CLI output formatting standards for worktrunk. Load before editing any code that calls warning_message, hint_message, error_message, info_message, eprintln, or println, or that produces strings the user will see (CLI help, progress UI, snapshot text). Documents ANSI color nesting rules, message patterns, and output system architecture.
66
82%
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 a strong, well-crafted skill description. It clearly identifies the project scope (worktrunk), lists specific function names as trigger terms, explicitly states when to load the skill, and describes what it documents. The description is concise yet comprehensive, making it easy for Claude to select this skill precisely when needed.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and artifacts: ANSI color nesting rules, message patterns, output system architecture, and names specific functions (warning_message, hint_message, error_message, info_message, eprintln, println). | 3 / 3 |
Completeness | Clearly answers both 'what' (CLI output formatting standards, ANSI color nesting rules, message patterns, output system architecture) and 'when' ('Load before editing any code that calls warning_message, hint_message, error_message, info_message, eprintln, or println, or that produces strings the user will see'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms a developer would encounter: specific function names (warning_message, hint_message, error_message, info_message, eprintln, println), domain terms (CLI output, ANSI color, CLI help, progress UI, snapshot text), and the project name 'worktrunk'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — scoped to a specific project ('worktrunk'), a specific domain (CLI output formatting), and lists exact function names as triggers. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 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 highly actionable and project-specific skill with excellent concrete examples, GOOD/BAD comparisons, and precise Rust code throughout. Its main weaknesses are its monolithic length (~600 lines covering many distinct topics that could be split into referenced sub-files) and the lack of an overarching workflow or checklist for applying these standards when writing new output code. The content is genuinely useful and project-specific, avoiding explanations of things Claude already knows.
Suggestions
Split the monolithic document into sub-files (e.g., ARCHITECTURE.md, MESSAGE_PATTERNS.md, STYLING_GUIDE.md, ERROR_FORMATTING.md) with a concise overview and navigation links in the main SKILL.md
Add a quick-reference checklist or workflow at the top summarizing the key steps when adding output to a new command (e.g., '1. Decide stdout vs stderr, 2. Choose message type, 3. Apply styling rules, 4. Add snapshot test')
Consider adding a validation step or review checklist for verifying output conformance before committing (e.g., 'verify no raw paths without format_path_for_display, no quoted commands, no manual escape codes')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extensive and mostly contains project-specific conventions Claude wouldn't know, which is appropriate. However, there's some redundancy (e.g., the same patterns are shown multiple times with GOOD/BAD examples that could be consolidated), and some sections like the shell integration architecture could be tighter. The document is long but most content earns its place as project-specific guidance. | 2 / 3 |
Actionability | The skill provides highly concrete, executable Rust code examples throughout, specific function names with their modules, exact formatting patterns with GOOD/BAD comparisons, and precise rules (e.g., use `@` not 'at', use `<underline>` in hints not `<bold>`). Every guideline is illustrated with copy-paste-ready code or concrete examples. | 3 / 3 |
Workflow Clarity | The skill covers many individual formatting decisions clearly, but lacks an overarching workflow for 'how to add output to a new command.' Decision trees are provided for some areas (warning placement, stdout vs stderr) which is good, but there's no validation/verification step for checking output conformance. The warning ordering section and prompt spacing section have clear sequences, but the document as a whole reads more as a reference than a workflow. | 2 / 3 |
Progressive Disclosure | The document is a monolithic ~600-line file covering architecture, formatting standards, error formatting, styling, path formatting, table alignment, and snapshot testing all inline. There are references to source files (e.g., 'See src/git/error.rs', 'See src/commands/list/render.rs') which is good, but the content itself would benefit from being split into separate files (e.g., architecture, message patterns, styling guide, error formatting) with a concise overview in the main SKILL.md. No bundle files are provided to offload detail. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (993 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 8 / 11 Passed | |
bd4c399
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.