writing-user-outputs

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.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/writing-user-outputs/SKILL.md

Quality

Content

57%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, highly actionable standards reference with excellent concrete code examples and decision frameworks, but it is a large monolith with no progressive disclosure into bundle files and some rationale prose that could be trimmed.

Suggestions

Split the body into reference files (e.g. references/formatting-standards.md, references/output-architecture.md) and keep SKILL.md as a concise overview with clearly signaled one-level-deep links, improving progressive_disclosure.

Trim historical/rationale prose such as the 'thirty call sites had open-coded...' passage and the verbose stderr-macro scanning narrative to the rule itself, improving conciseness.

Add explicit validation checkpoints for destructive/batch output operations (e.g. snapshot-test verification steps) to lift workflow_clarity above the reference-doc baseline.

Dimension	Reasoning	Score
Conciseness	Mostly efficient project-specific content without basic-concept padding, but several dense prose paragraphs (stderr macro scanning rationale, the 'thirty call sites had open-coded...' JSON history) could be tightened; matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than 4 due to these rationale/historical passages.	3 / 5
Actionability	Extensive concrete, copy-paste-ready Rust snippets, function tables, and GOOD/BAD comparisons provide mostly executable guidance, matching anchor 4; not 5 because a portion of examples are illustrative message strings rather than fully executable code.	4 / 5
Workflow Clarity	Clear decision frameworks (stdout-vs-stderr principle, warning placement tree, paging rules) give good sequencing guidance, but as a standards reference rather than a sequenced operation it lacks explicit validation checkpoints, matching 'sequence present but checkpoints missing or implicit'.	3 / 5
Progressive Disclosure	Well-organized with clear section headers across two logical halves, but the ~1135-line body is monolithic with no bundle files (references/scripts/assets absent) and content that belongs in separate reference files is inlined; matches 'some structure but could be better organized' rather than 4 given the absence of any file-level disclosure.	3 / 5
	Total	13 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states both capability and trigger conditions with concrete function names. The main gap is the absence of synonyms/file extensions and the minor overlap risk from generic macro names.

Dimension	Reasoning	Score
Specificity	Names concrete targets (warning_message, hint_message, error_message, info_message, eprintln, println) and specific subject areas (ANSI color nesting rules, message patterns, output system architecture), matching the 'lists several specific actions; minor gaps' anchor rather than 5 because 'Documents...' describes subject matter more than the discrete actions Claude performs.	4 / 5
Completeness	Explicitly answers both what ('Documents ANSI color nesting rules, message patterns, and output system architecture') and when ('Load before editing any code that calls ... or that produces strings the user will see') with concrete trigger phrases, matching the top anchor; not 4 because the 'when' is fully explicit rather than weakly implied.	5 / 5
Trigger Term Quality	Strong codebase-specific trigger terms (eprintln, println, CLI help, progress UI, snapshot text) that a worktrunk developer would naturally invoke, matching 'good keyword coverage; a few natural terms missing' rather than 5 because no synonyms or file extensions are included.	4 / 5
Distinctiveness Conflict Risk	The worktrunk-specific message functions give it a clear niche with minimal conflict, but the generic eprintln/println triggers create minor overlap risk with general Rust/logging skills, matching 'mostly distinct; minor overlap risk' rather than 5.	4 / 5
	Total	17 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1135 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	13 / 16 Passed

Repository: max-sixty/worktrunk
Path: .claude/skills/writing-user-outputs/SKILL.md
Commit: 6c263ed

Reviewed: 10 hours ago

Table of Contents

Discovery Implementation Validation

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.