tmux

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

2.00x

Quality

66%

Does it follow best practices?

Impact

86%

2.00x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./openclaw/skills/tmux/SKILL.md

Quality

Discovery

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.

The description is concise and technically specific, clearly conveying the skill's unique capability of controlling tmux sessions programmatically. Its main weakness is the absence of an explicit 'Use when...' clause, which caps completeness. Adding trigger guidance and a few more natural keyword variations would make it excellent.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user needs to interact with tmux sessions, send commands to terminal panes, or capture terminal output.'

Include additional natural trigger terms like 'terminal multiplexer', 'send-keys', 'capture terminal output', or 'automate CLI interactions' to improve keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'remote-control tmux sessions', 'sending keystrokes', and 'scraping pane output'. These are specific, actionable capabilities rather than vague language.	3 / 3
Completeness	Clearly answers 'what does this do' (remote-control tmux sessions by sending keystrokes and scraping output), but lacks an explicit 'Use when...' clause specifying when Claude should select this skill.	2 / 3
Trigger Term Quality	Includes good terms like 'tmux', 'keystrokes', 'pane output', and 'interactive CLIs', but misses common user variations like 'terminal multiplexer', 'send keys', 'capture output', 'tmux send-keys', or 'screen scraping'.	2 / 3
Distinctiveness Conflict Risk	Very distinct niche — tmux session control via keystrokes and pane scraping is highly specific and unlikely to conflict with other skills. The combination of 'tmux', 'keystrokes', and 'pane output' creates a clear, unique identity.	3 / 3
	Total	10 / 12 Passed

Implementation

64%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a solid, actionable reference skill with excellent concrete examples and copy-paste ready commands. Its main weaknesses are some verbosity in the use/don't-use sections and basic tmux commands Claude already knows, plus a lack of explicit validation/feedback loops when sending input to interactive sessions. The structure is good but could benefit from tighter editing and a capture-then-verify workflow pattern.

Suggestions

Remove or significantly trim the 'When to Use' / 'When NOT to Use' sections and the basic session management commands (create/kill/rename) that Claude already knows.

Add an explicit workflow pattern for send-then-verify: send keys → sleep → capture-pane → verify expected output appeared, with a retry/error path if the prompt wasn't consumed.

Consider extracting the 'Claude Code Session Patterns' section into a separate file and linking to it, keeping SKILL.md focused on core tmux control primitives.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient but includes some unnecessary content. The 'When to Use' and 'When NOT to Use' sections are somewhat verbose for Claude, and the session management section (create/kill/rename) is basic tmux knowledge Claude already has. The 'Notes' section at the end is lean and useful though.	2 / 3
Actionability	Every section provides concrete, copy-paste ready bash commands. The examples cover real scenarios like checking session status, approving prompts, and safely sending input to TUIs. The commands are fully executable with specific flags and targets.	3 / 3
Workflow Clarity	The skill presents individual commands clearly but lacks explicit multi-step workflows with validation checkpoints. The 'Sending Input Safely' section hints at a sequence (split text and Enter, use sleep) but doesn't provide a validate-then-proceed pattern. For operations like sending input to interactive sessions, there's no feedback loop to verify the input was received correctly.	2 / 3
Progressive Disclosure	The content is well-organized with clear section headers and a logical progression from basic to advanced patterns. However, the Claude Code Session Patterns section could be split into a separate reference file since it's a specific use case. Everything is inline in one file, which is borderline acceptable for this length but could benefit from separation.	2 / 3
	Total	9 / 12 Passed

Validation

81%

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 — 9 / 11 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	9 / 11 Passed

Repository: trpc-group/trpc-agent-go
Commit: fcc550d

Reviewed: 6 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.