qtpass-localization-audit

QtPass localization audit - structural checks on .ts files (placeholders, HTML balance, mnemonics, mixed-script artifacts)

Quality

72%

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 ./.opencode/skills/qtpass-localization-audit/SKILL.md

Quality

Content

77%

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

The body is highly actionable with executable scripts and a well-sequenced, validated cleanup workflow, but it is monolithic and somewhat redundant — the single-file and sweep scripts overlap heavily, and content that could live in reference files is all inline. Consolidating the duplicate logic and extracting the artifact/pattern catalog into a reference file would improve conciseness and progressive disclosure.

Suggestions

De-duplicate the "Quick audit" and "All-files sweep" code blocks — have the sweep reuse or reference the single-file check logic rather than repeating ~80% of the code inline.

Extract the "Common machine-translation artifact patterns" catalog and the "Targeted patterns" scripts into a one-level-deep reference file (e.g. references/patterns.md) linked from SKILL.md to improve progressive disclosure.

Keep the executable Python, git, and lrelease6 commands and the validated 7-step workflow as-is; these are the body's strongest aspects.

Dimension	Reasoning	Score
Conciseness	The content is mostly efficient and assumes Claude's competence, but the "Quick audit" and "All-files sweep" code blocks duplicate roughly 80% of the same audit logic and could be consolidated or cross-referenced.	2 / 3
Actionability	Provides fully executable, copy-paste-ready Python heredoc scripts plus concrete git and lrelease6 commands with specific flags, matching the anchor for copy-paste-ready executable guidance.	3 / 3
Workflow Clarity	The "Standard cleanup workflow" is a clear 7-step sequence with explicit validation checkpoints (step 5 re-run audit for 0 findings, step 6 lrelease6 smoke test) and per-finding decision guidance, giving a proper validate→fix→re-validate feedback loop.	3 / 3
Progressive Disclosure	Sections are well-organized, but the skill is a monolithic ~260-line single file with no bundle references; the targeted-pattern scripts and the machine-translation artifact catalog could be split into one-level-deep reference files.	2 / 3
	Total	10 / 12 Passed

Description

67%

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

The description is specific and distinctive, clearly scoping a QtPass .ts structural-audit niche, but it lacks an explicit "Use when..." trigger clause and omits common natural-language variations like "translation"/"i18n". Adding a usage-trigger clause and a couple of natural synonyms would lift completeness and trigger-term quality.

Suggestions

Append an explicit "Use when..." clause naming the trigger situations (e.g., reviewing/merging machine-translated QtPass .ts contributions, Weblate syncs, or reviewer-refined translations) to satisfy the completeness 'when' requirement.

Add natural-language terms users would actually say — "translation", "translate", "i18n", "Qt translation files" — alongside the technical jargon to improve trigger-term coverage.

Keep the concrete check list (placeholders, HTML balance, mnemonics, mixed-script artifacts) as-is; it is already specific and distinctive.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete check actions: "placeholders, HTML balance, mnemonics, mixed-script artifacts", matching the anchor for several specific concrete actions.	3 / 3
Completeness	The "what" is explicit (structural checks on .ts files with the listed checks) but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant keywords like "localization", ".ts files", "mnemonics", and "HTML balance" are present, but common natural variations a user would say ("translation", "translate", "i18n", "Qt translation files") are missing.	2 / 3
Distinctiveness Conflict Risk	The "QtPass localization audit" framing is a clear, narrow niche tied to a specific app and Qt .ts files, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: IJHack/QtPass
Path: .opencode/skills/qtpass-localization-audit/SKILL.md
Commit: 04899e4

Reviewed: 4 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.