tmux

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

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/tmux/SKILL.md

Quality

Content

82%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 body is well-structured, highly actionable, and concise, providing executable commands for the full tmux workflow with real helper scripts. Its main gaps are minor: a lack of explicit validation/confirm loops before destructive cleanup operations and a small amount of inlined helper detail.

Dimension	Reasoning	Score
Conciseness	The body is efficient and actionable with no padding about concepts Claude already knows; minor explanatory prose in 'Sending input safely' and the Tips list could be trimmed, keeping it just below the fully-lean anchor.	4 / 5
Actionability	Commands are fully executable and copy-paste ready throughout (quickstart, send-keys, capture-pane, polling loop, cleanup), covering the common cases with specific flags and real helper scripts.	5 / 5
Workflow Clarity	A clear create→start→send→capture→cleanup sequence exists with checkpoints ('always print monitor commands', wait-for-text polling); it is not 5 because destructive ops like kill-server lack an explicit validate/confirm feedback loop.	4 / 5
Progressive Disclosure	Content is organized into clear overview sections with one-level-deep, real references to scripts/find-sessions.sh and scripts/wait-for-text.sh; not 5 because the wait-for-text flag reference is inlined rather than split out.	4 / 5
	Total	17 / 20 Passed

Description

53%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 concrete and specific about what the skill does but omits any 'when to use it' trigger guidance, which limits its completeness and trigger-term quality. It is clearly distinguishable from other skills and names real actions rather than vague fluff.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g. 'Use when you need to drive an interactive CLI/TUI, send keystrokes to a tmux session, or scrape pane output').

Include natural synonyms users would say ('control a terminal', 'drive a CLI', 'send keys to tmux') alongside the technical terms to broaden trigger coverage.

Optionally name a second concrete action (e.g. attaching, polling for output) to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (tmux sessions, interactive CLIs) and two concrete actions ('sending keystrokes', 'scraping pane output'), matching the domain-plus-1-2-actions anchor; it is not a 4 because no broader action coverage is listed.	3 / 5
Completeness	It clearly states what the skill does but lacks any 'Use when...' trigger clause, which per the rubric caps completeness at 3; not a 2 because the 'what' is concrete rather than vague.	3 / 5
Trigger Term Quality	Relevant technical terms ('tmux sessions', 'interactive CLIs', 'keystrokes', 'pane output') are present but natural user-facing synonyms or variations are missing, so it sits at the some-keywords anchor rather than good coverage.	3 / 5
Distinctiveness Conflict Risk	The niche of remote-controlling tmux sessions for interactive CLIs is mostly distinct with only minor overlap risk; not a 5 because the trigger phrasing does not reinforce as narrow a niche as the top anchor.	4 / 5
	Total	13 / 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: Bitterbot-AI/bitterbot-desktop
Path: skills/tmux/SKILL.md
Commit: 017761f

Reviewed: 2 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.