tmux

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

1.37x

Quality

76%

Does it follow best practices?

Impact

80%

1.37x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./nanobot/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.

A tight, highly actionable skill body: every section is executable commands with a working quickstart, real helper scripts, verification helpers for waiting on output, and a thoughtful orchestration example. The only deductions are minor — slight repetition of socket/send-keys instructions, a missing explicit session-started check, and destructive cleanup without a pre-check.

Dimension	Reasoning	Score
Conciseness	The body is command-first and lean with no explanation of concepts Claude already knows (no 'what is tmux' padding). A 5 is withheld because socket setup is repeated between the Quickstart and 'Socket convention' sections and send-keys forms appear in several sections, so a few tokens could be trimmed.	4 / 5
Actionability	Every section gives copy-paste-ready, fully executable commands: the quickstart (socket setup, new session, send-keys, capture-pane), literal-send forms, capture commands, a complete orchestration loop with polling, and cleanup one-liners. It matches the 'fully executable, covers the common cases' anchor.	5 / 5
Workflow Clarity	The quickstart establishes a clear sequence (create socket dir → start session → send input → capture output), and wait-for-text.sh plus the poll-for-completion loop provide explicit verification checkpoints for the batch agent workflow. Minor gaps keep it at 4 rather than 5: no explicit 'verify the session started' step before sending input, and the destructive kill-server cleanup has no pre-check of what is running.	4 / 5
Progressive Disclosure	Sections are well organized and both referenced bundle files (scripts/find-sessions.sh, scripts/wait-for-text.sh) exist, are one level deep, and are clearly signaled with their usage documented inline. It is not a 5 because the body is a single flat file with some helper usage duplicated across sections rather than an optimally split overview-plus-references structure.	4 / 5
	Total	17 / 20 Passed

Description

70%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 concise, specific, third-person description anchored on a distinctive tool name, with concrete verbs for its core operations. Its main weakness is the missing explicit 'Use when...' trigger clause — the 'when' is only weakly implied by 'for interactive CLIs' — and slightly thin natural-language synonym coverage.

Suggestions

Add an explicit trigger clause, e.g. 'Use when you need to drive an interactive terminal, REPL, or TUI that exec/background mode cannot handle.'

Include natural synonyms users would say, such as 'terminal', 'REPL', or 'attach', to broaden trigger-term coverage.

Optionally mention session monitoring/attaching among the capabilities to round out action coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Remote-control tmux sessions') and multiple concrete actions ('sending keystrokes', 'scraping pane output', driving 'interactive CLIs'). It falls short of a 5 because coverage has minor gaps — no mention of monitoring/attaching, spawning, or cleaning up sessions.	4 / 5
Completeness	The 'what' is clear and concrete, and 'for interactive CLIs' weakly implies the 'when', but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines. It is above a 2 because the 'what' is fully explicit rather than vague.	3 / 5
Trigger Term Quality	'tmux', 'sessions', 'interactive CLIs', 'keystrokes', and 'pane output' anchor it on the exact term a user would say, giving good keyword coverage. A 5 is withheld because natural synonyms like 'terminal', 'REPL', or 'attach' are missing.	4 / 5
Distinctiveness Conflict Risk	Naming the specific tool 'tmux' with distinctive operations (keystrokes, pane output) gives it a clear niche with minimal conflict risk against any other skill.	5 / 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: HKUDS/nanobot
Path: nanobot/skills/tmux/SKILL.md
Commit: 6eccc28

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.