tmux

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output. Use when: (1) monitoring Claude/Codex sessions running in tmux, (2) sending input to interactive terminal applications, (3) scraping output from long-running processes inside tmux, (4) navigating tmux panes/windows programmatically, or (5) checking on background work in existing sessions. NOT for: one-off shell commands (use exec_command), starting new background processes (use background_process), or non-tmux interactive processes.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

72%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sectioned command reference that is easy to execute, but it functions as an inline wall of commands with no validation checkpoints around its destructive/batch operations and fails to point at the bundled helper scripts that already exist. Workflow clarity and progressive disclosure are the weak spots.

Suggestions

Reference the existing bundle scripts from the body (e.g., a 'Helper scripts' section linking scripts/find-sessions.sh and scripts/wait-for-text.sh) so progressive disclosure is honored and the scripts are discoverable.

Add a validation/verification checkpoint before destructive actions — e.g., 'Before kill-session, confirm the target with capture-pane | tail' — to lift workflow clarity above the 3 cap.

Trim the redundant opener ('Essential for managing Claude Code sessions') and other restated basics to push conciseness toward the 5 anchor.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command examples with terse inline comments, but the opener 'Essential for managing Claude Code sessions' and a few restated basics are mild padding that could be trimmed — efficient with minor over-explanation rather than perfectly lean.	4 / 5
Actionability	Commands are copy-paste ready and cover the common cases exhaustively — list/capture/send-keys/navigation/session-management plus Claude Code prompt-approval patterns — fully executable with no pseudocode.	5 / 5
Workflow Clarity	Content is organized by task category rather than as a sequenced workflow, and destructive operations (kill-session) and batch loops (Check All Sessions Status) lack any validation/verification checkpoints, capping this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	Section headers are clear, but the 125-line body is entirely inline and the provided bundle scripts (scripts/find-sessions.sh, scripts/wait-for-text.sh) are never referenced or signaled from the body — a clear 'references present but not clearly signaled; content that should be separate is inline' match.	3 / 5
	Total	15 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A model description: third-person voice, concrete actions, an explicit numbered 'Use when' trigger clause, and a 'NOT for' boundary that sharply separates it from sibling tools. Every dimension lands at the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'sending keystrokes and scraping pane output', 'monitoring', 'sending input', 'navigating tmux panes/windows programmatically' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' ('Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output') and 'when' (a numbered 'Use when: (1)-(5)' clause), plus a 'NOT for' boundary — matching the 5 anchor exactly.	5 / 5
Trigger Term Quality	Covers natural domain terms users would say — 'tmux sessions', 'Claude/Codex sessions', 'interactive terminal applications', 'long-running processes', 'panes/windows' — comprehensively and without jargon-only language.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear tmux-only niche and explicitly distinguishes itself from exec_command and background_process via the 'NOT for' clause, yielding minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: TokenRhythm/opensquilla
Path: src/opensquilla/skills/bundled/tmux/SKILL.md
Commit: 94ac35e

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.