oma-translator

Context-aware translation that preserves tone, style, and natural word order. Use when translating UI strings, documentation, marketing copy, or any multilingual content. Infers register, domain, and style from the source text and surrounding codebase context.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

81%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 comprehensive, highly actionable translation skill with excellent workflow sequencing and explicit validation feedback loops. Its main weakness is conciseness — repeated coverage across the verification gate, review stages, and restated workflow sections inflates the body without adding new information.

Suggestions

Consolidate the anti-AI/verification checks that recur across the Stage 4 Verification Gate, Stage 5 Critical Review, and Guardrails sections into a single canonical list with cross-references to avoid triple restatement.

Trim or remove the 'Logical Operations' Actions table (SSL primitives) since it restates workflow steps already covered in the Structural Flow and canonical workflow path without adding executable value.

Move the persona/voice tables and the full 19-item Guardrails list into separate reference files (e.g. references/personas.md, references/guardrails.md) and keep SKILL.md as a lean overview pointing to them.

Dimension	Reasoning	Score
Conciseness	Mostly efficient core content, but the ~540-line body repeats concepts across the Verification Gate, Stage 5-7 review, canonical workflow path, and Logical Operations tables, and the SSL-primitive Actions table adds structural padding Claude could infer.	3 / 5
Actionability	Highly concrete guidance with exact file paths, named rule identifiers, a literal ripgrep command, precise persona/routing tables, and copy-paste output format blocks covering the common cases.	5 / 5
Workflow Clarity	A clearly sequenced Stage 1-7 pipeline with an explicit blocking Verification Gate, revise-and-rerun feedback loops, a batch-size threshold for mandatory verification, and a diff-sync mode with hard rules — satisfying the feedback-loop requirement for destructive/batch operations.	5 / 5
Progressive Disclosure	Well-sectioned overview with a clear References list and one-level-deep external pointers, but no bundle files exist and substantial detail (persona tables, full guardrail list, troubleshooting) is inlined that could live in separate reference files.	4 / 5
	Total	17 / 20 Passed

Description

87%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, third-person description that concretely answers both what the skill does and when to use it with natural trigger phrases. Minor gaps in synonyms/file extensions and slightly abstract action verbs keep specificity and trigger_term_quality at 4.

Dimension	Reasoning	Score
Specificity	Names concrete capabilities ('preserves tone, style, and natural word order', 'translating UI strings, documentation, marketing copy', 'Infers register, domain, and style') with good coverage, but actions are slightly abstract rather than a literal list of output verbs, so it sits at 4 rather than 5.	4 / 5
Completeness	It explicitly states both what it does ('Context-aware translation that preserves tone, style, and natural word order') and when to use it ('Use when translating UI strings, documentation, marketing copy, or any multilingual content') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural user phrasing is present ('translating UI strings, documentation, marketing copy, multilingual content') with good coverage, but synonyms and file extensions like 'localization', 'i18n', or '.json' are missing, keeping it below 5.	4 / 5
Distinctiveness Conflict Risk	'Context-aware translation' with specific triggers (UI strings, marketing copy, multilingual content) carves a clear niche with minimal conflict risk, reinforced by the body's explicit 'When NOT to use' deflections.	5 / 5
	Total	18 / 20 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
skill_md_line_count	SKILL.md is long (546 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: first-fluke/oh-my-agent
Path: .agents/skills/oma-translator/SKILL.md
Commit: 032c988

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.