How do I install the Use Datax skill?

Run npx skillmds@latest add askairo/use-datax 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 Use Datax 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 Use Datax?

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 Use Datax free to use?

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

Who published Use Datax?

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

Use Datax by askairo — Agent Skill

Name: Use Datax
Author: askairo

Use Datax

Generate, validate, and run DataX sync jobs for MySQL table transfers. Use when the user needs to move one or more tables between environments, prepare explicit-column DataX JSON, read runtime DB settings from a .codex config directory, or troubleshoot a DataX sync run.

askairo a0a32a3 3 files · 3.7 KB Updated Sep 17, 2026

File contents

Use DataX

Overview

Use this skill to prepare and execute DataX syncs for project databases. It covers runtime config resolution, template-driven job generation, overwrite safety, execution, and fast failure reporting.

Configuration

Read runtime settings from the user's .codex config directory.

Only these values are externalized:

config_dir: directory that contains environment database config files
datax_home: DataX installation root
job_dir: directory for generated executable DataX JSON

Do not hardcode source/target environments, tables, columns, or date ranges in the skill. Derive JDBC settings from the env config files under config_dir. Treat any project-provided DataX JSON template as a structure reference only; when documenting or reproducing it, replace real credentials, hosts, and database names with placeholders.

Template First

When the project already contains a DataX JSON template, use it as the primary shape reference.

Prefer these adjustments over inventing a new layout:

keep the same job nesting and writer overwrite pattern
keep explicit column order aligned between reader and writer
preserve project-specific JDBC option baselines
keep file naming and output location driven by configuration

Do not copy real connection values into skill text or examples.

Workflow

Ask for the source env, target env, table name(s), date range or filter, and whether overwrite/truncate is allowed.
Resolve JDBC settings from config_dir.
Generate DataX JSON into job_dir with explicit columns by default.
For overwrite syncs, set writer preSql / postSql to disable FK checks and truncate the target table.
Validate the JSON before execution: environment, table, columns, and overwrite SQL.
Run DataX from datax_home.
Stop on the first error and report per-table success/failure counts.

Rules

Prefer explicit column lists for nontrivial tables.
Use full overwrite only when the user confirms the target table should be cleared.
Fail fast if the generated JSON points at the wrong environment.
Keep generated job files under the configured job_dir, not inside the skill.
When a project already has local DataX examples, align the generated jobs with those conventions instead of inventing new ones.

References

See references/config.md for the external config boundary used by this skill.

---name: use-dataxdescription: Generate, validate, and run DataX sync jobs for MySQL table transfers. Use when the user needs to move one or more tables between environments, prepare explicit-column DataX JSON, read runtime DB settings from a .codex config directory, or troubleshoot a DataX sync run.---# Use DataX## OverviewUse this skill to prepare and execute DataX syncs for project databases. It covers runtime config resolution, template-driven job generation, overwrite safety, execution, and fast failure reporting.## ConfigurationRead runtime settings from the user's `.codex` config directory.Only these values are externalized:- `config_dir`: directory that contains environment database config files- `datax_home`: DataX installation root- `job_dir`: directory for generated executable DataX JSONDo not hardcode source/target environments, tables, columns, or date ranges in the skill.Derive JDBC settings from the env config files under `config_dir`.Treat any project-provided DataX JSON template as a structure reference only; when documenting or reproducing it, replace real credentials, hosts, and database names with placeholders.## Template FirstWhen the project already contains a DataX JSON template, use it as the primary shape reference.Prefer these adjustments over inventing a new layout:- keep the same job nesting and writer overwrite pattern- keep explicit column order aligned between reader and writer- preserve project-specific JDBC option baselines- keep file naming and output location driven by configurationDo not copy real connection values into skill text or examples.## Workflow1. Ask for the source env, target env, table name(s), date range or filter, and whether overwrite/truncate is allowed.2. Resolve JDBC settings from `config_dir`.3. Generate DataX JSON into `job_dir` with explicit columns by default.4. For overwrite syncs, set writer `preSql` / `postSql` to disable FK checks and truncate the target table.5. Validate the JSON before execution: environment, table, columns, and overwrite SQL.6. Run DataX from `datax_home`.7. Stop on the first error and report per-table success/failure counts.## Rules- Prefer explicit column lists for nontrivial tables.- Use full overwrite only when the user confirms the target table should be cleared.- Fail fast if the generated JSON points at the wrong environment.- Keep generated job files under the configured `job_dir`, not inside the skill.- When a project already has local DataX examples, align the generated jobs with those conventions instead of inventing new ones.## References- See [references/config.md](references/config.md) for the external config boundary used by this skill.

Frequently asked questions