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

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 ./benchmarks/runs/oma/.agents/skills/oma-translator/SKILL.md

Quality

Content

73%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 well-structured, highly actionable translation skill with an excellent verification-gated workflow. Its main weakness is verbosity from redundant meta-structural sections that restate the workflow, plus referenced resource files that are signaled but not bundled.

Suggestions

Collapse the redundant workflow framings — Scheduling, Structural Flow, Logical Operations, Canonical workflow path, and How to Execute all restate Stages 1–7; keep one canonical sequence and drop the rest.

Move the large persona table and the 16-item guardrail list into referenced files (or trim to the few non-obvious rules) to reduce inline bulk.

Add one concrete worked example (source string → Stage 1 analysis → final target output) to make the already-actionable method fully copy-paste demonstrable.

Dimension	Reasoning	Score
Conciseness	The Translation Method stages and verification gate are efficient and task-specific, but the body is padded with redundant meta-structural framings (Scheduling, Structural Flow with SSL primitives, Logical Operations READ/WRITE table, Canonical workflow path, How to Execute) that restate the same workflow multiple ways — content Claude does not need.	3 / 5
Actionability	Highly concrete guidance throughout — persona tables, exact placeholder syntax (`{name}`, `{{count}}`, `%s`), a runnable `rg` command, output-format templates, and a troubleshooting table — with only minor gaps such as no full worked before/after example showing the method end-to-end on a real string.	4 / 5
Workflow Clarity	Stages 1–7 are clearly sequenced with an explicit blocking verification gate ("do not emit output until every item is confirmed"), revise-and-rerun feedback loops for failed mechanical checks, and batch-specific rules (>10 strings triggers mandatory verification), matching the checklist-and-feedback-loop anchor.	5 / 5
Progressive Disclosure	Good section structure with clearly signaled one-level-deep references to `resources/translation-rubric.md`, `resources/anti-ai-patterns.md`, and `../_shared/core/*`, but the referenced files are not present in any bundle directory and several large inlined blocks (persona tables, full guardrail list) could live in referenced files.	4 / 5
	Total	16 / 20 Passed

Description

83%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 description that clearly states both capability and trigger conditions in third person with concrete content-type examples. It could be sharpened by adding localization/i18n synonyms and listing more distinct actions.

Suggestions

Add natural trigger synonyms users say — "localize", "localization", "i18n", "l10n", and "glossary" — to broaden keyword coverage.

Surface a few more distinct concrete actions (e.g., "reviews existing translations", "builds glossaries", "adapts marketing copy") rather than describing qualities of translation.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete behaviors — "preserves tone, style, and natural word order" and "Infers register, domain, and style from the source text and surrounding codebase context" — but these are qualities of one main action (translation) rather than many distinct operations, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what ("Context-aware translation that preserves tone, style, and natural word order ... Infers register, domain, and style") and when ("Use when translating UI strings, documentation, marketing copy, or any multilingual content") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keywords — "translating UI strings, documentation, marketing copy, or any multilingual content" — but misses common synonyms users say like "localize", "localization", "i18n", "l10n", and "glossary".	4 / 5
Distinctiveness Conflict Risk	The context-aware + codebase-context inference niche with specific content-type triggers is mostly distinct from generic editing skills, but there is minor overlap risk with general localization or copy-editing skills.	4 / 5
	Total	17 / 20 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: benchmarks/runs/oma/.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.