tmux

Control tmux sessions and panes for interactive CLIs: discover sessions, capture output, send keys, paste text, and monitor prompts.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

93%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.

The content is lean, highly actionable, and well-structured with real one-level-deep script references, losing only a point on workflow clarity for the absence of an explicit validate→fix→retry feedback loop around destructive operations.

Dimension	Reasoning	Score
Conciseness	The body is lean — it never explains what tmux is and gives only commands plus terse guardrails, so every token earns its place and it assumes Claude's competence.	5 / 5
Actionability	It provides copy-paste-ready, fully executable commands across the common cases (list/capture/send-keys/special keys/session lifecycle) plus concrete script invocations for the harder operations.	5 / 5
Workflow Clarity	There is a clear prerequisite validation checkpoint ('command -v tmux' with a no-silent-install rule) and a destructive-operation guardrail for kill-session, but there is no explicit validate→fix→retry feedback loop, leaving a minor validation gap rather than the full level-5 sequence.	4 / 5
Progressive Disclosure	The SKILL.md is a concise, well-sectioned overview that references two real one-level-deep scripts (find-sessions.sh, wait-for-text.sh) via the baseDirectory path, with complex socket/polling logic appropriately split out and clearly signaled.	5 / 5
	Total	19 / 20 Passed

Description

71%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.

The description is specific and concrete with strong action coverage and a clear niche, but it lacks an explicit 'Use when...' trigger clause, which caps completeness and leaves a small overlap risk with general terminal skills.

Suggestions

Add an explicit trigger clause such as 'Use when controlling interactive CLIs already running in tmux, or when a command needs a persistent terminal across SSH disconnects.'

Include a few natural synonyms (e.g. 'terminal multiplexer', 'split panes') to broaden the trigger-term surface users might actually say.

Clarify the boundary vs. normal terminal execution in the description itself (currently only in the body) to reduce conflict risk.

Dimension	Reasoning	Score
Specificity	The description names the domain ('tmux sessions and panes for interactive CLIs') and lists five concrete actions — 'discover sessions, capture output, send keys, paste text, and monitor prompts' — giving comprehensive coverage rather than the minor-gaps level 4.	5 / 5
Completeness	The 'what' is clearly stated, but there is no explicit 'Use when...' trigger clause — the 'for interactive CLIs' phrase only weakly implies when, so per the guideline a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	It includes natural terms a user would say ('tmux sessions', 'send keys', 'capture output', 'interactive CLIs') with good coverage, but misses common synonyms such as 'terminal multiplexer' or 'split panes' that would push it to level 5.	4 / 5
Distinctiveness Conflict Risk	tmux is a clear, narrow niche with minimal conflict risk, but without an explicit trigger clause it could still overlap slightly with general terminal/CLI execution skills, fitting 'mostly distinct; minor overlap risk'.	4 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 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

	Total	14 / 16 Passed

Repository: EKKOLearnAI/hermes-studio
Path: packages/ekko-agent/skills/tmux/SKILL.md
Commit: 07ccb17

Reviewed: 5 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.