tmux

Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output.

Quality

76%

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.

A highly actionable, well-structured skill body with copy-paste commands and real helper scripts, sequenced clearly with polling checkpoints. Minor gains are available by trimming emphatic redundancy and moving the inlined script flag listing to the script file or a reference.

Suggestions

Consolidate the repeated monitor-command guidance into one stated rule plus one example to reduce emphatic redundancy.

Move the full wait-for-text.sh flag listing out of the body (reference the script's --help or a reference file) to keep SKILL.md a lean overview.

Add an explicit validate-and-retry loop (e.g. on prompt-timeout: inspect stderr capture, adjust, re-poll) to push workflow clarity toward 5.

Dimension	Reasoning	Score
Conciseness	Mostly lean and command-driven with short bullets, assuming Claude's tmux competence. Not a 5 due to repeated emphatic prose ('ALWAYS', 'must ALWAYS be printed') and a duplicated monitor-command block that could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste-ready tmux commands in the quickstart and per-tool recipes (Python REPL, gdb, other TTY apps), plus documented helper scripts (find-sessions.sh, wait-for-text.sh) with real flag listings covering common cases.	5 / 5
Workflow Clarity	Clear sequence (start session, send input, poll for prompt, capture output, cleanup) with prompt-polling checkpoints via wait-for-text.sh. Not a 5 because there is no explicit error-recovery/feedback loop beyond the script's stderr dump on failure.	4 / 5
Progressive Disclosure	Well-sectioned single SKILL.md with one-level-deep references to real scripts (./scripts/find-sessions.sh, ./scripts/wait-for-text.sh, both present). Not a 5 because the full wait-for-text.sh flag listing is inlined rather than referenced, slightly bloating the overview.	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 specific, well-targeted description with concrete actions and low conflict risk, but it lacks any explicit 'Use when...' trigger guidance, which caps its completeness. Adding a trigger clause would meaningfully raise the score.

Suggestions

Append an explicit trigger clause, e.g. 'Use when driving interactive CLIs (python, gdb, ipdb, psql) inside tmux, or when you need to send keystrokes and read pane output programmatically.'

Consider mentioning monitoring/control-key capabilities to broaden action coverage toward a 5 on specificity.

Dimension	Reasoning	Score
Specificity	Names the domain (tmux sessions for interactive CLIs) and several concrete actions ('sending keystrokes', 'scraping pane output') plus named CLIs (python, gdb), with only minor coverage gaps. Not a 5 because it omits monitoring/control-key actions and is a single terse sentence.	4 / 5
Completeness	Clearly states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. The 'when' is only weakly implied by the domain naming.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('tmux sessions', 'interactive CLIs', 'python, gdb', 'keystrokes', 'pane output'). Not a 5 because synonyms like 'terminal' or 'multiplexer' phrasings a user might say are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (remote-controlling interactive CLI sessions via tmux keystrokes/pane scraping) with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mitsuhiko/agent-stuff
Path: skills/tmux/SKILL.md
Commit: 13bc8f8

Reviewed: 9 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.