tmux

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

Quality

66%

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

75%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 a lean, highly executable operating manual with real, verified helper scripts and effective feedback loops for interactive workflows. Its weaknesses are minor: a broken variable assignment in the quickstart, duplicated socket/send-key guidance, and slightly uneven helper documentation.

Dimension	Reasoning	Score
Conciseness	The body is command-first and assumes tmux knowledge ('Prefer literal sends', target format conventions) with no padding or basic-concept explanations. It is not a 5 because socket setup and the split-text-and-Enter guidance each appear twice with slightly different conventions (BITTERBOT_TMUX_SOCKET_DIR default vs. ${TMPDIR}/codex-army.sock).	4 / 5
Actionability	Nearly everything is copy-paste-ready and covers the common cases: quickstart, monitoring, multi-agent orchestration, cleanup, and verified script flags for find-sessions.sh (-S/--all) and wait-for-text.sh (-t/-p/-F/-T/-i/-l). It falls short of 5 because the quickstart contains 'SESSION.bitterbot-python', which is not valid shell and would fail on first use.	4 / 5
Workflow Clarity	Sequences are clear (create socket dir, start session, send input, capture/monitor, cleanup) and feedback loops exist via wait-for-text.sh and the prompt-poll loop in the batch orchestration example. It is not a 5 because some checkpoints are implicit — e.g., there is no explicit 'verify the session started' step after 'tmux new -d'.	4 / 5
Progressive Disclosure	Both bundle references ({baseDir}/scripts/find-sessions.sh and wait-for-text.sh) are real files, one level deep, and clearly signaled with documented usage. It is not a 5 because wait-for-text.sh flags are documented in a separate trailing section duplicating the earlier mention, and find-sessions.sh's own options are not surfaced, leaving minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

57%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 concise, accurate, and highly distinctive thanks to the 'tmux' keyword, but it lists only two actions and entirely lacks a 'Use when...' trigger clause. Adding explicit usage triggers and one or two more capabilities (session monitoring, parallel agent orchestration) would raise it substantially.

Suggestions

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

Mention additional concrete capabilities such as waiting for pane output, monitoring sessions, and running multiple coding agents in parallel.

Include natural synonyms users would say, such as 'terminal', 'TTY', or 'attach to a session', to broaden trigger coverage without adding fluff.

Dimension	Reasoning	Score
Specificity	Names the domain ('tmux sessions for interactive CLIs') and exactly two concrete actions ('sending keystrokes and scraping pane output'), matching the 1-2-concrete-actions anchor. It is not a 4 because capabilities like session setup, monitoring, or cleanup are absent from the description.	3 / 5
Completeness	The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance — the 'when' is only weakly implied by 'for interactive CLIs'. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3.	3 / 5
Trigger Term Quality	'tmux', 'interactive CLIs', and 'keystrokes' are relevant keywords a user might say, but common natural variations like 'terminal', 'TTY', or 'background process' are missing. It is above a 2 because 'tmux' alone is a strong, specific natural keyword rather than generic filler.	3 / 5
Distinctiveness Conflict Risk	'Remote-control tmux sessions' carves out a clear niche with a distinct trigger term (tmux) plus specific mechanics (keystrokes, pane output), giving minimal overlap risk with other skills. It clearly matches the 'clear niche with distinct triggers' anchor rather than the minor-overlap anchor at 4.	5 / 5
	Total	14 / 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: 1c7dc1b

Reviewed: 20 hours 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.