catalan-adobe/cmux-setup
BEFORE manually calling cmux set-status or writing chpwd hooks for workspace coloring, use this skill. Manages workspace color rules that auto-apply based on directory patterns. Handles config creation, zsh hook installation, rule management, and on-demand workspace coloring via cmux set-status. Triggers on "cmux setup", "workspace colors", "color this workspace", "add color rule", "project colors", or any request to visually differentiate cmux workspaces.
97
97%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 strong skill description that clearly defines its niche (cmux workspace color management), lists concrete actions (config creation, zsh hook installation, rule management), and provides explicit trigger guidance with natural user phrases. The opening 'BEFORE manually...' clause adds helpful context about when to prefer this skill over manual approaches. Minor improvement could be made by slightly tightening the prose, but overall it's well-crafted.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: manages workspace color rules, handles config creation, zsh hook installation, rule management, and on-demand workspace coloring via cmux set-status. | 3 / 3 |
Completeness | Clearly answers both 'what' (manages workspace color rules, config creation, zsh hook installation, rule management, on-demand coloring) and 'when' (explicit 'Triggers on...' clause with specific phrases, plus the opening 'BEFORE manually calling cmux set-status...' guidance). | 3 / 3 |
Trigger Term Quality | Includes a rich set of natural trigger terms users would say: 'cmux setup', 'workspace colors', 'color this workspace', 'add color rule', 'project colors', and the broader 'visually differentiate cmux workspaces'. Also mentions 'cmux set-status' and 'chpwd hooks' for more technical users. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: cmux workspace coloring with directory-pattern-based rules. The specific tool name (cmux), the concept of workspace color rules, and zsh hook installation make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with excellent actionability and conciseness. Commands are fully specified, workflows are clearly sequenced with two distinct modes, and the conversational request table is an efficient pattern for mapping user intents to actions. The only minor weakness is that some operational details (script location discovery, installation) could be split out for cleaner progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every section serves a purpose—no explanations of what cmux is, no padding about color theory or terminal concepts. The conversational request table is a compact way to map intents to actions. | 3 / 3 |
Actionability | All commands are fully specified with exact CLI syntax, flags, and arguments. The script location block is copy-paste ready, the config format includes a concrete JSON example, and both persistent and on-demand modes have clear step-by-step instructions. | 3 / 3 |
Workflow Clarity | Mode 1 (Persistent Setup) is a clearly numbered 5-step sequence with an immediate apply step and a reminder to source the shell config. Mode 2 distinguishes between existing-config and ad-hoc paths. The conversational request table provides clear action mappings. The workflow is not destructive enough to require explicit validation loops beyond what's provided. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections, but the script location discovery logic and config format details are inline rather than referenced from separate files. For a skill of this size (~100 lines) this is borderline acceptable, but the standalone installation section and script location block add weight that could be externalized. | 2 / 3 |
Total | 11 / 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.
Reviewed
Table of Contents