How do I install the Verifiable Translation Rule Compliance skill?

Run npx skillmds@latest add dingxingdi/verifiable-translation-rule-compliance-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Verifiable Translation Rule Compliance safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Verifiable Translation Rule Compliance?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Verifiable Translation Rule Compliance free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Verifiable Translation Rule Compliance?

dingxingdi (@dingxingdi) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Verifiable Translation Rule Compliance by dingxingdi

Name: Verifiable Translation Rule Compliance
Author: dingxingdi

Verifiable Translation Rule Compliance

Use this skill when the user wants translation data with hard rules that can be checked exactly, such as "keep the URL as-is," "change dates to DD/MM/YYYY," "convert dollars to pesos," or "put the original museum name in parentheses." Trigger it for requests like "test translation plus formatting rules," "make it follow localization instructions," or "the output must obey several exact constraints, not just be a good translation."

dingxingdi Updated Sep 17, 2026

File contents

Skill: verifiable-translation-rule-compliance

1. Capability Definition & Real Case

Professional Definition: The ability to translate faithfully while also satisfying explicit, objectively checkable user rules such as date formatting, currency conversion, unit conversion, URL preservation, named-entity formatting, or other source-dependent transformations.
Dimension Hierarchy: Contextual and Constraint-Aware Translation->Rule-Conditioned Translation->verifiable-translation-rule-compliance

Real Case

[Case 1]

Initial Environment: A translation agent is given an English marketing paragraph, a Spanish (Latin America) target locale, and three explicit rules: convert dates to DD/MM/YYYY, keep email addresses and URLs unchanged, and convert US dollars to Mexican pesos at a stated rate. The source text was written so that every rule is applicable.
Real Question: Translate the following short text into Spanish (Latin America). Follow these rules: (1) convert all dates to DD/MM/YYYY, (2) keep email addresses and website URLs unchanged, and (3) convert all dollar amounts to Mexican pesos using 1 USD = 18 MXN. Text: "The SmartFit app launched on 5/15/2023. I already saved $120 this month. Visit www.smartfit-tech.com or email help@smartfit-tech.com."
Real Trajectory: The agent parses the source text, applies each rule to the relevant span, checks that the URL and email remain unchanged, converts the amount, and returns only the final Spanish translation.
Real Answer: La aplicación SmartFit se lanzó el 15/05/2023. Ya ahorré 2160 MXN este mes. Visita www.smartfit-tech.com o escribe a help@smartfit-tech.com.
Why this demonstrates the capability: The task requires simultaneous control over adequacy and rule obedience, and both dimensions are visible in the final output. The example is especially useful because each constraint is objectively verifiable rather than stylistically subjective. A strong system must therefore execute translation and localized transformation as one coordinated process.

Pipeline Execution Instructions

To synthesize data for this capability, you must strictly follow a 3-phase pipeline. Do not hallucinate steps. Read the corresponding reference file for each phase sequentially:

Phase 1: Environment Exploration Read the exploration guidelines to discover raw knowledge seeds: references/EXPLORATION.md
Phase 2: Trajectory Selection Once Phase 1 is complete, read the selection criteria to evaluate the trajectory: references/SELECTION.md
Phase 3: Data Synthesis Once a trajectory passes Phase 2, read the synthesis instructions to generate the final data: references/SYNTHESIS.md

---name: verifiable-translation-rule-compliance-2description: Use this skill when the user wants translation data with hard rules that can be checked exactly, such as "keep the URL as-is," "change dates to DD/MM/YYYY," "convert dollars to pesos," or "put the original museum name in parentheses." Trigger it for requests like "test translation plus formatting rules," "make it follow localization instructions," or "the output must obey several exact constraints, not just be a good translation."---# Skill: verifiable-translation-rule-compliance## 1. Capability Definition & Real Case* **Professional Definition**: The ability to translate faithfully while also satisfying explicit, objectively checkable user rules such as date formatting, currency conversion, unit conversion, URL preservation, named-entity formatting, or other source-dependent transformations.* **Dimension Hierarchy**: Contextual and Constraint-Aware Translation->Rule-Conditioned Translation->verifiable-translation-rule-compliance### Real Case**[Case 1]*** **Initial Environment**: A translation agent is given an English marketing paragraph, a Spanish (Latin America) target locale, and three explicit rules: convert dates to DD/MM/YYYY, keep email addresses and URLs unchanged, and convert US dollars to Mexican pesos at a stated rate. The source text was written so that every rule is applicable.* **Real Question**: Translate the following short text into Spanish (Latin America). Follow these rules: (1) convert all dates to DD/MM/YYYY, (2) keep email addresses and website URLs unchanged, and (3) convert all dollar amounts to Mexican pesos using 1 USD = 18 MXN. Text: "The SmartFit app launched on 5/15/2023. I already saved $120 this month. Visit www.smartfit-tech.com or email help@smartfit-tech.com."* **Real Trajectory**: The agent parses the source text, applies each rule to the relevant span, checks that the URL and email remain unchanged, converts the amount, and returns only the final Spanish translation.* **Real Answer**: La aplicación SmartFit se lanzó el 15/05/2023. Ya ahorré 2160 MXN este mes. Visita www.smartfit-tech.com o escribe a help@smartfit-tech.com.* **Why this demonstrates the capability**: The task requires simultaneous control over adequacy and rule obedience, and both dimensions are visible in the final output. The example is especially useful because each constraint is objectively verifiable rather than stylistically subjective. A strong system must therefore execute translation and localized transformation as one coordinated process.## Pipeline Execution InstructionsTo synthesize data for this capability, you must strictly follow a 3-phase pipeline. **Do not hallucinate steps.** Read the corresponding reference file for each phase sequentially:1. **Phase 1: Environment Exploration** Read the exploration guidelines to discover raw knowledge seeds: `references/EXPLORATION.md`2. **Phase 2: Trajectory Selection** Once Phase 1 is complete, read the selection criteria to evaluate the trajectory: `references/SELECTION.md`3. **Phase 3: Data Synthesis** Once a trajectory passes Phase 2, read the synthesis instructions to generate the final data: `references/SYNTHESIS.md`

Frequently asked questions