tmux

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

2.00x

Quality

—

Does it follow best practices?

Impact

86%

2.00x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

80%

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 command catalog with good organization. The main weaknesses are missing verification feedback loops after risky operations and a complete failure to surface the bundled helper scripts that already implement polling and session discovery.

Suggestions

Reference the existing bundle scripts (e.g., 'Poll a pane until text appears: scripts/wait-for-text.sh -t shared -p "proceed"') instead of leaving that capability undiscovered.

Add a verify step after risky operations: after send-keys or kill-session, capture-pane again to confirm the intended state was reached.

Point to scripts/find-sessions.sh from the 'List Sessions' section rather than only the bare 'tmux ls' command.

Dimension	Reasoning	Score
Conciseness	The body is command-focused and assumes Claude's tmux competence, avoiding explanations of concepts Claude already knows; every section earns its place like the 3 anchor.	3 / 3
Actionability	Fully executable, copy-paste-ready tmux commands with concrete examples for capture-pane, send-keys, and session management, matching the 3 anchor.	3 / 3
Workflow Clarity	Sequenced patterns exist (check-for-input then approve-prompt, split send/Enter), but there are no validation/feedback loops for destructive or batch operations such as kill-session, capping this at 2.	2 / 3
Progressive Disclosure	Sections are well-organized (not a monolithic wall), but the provided bundle scripts find-sessions.sh and wait-for-text.sh are never referenced, and equivalent polling/listing logic is kept inline rather than split out.	2 / 3
	Total	10 / 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 tight, specific, third-person description that concretely states capabilities and is highly distinct. Its only gap is the missing explicit 'when to use' trigger guidance, which caps completeness.

Suggestions

Append a 'Use when ...' clause naming natural triggers (e.g., 'Use when controlling interactive CLI sessions in tmux, sending input, or reading pane output') to lift completeness to 3.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "Remote-control tmux sessions", "sending keystrokes", "scraping pane output" — matching the multi-action 3 anchor rather than the single-action 2 anchor.	3 / 3
Completeness	Clearly states what the skill does but has no "Use when..." clause or equivalent explicit trigger, so per the guidelines completeness is capped at 2 rather than 3.	2 / 3
Trigger Term Quality	Includes natural terms a user would say ("tmux sessions", "keystrokes", "pane output"); not just one keyword like the 2 anchor, giving good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	The tmux-specific, interactive-CLI niche is clearly distinct and unlikely to fire for unrelated skills, matching the 3 anchor.	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: trpc-group/trpc-agent-go
Commit: 737835b

Reviewed: 2 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.