Guidance for Worktrunk (the `wt` CLI) — git worktree management, hooks, and config. Load when editing .config/wt.toml or ~/.config/worktrunk/config.toml; adding, modifying, or debugging hooks (post-merge, post-start, pre-commit, pre-merge, post-switch, etc.); configuring commit message generation or command aliases; or troubleshooting wt behavior. Also answers general worktrunk/wt questions.
75
92%
Does it follow best practices?
Impact
—
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 an excellent skill description that clearly identifies the specific tool (Worktrunk/wt CLI), enumerates concrete capabilities (worktree management, hooks, config), and provides explicit trigger conditions with specific file paths and hook names. The description is well-structured, uses third person voice appropriately, and provides enough detail to distinguish it from general git or other CLI tool skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: git worktree management, hooks, config editing, debugging hooks (with specific hook types enumerated), configuring commit message generation, command aliases, and troubleshooting. | 3 / 3 |
Completeness | Clearly answers both 'what' (guidance for Worktrunk CLI — git worktree management, hooks, and config) and 'when' with explicit triggers ('Load when editing .config/wt.toml...adding, modifying, or debugging hooks...configuring commit message generation...troubleshooting wt behavior'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'wt', 'worktrunk', 'wt CLI', 'worktree', specific config file paths (.config/wt.toml, ~/.config/worktrunk/config.toml), specific hook names (post-merge, post-start, pre-commit, etc.), 'commit message generation', 'command aliases'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific CLI tool ('wt' / 'worktrunk') with specific config file paths and hook types. Very unlikely to conflict with generic git skills or other tool-specific skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%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-structured, highly actionable skill that effectively guides Claude through Worktrunk configuration and hook management. The progressive disclosure is excellent with clear references to supporting documentation, and workflows include proper validation checkpoints. Minor verbosity in some sections (config type determination, permission models) could be tightened, but overall the content earns its token budget.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally efficient and avoids explaining basic concepts Claude already knows, but some sections are somewhat verbose — e.g., the 'Determining Which Config to Use' section with bullet-pointed indicators could be tighter, and the permission models section repeats information already conveyed in the config descriptions. The agent handoffs section is detailed but justified given the complexity. | 2 / 3 |
Actionability | The skill provides concrete, executable bash commands and TOML configuration snippets throughout. Workflows include specific commands like `wt config show`, `npm run lint --dry-run`, `bash -n -c ...`, and complete tmux/zellij invocations. The code examples are copy-paste ready and cover real scenarios. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly numbered with explicit validation checkpoints — e.g., 'Validate commands work' before creating hooks, 'verify prompt builds' after config changes, checking command existence before adding hooks. The hook approval section includes clear error recovery guidance. Dangerous patterns are flagged with warnings. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to specific reference files (config.md, hook.md, llm-commits.md, etc.). The 'Common Tasks Reference' section acts as a navigation index. Grep commands are provided for finding specific sections within reference files. Content is appropriately split between the overview and referenced documentation. | 3 / 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.
eaa230b
Table of Contents
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.