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

78%

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

65%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.

An exceptionally actionable and well-organized internal standards document, weakened mainly by its monolithic ~1100-line length, some narrative over-explanation, and the absence of progressive disclosure via bundle files.

Suggestions

Split large reference blocks (output function tables, styling/cformat tag reference, architecture deep-dive) into reference files under references/ and link to them one level deep to improve progressive disclosure and shrink the SKILL.md body.

Trim narrative rationale paragraphs (e.g., the broken-pipe history and stderr-macro digression) to the rule plus a one-line justification to raise conciseness.

Add a short "When editing output" workflow at the top — route stdout/stderr, pick message type, apply styling, then validate via snapshot test — to give the standards an explicit sequenced application with a validation checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is dense and project-specific (no padding with concepts Claude already knows), but at ~1100 lines it is long, and several narrative rationale paragraphs (e.g., the broken-pipe historical digression, the stderr-macro deep-dive) could be tightened without losing the rule.	3 / 5
Actionability	Highly actionable throughout: copy-paste-ready Rust snippets, exact function signatures and tables, concrete GOOD/BAD message strings, and specific commands (e.g., format_path_for_display, cformat! tags) cover the common cases.	5 / 5
Workflow Clarity	This is a standards/reference catalog rather than a sequenced process, so there is no explicit multi-step workflow with validation checkpoints; the snapshot-testing validation step appears only at the end and is not woven into an applied workflow.	3 / 5
Progressive Disclosure	Good internal section structure with clear headers and tables, but it is a single monolithic ~1100-line file with no bundle/reference files, so substantial reference content (architecture deep-dive, styling tables, message patterns) that could be split out is inlined.	3 / 5
	Total	14 / 20 Passed

Description

92%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 what the skill documents and when to load it, anchored to concrete function names. Slightly jargon-heavy on trigger terms but otherwise excellent.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions and surfaces — "warning_message, hint_message, error_message, info_message, eprintln, or println" plus "ANSI color nesting rules, message patterns, and output system architecture" — giving comprehensive coverage rather than vague abstraction.	5 / 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...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good keyword coverage via the six named message functions and terms like "CLI help, progress UI, snapshot text", but the triggers lean technical-jargon-heavy and omit a few more natural phrasings (e.g., "message styling", "terminal output") a user might say.	4 / 5
Distinctiveness Conflict Risk	Clear niche scoped to worktrunk's specific output functions and conventions, with distinct triggers tied to named APIs, so conflict with unrelated skills is minimal.	5 / 5
	Total	19 / 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 (1106 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: 8faeabf

Reviewed: 2 days 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.