Turns customer feedback into structured output
The source asks the model to group, classify, answer, or prioritize review feedback rather than treating every comment as an isolated case.
IntermediateKostja Zhang
Translation
Translation is an ecommerce AI skill for Kostja Zhang, built for teams working with OpenClaw. Use it to you are taking a product or store into a new language or…
- Views
- 0
- Installs
- 0
- Favorites
- 0
What this Skill does
You are taking a product or store into a new language or market. Do not change every step at once: test Setting up a Translation workflow for a SaaS product expanding to new markets alongside Creating a multilingual glossary and style guide for consistent brand voice across…,… Start with a small test around “Setting up a Translation workflow for a SaaS product expanding to new markets”, then check whether “Creating a multilingual glossary and style guide for consistent brand voice across locales” fits the way your team actually works.
What makes it different
Creates listing and search-content fields together
The source covers product or listing copy alongside SEO-related fields such as keywords, metadata, or image text when those fields are requested.
No installation needed
Copy and paste into a model chat
- Expand and copy the complete original Skill.md below.
- Open a new conversation in a compatible AI model, then paste it into the chat box.
- Add verified task details, run one low-risk example, and review the result before using it in store operations.
Original Skill.md
The complete source is shown below. Copy it from the top right to use it.
You are a translation workflow expert. Guide the translation process through three phases: 1) Brief — create a translator brief with context, target audience, tone, glossary reference, style guide, and constraints (character limits, SEO keywords); 2) Translate — execute first-pass translation using glossary and translation memory where available; 3) Review — native speaker review for consistency, brand voice, and SEO. Identify the content type to determine approach: Product UI requires glossary and TM precision, marketing copy needs human translation with cultural adaptation, blog articles need keyword re-research in the target language (never translate keyword lists directly), landing pages need conversion-tested human translation, and technical docs can use MT+post-edit for volume. Create and maintain a glossary with source term, target term, context, and 'do not translate' flags. Define per-language style guides covering voice, tone, register, punctuation, formatting, and forbidden terms. For SEO, re-research keywords in the target language and translate all metadata. Avoid publishing many low-quality translated pages at once to prevent thin content penalties.Get started
Starter prompts for the main use cases—copy and use them directly.
01Start with one real task
Do not begin with a store-wide rollout. Pick one reversible task where Translation can help you create, localize, or check product content and visual assets. Use this when the input boundary, owner, and one primary measure from factual corrections, editing time, approval rate, and conversion quality are written down.
Show prompt and variablesHide prompt and variables
Start with one real task
Do not begin with a store-wide rollout. Pick one reversible task where Translation can help you create, localize, or check product content and visual assets. Use this when the input boundary, owner, and one primary measure from factual corrections, editing time, approval rate, and conversion quality are written down.
Use the Skill above to help me with this task: Start with one real task.
Task details: [TASK_DETAILS]
Constraints or policies to follow: [CONSTRAINTS]
Do not begin with a store-wide rollout. Pick one reversible task where Translation can help you create, localize, or check product content and visual assets.
Return a practical result and clearly flag anything that needs human review.Replace these variables
[TASK_DETAILS]- The facts, context, or source material for this task.
[CONSTRAINTS]- Replace this placeholder with your verified store-specific information.
02Prepare the input and guardrails
Collect only the verified product facts, source images, brand rules, target channel, and prohibited claims needed for this test. Remove unrelated personal data and state which actions must never run automatically. Use this when every input has a known source, sensitive fields are minimized, and the approver knows what the trial can read or change.
Show prompt and variablesHide prompt and variables
Prepare the input and guardrails
Collect only the verified product facts, source images, brand rules, target channel, and prohibited claims needed for this test. Remove unrelated personal data and state which actions must never run automatically. Use this when every input has a known source, sensitive fields are minimized, and the approver knows what the trial can read or change.
Use the Skill above to help me with this task: Prepare the input and guardrails.
Task details: [TASK_DETAILS]
Constraints or policies to follow: [CONSTRAINTS]
Collect only the verified product facts, source images, brand rules, target channel, and prohibited claims needed for this test. Remove unrelated personal data and state which actions must never run automatically.
Return a practical result and clearly flag anything that needs human review.Replace these variables
[TASK_DETAILS]- The facts, context, or source material for this task.
[CONSTRAINTS]- Replace this placeholder with your verified store-specific information.
03Inspect the source Skill, then run it
Read the source, installation method, and permission notes before adding Translation to a separate test project. Keep commands and Skill text exactly as published. Use this when you have a product-content draft that a responsible operator can inspect, and it stayed inside the approved boundary.
Show prompt and variablesHide prompt and variables
Inspect the source Skill, then run it
Read the source, installation method, and permission notes before adding Translation to a separate test project. Keep commands and Skill text exactly as published. Use this when you have a product-content draft that a responsible operator can inspect, and it stayed inside the approved boundary.
Use the Skill above to help me with this task: Inspect the source Skill, then run it.
Task details: [TASK_DETAILS]
Constraints or policies to follow: [CONSTRAINTS]
Read the source, installation method, and permission notes before adding Translation to a separate test project. Keep commands and Skill text exactly as published.
Return a practical result and clearly flag anything that needs human review.Replace these variables
[TASK_DETAILS]- The facts, context, or source material for this task.
[CONSTRAINTS]- Replace this placeholder with your verified store-specific information.
04Review it against a baseline
Do not judge the result by fluency. Compare it with source data, the current SOP, and the pre-test baseline; record factual errors, omissions, and editing time. Use this when factual corrections, editing time, approval rate, and conversion quality has a pre-test baseline, and errors and exceptions are logged separately.
Show prompt and variablesHide prompt and variables
Review it against a baseline
Do not judge the result by fluency. Compare it with source data, the current SOP, and the pre-test baseline; record factual errors, omissions, and editing time. Use this when factual corrections, editing time, approval rate, and conversion quality has a pre-test baseline, and errors and exceptions are logged separately.
Use the Skill above to help me with this task: Review it against a baseline.
Task details: [TASK_DETAILS]
Constraints or policies to follow: [CONSTRAINTS]
Do not judge the result by fluency. Compare it with source data, the current SOP, and the pre-test baseline; record factual errors, omissions, and editing time.
Return a practical result and clearly flag anything that needs human review.Replace these variables
[TASK_DETAILS]- The facts, context, or source material for this task.
[CONSTRAINTS]- Replace this placeholder with your verified store-specific information.
Risks and operating notes
Use the minimum customer data needed
The workflow may need an order reference or case facts. Do not paste payment details, full addresses, or unrelated order history into a model conversation; redact them unless they are essential to the decision.
Keep claims tied to verified product facts
When this instruction drafts marketing or product content, review specifications, comparisons, performance claims, and testimonials against approved evidence before publishing.
Treat review patterns as hypotheses to test
The instruction can group and prioritize feedback, but repeated wording is not proof of a product defect or customer-wide preference. Check the underlying sample before changing a product, policy, or campaign.
Kostja Zhang
AI and SaaS growth practitioner publishing skills for SEO, content marketing, translation, and international growth.
Risk, permissions, and limitations
Review third-party permission scopes before providing store data. Never paste payment credentials, customer passwords, or unnecessary personal data into a model. Outputs must be checked by the operator responsible for the workflow.
Content checked:
No reviews yet.