From lokalise-pack
Execute Lokalise primary workflow: Upload source files and manage translation keys. Use when uploading translation files, creating/updating keys, or managing source strings in Lokalise projects. Trigger with phrases like "lokalise upload", "lokalise push keys", "lokalise source strings", "add translations to lokalise".
How this skill is triggered — by the user, by Claude, or both
Slash command
/lokalise-pack:lokalise-core-workflow-aThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Primary workflow for uploading source translation files and managing keys in Lokalise.
Primary workflow for uploading source translation files and managing keys in Lokalise.
lokalise-install-auth setupRead(${CLAUDE_SKILL_DIR}/references/implementation-guide.md)| Error | Cause | Solution |
|---|---|---|
400 Invalid file format | Unsupported format | Check supported formats |
400 Key already exists | Duplicate key name | Use replace_modified or unique names |
413 Payload too large | File too big | Split into smaller files |
429 Rate limited | Too many requests | Use --poll flag, wait between uploads |
lokalise2 file upload \
--token "$LOKALISE_API_TOKEN" \
--project-id "$LOKALISE_PROJECT_ID" \
--file "./locales/en.json" \
--lang-iso en \
--cleanup-mode # Remove keys not in file
--replace-modified # Update existing translations
--fill-empty # Copy base to empty translations
--poll
For downloading translations, see lokalise-core-workflow-b.
npx claudepluginhub terrylica/claude-code-plugins-plus --plugin lokalise-pack4plugins reuse this skill
First indexed Jul 11, 2026
Guides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Synthesizes the current conversation into a structured spec (PRD) and publishes it to the project issue tracker with a ready-for-agent label, without interviewing the user.