tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
71
66%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./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 is concise and specific about its capabilities, clearly identifying tmux remote control via keystrokes and pane scraping. Its main weaknesses are the lack of an explicit 'Use when...' clause and missing some natural trigger term variations that users might employ when needing this skill.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when needing to interact with interactive CLI tools, TUI applications, or programs that require terminal input/output within tmux.'
Include additional trigger terms users might naturally say, such as 'interactive command', 'terminal automation', 'TUI', 'send-keys', or 'capture terminal output'.
| 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 pane output), but lacks an explicit 'Use when...' clause specifying when Claude should select this skill. The 'when' is only implied. | 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'. Users might also say 'run interactive command' or 'automate terminal'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — tmux session control via keystrokes and pane scraping is a very specific niche. Unlikely to conflict with general terminal, shell, or CLI skills due to the explicit tmux and keystroke-sending focus. | 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 skill with excellent concrete examples and copy-paste ready commands for tmux session management. Its main weaknesses are the lack of explicit validation/error recovery steps in workflows (especially around timing-sensitive operations like send-keys) and some verbosity in the orchestration section that could be extracted to a separate reference file. The content structure is good but could benefit from tighter organization.
Suggestions
Add explicit error handling/validation steps — e.g., after creating a session, verify it exists with `tmux -S "$SOCKET" has-session -t "$SESSION"`, and after send-keys, capture output to confirm the command was received.
Move the 'Orchestrating Coding Agents' section to a separate reference file (e.g., ORCHESTRATION.md) and link to it from the main skill to reduce the monolithic feel.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient with concrete commands, but includes some unnecessary explanation (e.g., 'For interactive TUI apps like Claude Code/Codex, this guidance covers how to send commands' and the Windows/WSL section). The orchestrating coding agents section is lengthy and could be trimmed, though it does provide useful patterns. | 2 / 3 |
Actionability | Excellent executable examples throughout — copy-paste ready bash commands for session creation, sending keys, capturing output, polling for completion, and cleanup. The quickstart, orchestration example, and helper script usage are all concrete and complete. | 3 / 3 |
Workflow Clarity | The quickstart provides a clear sequence for session setup, and the orchestration section shows a multi-agent workflow. However, there are no explicit validation checkpoints or error recovery steps — e.g., no guidance on what to do if session creation fails, if send-keys doesn't work, or if capture-pane returns unexpected output. For an interactive session management skill with potential timing issues, feedback loops are important. | 2 / 3 |
Progressive Disclosure | Well-organized with clear section headers and references to helper scripts (`{baseDir}/scripts/find-sessions.sh`, `{baseDir}/scripts/wait-for-text.sh`). However, the orchestrating coding agents section is quite long and could be split into a separate file. No bundle files were provided, so the `{baseDir}` references can't be verified, and the content is somewhat monolithic for its length. | 2 / 3 |
Total | 9 / 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
- deepgram/dglabs-deepclaw
- Commit
ec8d4f8
- 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.