tmux

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

Quality

77%

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

87%

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 that uses real bundle scripts for progressive disclosure; its main gap is the absence of explicit inline validation/safety checkpoints in the core and destructive workflows.

Suggestions

Add an explicit verification checkpoint to the quickstart, e.g. after send-keys run wait-for-text.sh (or capture-pane) to confirm the prompt/expected output appeared before proceeding.

Precede destructive cleanup (kill-session / kill-server) with a brief confirm-by-listing step such as list-sessions and a guard against killing unintended sessions.

Make the wait-for-text feedback loop part of the stated workflow rather than only documenting it as a standalone helper.

Dimension	Reasoning	Score
Conciseness	The body is dense with executable tmux commands and minimal prose; explanations that exist (e.g. PYTHON_BASIC_REPL breaking send-keys, split text+Enter timing) are non-obvious gotchas rather than concepts Claude already knows, so tokens earn their place.	3 / 3
Actionability	Commands are concrete and copy-paste ready throughout (socket setup, send-keys -l, capture-pane, kill-session), with real flag combinations and worked multi-agent examples rather than pseudocode.	3 / 3
Workflow Clarity	Sequences are present (quickstart, orchestration) and verification tooling exists (wait-for-text.sh, capture-pane polling for the prompt), but the primary quickstart does not embed an explicit validate-then-proceed checkpoint and the destructive cleanup (kill-server) has no safety/verification step, which caps this at 2.	2 / 3
Progressive Disclosure	Content is organized into clear sections with helper logic split into real one-level-deep bundle scripts referenced via {baseDir}/scripts/find-sessions.sh and wait-for-text.sh (both present), keeping the overview lean while signaling where detail lives.	3 / 3
	Total	11 / 12 Passed

Description

67%

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, distinctive description with concrete actions, but it omits an explicit when-to-use trigger clause, which caps completeness and slightly limits natural trigger-term coverage.

Suggestions

Add an explicit 'Use when ...' clause naming trigger situations, e.g. 'Use when you need to drive an interactive TTY/CLI (REPLs, TUI apps) that cannot run in exec background mode.'

Broaden natural trigger terms to include everyday phrasings like 'terminal', 'TTY', or 'interactive shell' so users' requests match more directly.

Keep the concrete actions but tie them to the trigger context so the what and when are both explicit in one sentence.

Dimension	Reasoning	Score
Specificity	Names the domain ("tmux sessions for interactive CLIs") and multiple concrete actions ("sending keystrokes and scraping pane output"), matching the anchor for listing several specific concrete actions rather than just naming a domain.	3 / 3
Completeness	The what is explicit (remote-control via keystrokes/scraping), but there is no "Use when..." or equivalent explicit trigger guidance, so per the guidelines completeness is capped at 2 with when only implied.	2 / 3
Trigger Term Quality	"tmux sessions" and "interactive CLIs" are natural terms, but "keystrokes" and "pane output" lean technical and common variations like "terminal", "TTY", or "attach" are absent; it does not reach the broad natural-term coverage of a 3.	2 / 3
Distinctiveness Conflict Risk	"Remote-control tmux sessions" carves out a clear, narrow niche tied to a specific tool that is unlikely to overlap with or trigger other skills.	3 / 3
	Total	10 / 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: Bitterbot-AI/bitterbot-desktop
Path: skills/tmux/SKILL.md
Commit: e73c717

Reviewed: about 15 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.