Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/academic-translation-guide
Academic translation, post-editing, and Chinglish correction guide
Passed 24 of 25 test cases with the skill, and 20 of 25 without it.
and 3 more in the full report
4 fixed20 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
Edit the following sentence for formal academic grammar: "The experiment result shows that our model achieves superior performance across all benchmarks."
| Checked | Without skill | With skill |
|---|---|---|
| Corrects "experiment result shows" to "experimental results show". | Missed | Passed |
The instructions your model reads when the skill loads.
Translate and polish research manuscripts between languages with a focus on academic register, domain-specific terminology, and common pitfalls for Chinese-English academic writing.
| Engine | Strengths | Weaknesses | Best For |
|---|---|---|---|
| DeepL | Excellent European languages, natural output | Limited Asian language pairs | EU language papers |
| Google Translate | Broadest language coverage | Less polished academic register | Quick drafts, rare languages |
| ChatGPT / Claude | Context-aware, follows style instructions | May hallucinate terminology | Post-editing, term-aware translation |
| Tencent TranSmart | Strong Chinese-English technical | Limited other languages | CN-EN STEM papers |
| Baidu Translate | Strong Chinese-English | Less natural English | CN-EN drafts |
# Example: Light post-editing checklist
- [ ] Technical terms are correct and consistent
- [ ] Numbers, units, and chemical formulas are accurate
- [ ] Negation is preserved (a common MT error)
- [ ] Subject-verb agreement is correct
- [ ] Hedging language is appropriate ("may" vs "will")
- [ ] Citations and references are intact
| Chinglish | Correction | Explanation |
|---|
test cases passed, vs 20 / 25 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.