CtrlK
BlogDocsLog inGet started
Tessl Logo

tmux

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

74

2.00x
Quality

66%

Does it follow best practices?

Impact

86%

2.00x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/tmux/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

53%

Dispatch Tasks to AI Coding Agents

Safe TUI input dispatch

Criteria
Without context
With context

Literal flag used

0%

100%

End-of-options separator

0%

100%

Text and Enter are separate

37%

100%

Sleep between sends

0%

100%

Enter as named key

100%

100%

Capture uses -p flag

100%

100%

Tail used on capture output

100%

100%

Target passed to capture

100%

100%

Target passed to send-keys

55%

100%

README documents split-send rationale

20%

100%

100%

59%

Monitor Multi-Agent Worker Sessions

Session discovery and status monitoring

Criteria
Without context
With context

Uses find-sessions.sh

0%

100%

Query flag used

0%

100%

All-sockets flag used

0%

100%

Prompt pattern includes special char

0%

100%

Prompt pattern completeness

80%

100%

Capture-pane -p flag

100%

100%

Shared session named

0%

100%

Worker session naming

55%

100%

Tail on capture output

100%

100%

Target uses -t flag

100%

100%

59%

16%

Automated Code Review Dispatcher

Automated task dispatch with completion polling

Criteria
Without context
With context

Uses wait-for-text.sh

0%

0%

Timeout flag passed

0%

0%

Target flag passed to wait

0%

0%

Pattern flag passed to wait

0%

0%

Full scrollback capture

100%

100%

Joined lines capture

100%

100%

Capture uses -p flag

100%

100%

Output saved to file

100%

100%

Literal flag on send

0%

100%

Split send pattern

0%

100%

Repository
qsimeon/openclaw-engaging
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

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.