tmux

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Install with Tessl CLI

npx tessl i github:Hung-Reo/hungreo-openclaw --skill tmux

What are skills?

Review — 77%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 9 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

53%

Dispatch Tasks to AI Coding Agents

Safe TUI input dispatch

Criteria

Without context

With context

Literal flag used

100%

End-of-options separator

100%

Text and Enter are separate

37%

100%

Sleep between sends

100%

Enter as named key

100%

Capture uses -p flag

100%

Tail used on capture output

100%

Target passed to capture

100%

Target passed to send-keys

55%

100%

README documents split-send rationale

20%

100%

Without context: $0.2565 · 1m 3s · 17 turns · 22 in / 3,587 out tokens

With context: $0.3841 · 1m 14s · 26 turns · 80 in / 3,771 out tokens

100%

59%

Monitor Multi-Agent Worker Sessions

Session discovery and status monitoring

Criteria

Without context

With context

Uses find-sessions.sh

100%

Query flag used

100%

All-sockets flag used

100%

Prompt pattern includes special char

100%

Prompt pattern completeness

80%

100%

Capture-pane -p flag

100%

Shared session named

100%

Worker session naming

55%

100%

Tail on capture output

100%

Target uses -t flag

100%

Without context: $0.2101 · 1m 3s · 13 turns · 20 in / 3,808 out tokens

With context: $0.5684 · 2m 30s · 23 turns · 1,244 in / 8,969 out tokens

59%

16%

Automated Code Review Dispatcher

Automated task dispatch with completion polling

Criteria

Without context

With context

Uses wait-for-text.sh

Timeout flag passed

Target flag passed to wait

Pattern flag passed to wait

Full scrollback capture

100%

Joined lines capture

100%

Capture uses -p flag

100%

Output saved to file

100%

Literal flag on send

100%

Split send pattern

100%

Without context: $0.2028 · 52s · 13 turns · 20 in / 2,887 out tokens

With context: $0.4380 · 1m 29s · 23 turns · 272 in / 4,743 out tokens

Evaluated: about 13 hours ago
Agent: Claude Code

Table of Contents

Dispatch Tasks to AI Coding Agents Monitor Multi-Agent Worker Sessions Automated Code Review Dispatcher

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.