translate

Adding, changing or translating interface strings in the SurfSense desktop app (surfsense_local). Use when adding a message to the code, moving hard-coded UI text into messages, translating into every language in LOCALES, or adding a language. Owns the key shape, the tone per language and the glossary.

Quality

94%

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

Quality

Content

96%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 dense, fully executable skill: every rule is project-specific, each workflow ends in an explicit validation checkpoint with a feedback loop, and references are cleanly signaled one level deep. The single weakness is that the referenced glossary.md is missing from the bundle.

Suggestions

Ship glossary.md alongside SKILL.md — the body requires translators to follow it and mandates that recurring new terms be added there ("A new term that will recur goes into glossary.md in the same change"), but the file is absent from the bundle.

Dimension	Reasoning	Score
Conciseness	Every line is a non-obvious project rule (key shape, ICU skeletons, per-language register, apostrophe escaping) with zero padding; it never explains what FormatJS or ICU MessageFormat is, fully assuming Claude's competence.	5 / 5
Actionability	Copy-paste-ready commands throughout ("pnpm translations", "pnpm translations:verify", "node scripts/check_translations.mjs", the git-diff bash block) plus exact code patterns like intl.formatMessage({ id: "sources_list_empty", defaultMessage: "No sources yet" }) and concrete ICU examples ({count, plural, one {# document} other {# documents}}).	5 / 5
Workflow Clarity	Three workflows (Adding English, Translating, Adding a language) are each a clear numbered sequence ending in explicit validation ("Stop and fix on any failure; do not commit around it", pre-commit hooks, pnpm test), providing a validate→fix→retry feedback loop for the batch translation operation.	5 / 5
Progressive Disclosure	Sections are well organized with clearly signaled one-level references ([glossary.md](glossary.md), docs/architecture/localization.md, ADR 0017), but the referenced glossary.md is not present in the bundle even though the body directs translators to it ("Follow the tone below and glossary.md"). Minor structural gap, so anchor 4 fits better than 5.	4 / 5
	Total	19 / 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.

The description is exemplary: it names concrete actions, gives an explicit 'Use when' clause with multiple trigger scenarios, and delimits ownership to avoid conflicts. Its only gap is the absence of common synonyms such as 'localization' or 'i18n' that a user might naturally say.

Dimension	Reasoning	Score
Specificity	"Adding, changing or translating interface strings", "moving hard-coded UI text into messages", and "adding a language" are multiple specific concrete actions covering the skill's full scope, matching the comprehensive-coverage anchor.	5 / 5
Completeness	"Adding, changing or translating interface strings in the SurfSense desktop app (surfsense_local)" states the what, and "Use when adding a message to the code, moving hard-coded UI text into messages, translating into every language in LOCALES, or adding a language" explicitly states the when with concrete trigger phrases — exactly the anchor-5 pattern.	5 / 5
Trigger Term Quality	Natural phrases a user would say are present ("translating", "hard-coded UI text", "adding a message", "adding a language"), but common synonyms like "localization" or "i18n" are missing. Fits anchor 4 (good coverage, a few natural terms missing) rather than 5.	4 / 5
Distinctiveness Conflict Risk	Scoped to a single named app with explicit ownership ("Owns the key shape, the tone per language and the glossary"), giving it a clear niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 missing, 2 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: MODSetter/SurfSense
Path: .agents/skills/translate/SKILL.md
Commit: 7fb479c

Reviewed: 3 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.