tmux-processes
Patterns for running long-lived processes in tmux. Use when starting dev servers, watchers, tilt, or any process expected to outlive the conversation.
86
83%
Does it follow best practices?
Impact
90%
1.52xAverage 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 'Use when' guidance and good trigger terms that cover the main use cases. 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 excellent executable examples and good safety constraints (isolation rules, idempotent patterns). Its main weakness is repetition — the SESSION variable line and similar patterns appear many times, inflating token cost. The content would benefit from deduplication and potentially splitting common patterns into a separate file.
Suggestions
Define the SESSION variable derivation once at the top and reference it in subsequent sections (e.g., 'Using $SESSION as defined above') to reduce ~12 repetitions of the same line.
Consider moving the 'Common Patterns' section to a separate PATTERNS.md file since it largely recombines earlier content, and link to it from the main skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with executable examples, but there's significant repetition — the SESSION variable derivation line is repeated ~12 times verbatim across sections. This could be stated once and referenced. Some sections like 'Adding Windows' and the 'Common Patterns > Start dev server if not running' overlap heavily with earlier content. | 2 / 3 |
Actionability | Every section provides fully executable, copy-paste ready bash commands. The WRONG vs CORRECT pattern at the top is immediately actionable, and all examples use real commands (npm run dev, tilt up, tail -f) with proper tmux syntax including session/window targeting. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced (create session → send keys → monitor → manage lifecycle). Validation checkpoints are present: idempotent start checks, error monitoring with grep, ready-state polling with retry loops, and explicit verification before kill operations. The isolation rules provide clear safety constraints. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear section headers and a useful decision table, but at ~180 lines it's a long single file. The 'Common Patterns' section at the end largely recombines earlier sections and could be a separate reference. No external file references are used, though the content length would benefit from splitting advanced patterns out. | 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
e437c3c
- 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.