tmux

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

1.37x

Quality

—

Does it follow best practices?

Impact

80%

1.37x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

100%

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

A lean, highly actionable skill body built almost entirely from executable tmux commands, with clear sequencing, feedback loops via helper scripts, and one-level-deep references to real bundle files. Little to improve beyond minor redundancy in the OS-gating note.

Dimension	Reasoning	Score
Conciseness	The body is command-dense and assumes Claude's competence; it does not explain what tmux is, and nearly every line is an executable snippet or a tight bullet. Minor redundancy (OS gating restated in 'Windows / WSL') keeps it just at 3 rather than below.	3 / 3
Actionability	Quickstart and every section give copy-paste-ready bash commands with real flags, and the two helper scripts are documented with concrete option lists — fully executable, not pseudocode.	3 / 3
Workflow Clarity	The quickstart is a clearly sequenced flow (create socket dir → new session → send-keys → capture-pane → print monitor commands), and wait-for-text.sh plus the poll-for-completion loop in the agents section provide explicit feedback loops for verification.	3 / 3
Progressive Disclosure	Content is organized into well-labeled sections with one-level-deep references to real bundle files ({baseDir}/scripts/find-sessions.sh and wait-for-text.sh, both present), keeping the overview navigable and details in helper scripts.	3 / 3
	Total	12 / 12 Passed

Description

82%

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 crisp, third-person description with concrete actions and natural trigger terms, but it omits an explicit 'Use when...' clause, which caps completeness at 2. Voice is correct and conflict risk is low.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when you need an interactive TTY for a CLI that cannot run in exec background mode, or when driving interactive shells/repls via tmux.'

Consider adding a couple more natural phrasings users might say ('interactive shell', 'repl', 'drive a TTY') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Remote-control tmux sessions', 'sending keystrokes', 'scraping pane output' — matching the 3-anchor example of several specific actions.	3 / 3
Completeness	It clearly states what the skill does but lacks an explicit 'Use when...' trigger clause, so per the rubric guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	Natural terms a user would say are present — 'tmux sessions', 'interactive CLIs', 'keystrokes', 'pane output' — giving good coverage of likely phrasings.	3 / 3
Distinctiveness Conflict Risk	Narrow niche (tmux + interactive CLIs) with distinct triggers makes it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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: HKUDS/nanobot
Commit: c9c69e4

Reviewed: 1 day 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.