integration-sync skill
✓ VerifiedSyncs content between Crowdin and connected platforms like Webflow, HubSpot, or Contentful via connectors or the Crowdin CLI.
- GitHub stars
- 10
- Files
- 4
- Last commit
- Nov 9, 2026
- License
- MIT
- Allowed tools
- —
What does the integration-sync skill do?
integration-sync syncs content between Crowdin and connected platforms like Webflow, HubSpot, or Contentful via connectors or the Crowdin CLI.
Summary generated from the skill's SKILL.md.
About the integration-sync skill
Content managers and localization teams use this skill to synchronize text between Crowdin and external platforms like Webflow, HubSpot, Contentful, Zendesk Guide, and Braze. It automates the movement of content by importing new platform entries into Crowdin for translation or pushing finished translations back to the original source. The skill operates through two primary paths: using connector tools within an assistant session or executing commands via the Crowdin CLI in a shell environment.
When an agent loads this skill, it can perform complex loops including discovering app methods, reading integration trees to identify new or updated items, and monitoring job statuses until they reach a finished or failed state. It manages the entire lifecycle of a translation task, from mapping platform entries to Crowdin file IDs to handling pre-translation engines. Users can also configure automated schedules to ensure content stays in sync without manual intervention, such as setting up nightly blog post imports or enabling auto-sync for new platform items.
What an agent can do with it
- 1Import platform contentBring new pages or marketing campaigns from Webflow or HubSpot into Crowdin for translation.
- 2Push translations backSend completed German translations from Crowdin back to a Contentful project.
- 3Monitor sync statusCheck if a specific synchronization job for Zendesk has completed successfully.
- 4Automate content updatesSet up a recurring schedule to automatically sync blog posts every night.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the integration-sync skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the integration-sync skill in Plugin
/plugin marketplace add crowdin/skills /plugin install crowdin@crowdin-skills
Install the integration-sync skill in Claude Code
~/.claude/skills/integration-sync/SKILL.md
$ npx degit crowdin/skills/skills/integration-sync ~/.claude/skills/integration-syncInstall the integration-sync skill in Claude Code (project)
.claude/skills/integration-sync/SKILL.md
$ npx degit crowdin/skills/skills/integration-sync .claude/skills/integration-syncInstall the integration-sync skill in Codex
~/.agents/skills/integration-sync/SKILL.md
$ npx degit crowdin/skills/skills/integration-sync ~/.agents/skills/integration-syncInstall the integration-sync skill in Gemini CLI
~/.gemini/skills/integration-sync/SKILL.md
$ npx degit crowdin/skills/skills/integration-sync ~/.gemini/skills/integration-syncInstall the integration-sync skill in Claude.ai
npx degit crowdin/skills/skills/integration-sync integration-sync && zip -r integration-sync.zip integration-sync # claude.ai → Customize → Skills → + → Create skill → Upload a skill → integration-sync.zip
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work
- Source repository linked and reachablecrowdin/skills/skills/integration-sync is public and reachablegithub.com/crowdin/skills/tree/HEAD/skills/integration-sync ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-09github.com/crowdin/skills/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/crowdin/skills/blob/HEAD/skills/integration-sync/ ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/crowdin/skills/blob/HEAD/skills/integration-sync/ ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 66 linesgithub.com/crowdin/skills/blob/HEAD/skills/integration-sync/ ↗Pass
SKILL.md
View on GitHubIntegration sync
Integration apps share one set of API methods, and this skill is the loop over them. The steps and their done conditions are below; the tool or command for each step is in one reference per path.
Pick the path
- Connector tools present in the session (the Crowdin MCP server, as in the assistant built into Crowdin, Cowork, Claude.ai or ChatGPT): follow references/connector.md.
- A shell with the Crowdin CLI and no connector tools: follow references/cli.md.
- Both: the connector, unless the user asked for commands or pasted a
crowdin appcommand. Say in one line which path you took. - Neither: describe the loop in the user's terms and name both ways to run it.
Everything below holds on both paths.
The integration loop
Work through the steps in order; each ends on its done condition. An app whose methods are not the shared set is driven through discovery (step 2) and its own list method, with the same rules for bodies, jobs and state changes; the reference says whether the path can drive it at all.
