. way more fun than staring at a to do list all day

Om Patel

12,978 просмотров • 3 месяцев назад