tmux
Patterns for running long-lived processes in tmux. Use when starting dev servers, watchers, tilt, or any process expected to outlive the conversation.
88
83%
Does it follow best practices?
Impact
100%
1.14xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description with clear 'when' guidance and good trigger terms that would help Claude select it appropriately. Its main weakness is the vague 'Patterns for' phrasing which doesn't specify concrete actions Claude would take (e.g., creating sessions, detaching, checking output). Overall it performs well for skill selection purposes.
Suggestions
Replace 'Patterns for running' with specific actions like 'Creates and manages tmux sessions for running long-lived processes' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (long-lived processes in tmux) and gives examples (dev servers, watchers, tilt), but doesn't list specific concrete actions like 'create tmux sessions', 'detach processes', or 'monitor output'. The word 'Patterns' is vague. | 2 / 3 |
Completeness | Clearly answers both what ('Patterns for running long-lived processes in tmux') and when ('Use when starting dev servers, watchers, tilt, or any process expected to outlive the conversation') with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'dev servers', 'watchers', 'tilt', 'tmux', 'long-lived processes', and 'outlive the conversation'. These cover common variations of how users would describe this need. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: tmux + long-lived processes is a very specific combination unlikely to conflict with other skills. The trigger terms (dev servers, watchers, tilt, outlive the conversation) clearly delineate this skill's scope. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%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, highly actionable skill with clear rules, executable examples, and good workflow structure including validation checkpoints and idempotency patterns. Its main weakness is repetition of the SESSION derivation and session-check boilerplate across nearly every code block, which inflates token usage. The content could benefit from factoring out repeated patterns and potentially splitting advanced patterns into a separate reference file.
Suggestions
Define the SESSION derivation and session-existence check once at the top, then reference it in subsequent examples rather than repeating the same 2-3 lines in every code block.
Consider extracting the 'Common Patterns' and 'Monitoring Output' sections into a separate reference file to keep the main SKILL.md focused on core rules and the most essential patterns.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining what tmux is, but there's significant repetition — the SESSION derivation line appears 10+ times verbatim, and patterns like 'check session, create if needed' are repeated across multiple sections with minor variations. This could be tightened by defining the session derivation once and referencing it. | 2 / 3 |
Actionability | Every section provides fully executable bash commands that are copy-paste ready. The WRONG vs CORRECT examples, the idempotent window creation patterns, the monitoring commands, and the polling loop for server readiness are all concrete and immediately usable. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints — checking session existence before creation, checking window existence before adding, polling for readiness, and error-checking output with grep. The isolation rules and 'When to Use tmux' table provide clear decision boundaries. The restart pattern includes a sleep for graceful shutdown. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and a logical progression from rules to patterns to lifecycle management. However, at ~180 lines with no bundle files, some content (like the full 'Common Patterns' section or the monitoring commands) could be split into referenced files to keep the main skill leaner. The decision table is a nice touch for quick reference. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- NeverSight/skills_feed
- Commit
aa009ea
- 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.