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

83%

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

77%

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

A thorough, highly actionable translation workflow with excellent sequencing and validation gates. Its main weaknesses are conciseness (redundant restating of verification criteria) and progressive disclosure (a large monolithic body that could offload detail into the referenced resource files).

Suggestions

Consolidate the verification criteria so they appear once — Stage 4 is the canonical gate; prune the duplicate mechanical checks/rubric items from the Guardrails list and Canonical workflow path.

Move the full persona/voice tables, anti-AI pattern catalog, and troubleshooting table into referenced files (e.g. resources/translation-rubric.md, resources/personas.md) and keep SKILL.md as a lean overview with one-level-deep pointers.

Verify the referenced resources/translation-rubric.md, resources/anti-ai-patterns.md, and ../_shared/core/*.md files actually ship with the skill bundle; dangling references weaken the disclosure model.

Dimension	Reasoning	Score
Conciseness	The body is genuinely skill-specific (persona tables, CJK em-dash rules, anti-AI checks) rather than padding basic concepts, but at ~425 lines it repeats the same verification criteria across Stage 4, the Guardrails list, and the Canonical workflow path, leaving room to tighten.	2 / 3
Actionability	It provides concrete, copy-paste-ready guidance throughout — exact placeholder syntax ({name}, {{count}}, %s), the translator's-note format `번역어（원어, 쉬운 설명）`, output templates, and a literal `rg` command — which meets the anchor-3 bar for actionable instruction (code absence is not penalized for instruction-only skills).	3 / 3
Workflow Clarity	The Stage 1–7 pipeline is clearly sequenced with an explicit blocking verification gate ('do not emit output until every item is confirmed'), feedback loops ('If any mechanical check fails, revise and re-run'), and mandatory verification for batches > 10 strings, matching the anchor-3 validate→fix→retry pattern.	3 / 3
Progressive Disclosure	No bundle files exist, yet the SKILL.md is a near-monolithic ~425-line body keeping the persona tables, full verification rubric, troubleshooting table, and all 16 guardrails inline; the referenced resources/ and ../_shared/ paths are one level deep and signaled, but content that should be split remains inline.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 clearly answers both 'what' and 'when' with natural trigger terms and a distinct niche. Its only gap is specificity: it characterizes capabilities at a moderately high level rather than listing multiple discrete concrete actions.

Dimension	Reasoning	Score
Specificity	The description names the domain and concrete capabilities ('preserves tone, style, and natural word order', 'Infers register, domain, and style') but does not enumerate multiple distinct discrete actions in the manner of the anchor-3 example ('extract... fill... merge').	2 / 3
Completeness	It explicitly states what the skill does ('Context-aware translation that preserves tone, style, and natural word order') and when to use it via an explicit 'Use when...' clause, satisfying both halves of the anchor-3 criteria.	3 / 3
Trigger Term Quality	'Use when translating UI strings, documentation, marketing copy, or any multilingual content' gives good coverage of natural phrases a user would actually say, matching the anchor-3 expectation of broad natural-term coverage.	3 / 3
Distinctiveness Conflict Risk	The niche is clearly scoped to context-aware translation/localization with explicit, distinctive triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: first-fluke/oh-my-agent
Path: .agents/skills/oma-translator/SKILL.md
Commit: 3021301

Reviewed: about 21 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.