tmux

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

2.00x

Quality

66%

Does it follow best practices?

Impact

86%

2.00x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

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

Quality

Discovery

67%

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

The description is technically specific and occupies a clear niche, making it distinctive and unlikely to conflict with other skills. However, it lacks an explicit 'Use when...' clause, which caps completeness, and could benefit from additional natural trigger terms that users might employ when needing this functionality.

Suggestions

Add a 'Use when...' clause, e.g., 'Use when the user needs to interact with a tmux session, send commands to a running terminal, or read output from a tmux pane.'

Include additional trigger terms like 'terminal multiplexer', 'send-keys', 'capture-pane', 'terminal automation', or 'read terminal output' to improve keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'remote-control tmux sessions', 'sending keystrokes', and 'scraping pane output'. These are specific, actionable capabilities rather than vague language.	3 / 3
Completeness	Clearly answers 'what does this do' (remote-control tmux sessions by sending keystrokes and scraping output), but lacks an explicit 'Use when...' clause specifying when Claude should select this skill.	2 / 3
Trigger Term Quality	Includes good terms like 'tmux', 'keystrokes', 'pane output', and 'interactive CLIs', but misses common user variations like 'terminal multiplexer', 'send keys', 'read terminal output', 'tmux send-keys', or 'capture-pane'.	2 / 3
Distinctiveness Conflict Risk	Very distinct niche — tmux session control via keystrokes and pane scraping is highly specific and unlikely to conflict with other skills. The combination of 'tmux', 'keystrokes', and 'scraping pane output' creates a clear, unique identity.	3 / 3
	Total	10 / 12 Passed

Implementation

64%

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

This is a solid, practical skill with excellent actionability—nearly every section provides executable commands for real tmux control scenarios. The main weaknesses are some unnecessary content (basic tmux commands Claude already knows, verbose use/don't-use sections) and the lack of validation/error-handling guidance in workflows. The Claude Code-specific patterns are the most valuable and differentiated content.

Suggestions

Remove basic tmux knowledge Claude already has (session create/kill/rename, basic list commands) to improve conciseness and focus on the non-obvious patterns like safe input sending and pane scraping.

Add validation steps to workflows—e.g., after sending keys, capture output to verify the input was received; handle cases where capture-pane returns empty or the session doesn't exist.

Trim the 'When to Use' / 'When NOT to Use' sections to a brief 2-3 line summary to save tokens.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient but includes some unnecessary content. The 'When to Use' and 'When NOT to Use' sections add moderate value but are somewhat verbose. The session management section (create/kill/rename) is basic tmux knowledge Claude already knows. The Notes section at the end is lean and useful.	2 / 3
Actionability	Every section provides concrete, copy-paste ready bash commands. The examples cover real scenarios like capturing output, sending keys safely, checking session status, and approving prompts. The for-loop to check all sessions is particularly practical and executable.	3 / 3
Workflow Clarity	The 'Sending Input Safely' section shows a clear multi-step pattern with the sleep between sends, and the Claude Code patterns show practical sequences. However, there are no explicit validation checkpoints or error recovery steps—e.g., no guidance on what to do if capture-pane returns empty, or if a send-keys doesn't register.	2 / 3
Progressive Disclosure	The content is well-organized with clear headers and logical grouping, but everything is in a single file. The session management basics and some of the more advanced Claude Code patterns could be split out. For a skill of this size (~100 lines of content), it's borderline acceptable but the table of contents via headers works reasonably well.	2 / 3
	Total	9 / 12 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 — 9 / 11 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

	Total	9 / 11 Passed

Repository: qsimeon/openclaw-engaging
Commit: 4467e04

Reviewed: 7 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.