tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
81
Quality
77%
Does it follow best practices?
Impact
86%
2.00xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./openclaw/skills/tmux/SKILL.mdQuality
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 effectively communicates specific technical capabilities for tmux automation with good distinctiveness. However, it lacks explicit trigger guidance ('Use when...') and could benefit from more natural user-facing keywords beyond technical jargon to help Claude recognize when users need this skill.
Suggestions
Add a 'Use when...' clause with trigger scenarios like 'Use when the user needs to interact with interactive CLI programs, automate terminal sessions, or work with programs that require keyboard input'
Include more natural trigger terms users might say: 'terminal automation', 'interactive programs', 'CLI tools', 'command-line interaction', 'terminal session'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'remote-control tmux sessions', 'sending keystrokes', and 'scraping pane output'. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly describes WHAT it does (remote-control tmux, send keystrokes, scrape output) but lacks an explicit 'Use when...' clause explaining WHEN Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Includes good technical terms like 'tmux', 'keystrokes', 'pane output', but misses common user phrases like 'terminal automation', 'interactive programs', 'CLI tools', or specific use cases users might mention. | 2 / 3 |
Distinctiveness Conflict Risk | Very distinct niche - tmux session control is specific and unlikely to conflict with other skills. The combination of 'tmux', 'keystrokes', and 'pane output' creates a clear, unique domain. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable skill that efficiently teaches tmux session control with concrete, executable commands. The 'When to Use' and 'When NOT to Use' sections provide excellent boundaries. Minor improvement could be made by adding explicit validation steps when interacting with Claude Code sessions to confirm actions succeeded.
Suggestions
Add a validation step after sending input to Claude Code sessions (e.g., 'After sending, capture output again to confirm the prompt was accepted')
Consider adding a brief troubleshooting section for common issues like 'session not found' or 'pane has no output'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, presenting commands directly without explaining what tmux is or how terminals work. Every section provides actionable commands without unnecessary preamble. | 3 / 3 |
Actionability | All examples are copy-paste ready bash commands with clear syntax. The skill provides executable commands for every operation including capturing output, sending keys, and managing sessions. | 3 / 3 |
Workflow Clarity | While individual commands are clear, the 'Sending Input Safely' section hints at a workflow pattern but doesn't provide explicit validation steps. The Claude Code patterns section lists useful checks but lacks a clear sequence with feedback loops for error recovery. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections progressing from basic commands to advanced patterns. For a skill of this scope (~100 lines), the structure is appropriate with logical groupings and no need for external file references. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%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
50ef2f3
- Reviewed
Table of Contents
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.