- Find the app and the project. Find the app among the installed ones and read its permissions.
permissions.projectsays which projects the app may serve:own(every project the user owns) orrestrictedwith a list of IDs. It does not say which project the integration is connected in, and an unconnected project answers 403. With one ID in arestrictedlist, use it; otherwise ask the user for the project. Done when you hold the app identifier and the project ID. - Discover. Learn which methods the app offers and what each takes. Done when every planned call has its method and required parameters from a description. When a description has no parameters, read the app's documentation link or ask the user. A write goes out with field names taken from a description, the app's documentation, or the user, never guessed.
- Read the integration tree. List the platform's content as the app sees it. Files carry a
type; folders do not. Done when each item to import is matched to exactly one entry with atype; match onpath, since names repeat. An entry'snotSynced: truemarks an item never imported into Crowdin, and it turns false after the import. The other flags (synced,isNew,isUpdated) read false on an app that does not compute them, so whether an item is in Crowdin is read fromnotSyncedalone. - Import into Crowdin. Send the selected entries from step 3's output, in the shape the reference gives. Done when the call returns a job ID.
- Follow the job. Read the job until
statusisfinishedorfailed. Done when you have seen that status: a job is reported finished only then, and a job you stopped following is reported as still running, with its ID and how to check it. Afailedjob is reported with itsinfo; "Finished with errors. See error logs." can still have delivered part of the work, and those logs are not in the API: send the user to the app's page in the Crowdin project to read them. The job also carriesprogress,payloadanddata; some apps storepayloadanddataas JSON text, sometimes encoded more than once, so decode until the result is no longer a string. - Map to Crowdin files. List the Crowdin-side files the app manages, matched by name under the right parent folder. Crowdin file IDs are different from the integration's IDs. Done when each imported item has its Crowdin file ID.
- Translate. In Crowdin: pre-translation when the user asked for it (the reference names it), or the project's translators. A pre-translation job ends
finishedwhether or not it added anything, so read what it applied (the reference says how) before reporting it. When it applied nothing, say so and ask the user to pick another engine or method, or to fix this engine's setup in Crowdin (its credentials, projects and languages) before a second run. Progress is read per Crowdin file ID and reports translation and approval progress per language. Done when every target language shows the progress the user asked for, or the user says to push as is. - Push back. Send a map of Crowdin file ID to language codes, then step 5 again. The push request has no approval option, so unapproved translations go out with approved ones. Name the languages whose approval progress is below 100 (step 7), and which of them hold machine or AI output from a pre-translation: in the offer when you propose the push, in the report when the user already asked for it. Done when the push job is
finished.
What's new on the platform
A question about new or changed content runs steps 1 to 3 and answers from the tree. Done when every entry with a type is counted as new or already in Crowdin.
- New: the entries with a
typethat step 3 reads as not yet in Crowdin. An app that marks no entrynotSynced: truemay not compute the flag (an app that loads its tree one level at a time does not by default): count against the Crowdin-side files (step 6) instead. List the new items bypath, grouped by folder, and add how many items are already in Crowdin and whether auto-sync is set (the sync settings for both providers), so the user knows whether new items arrive on their own. - Changed: the tree has no reliable sign of an edit to an item already in Crowdin.
isUpdatedmay not be computed at all (step 3), and a date the app shows (Webflow's tooltip "Last update") also moves when a push writes translations back. Say so, and offer to re-import the items the user wants refreshed.
Opaque IDs
An entry ID is copied, never written. It is whatever string the app returned, and it can be JSON text full of quotes and apostrophes (Webflow's is). A Webflow, HubSpot or other platform ID on its own matches nothing. Select entries from the app's own output and carry the ID byte for byte; the reference says how on each path.
Calls that change state
Import and push change content in Crowdin or in the external platform. A settings write, a sync-settings write and a job cancel change the app's configuration or stop work. Run a state-changing call only when the user asked for that change.
Import and push both say "update" in their names and point in opposite directions. Name the direction you understood before sending either: "into Crowdin" is an import, "back to the platform" is a push, and a push overwrites the platform's content.
Auto-sync and schedules
The sync settings hold two lists, one per provider:
provider |
Direction | files shape |
|---|---|---|
integration |
Platform to Crowdin: these items are imported on schedule | Array of tree entries, each with "schedule": true |
crowdin |
Crowdin to platform: these files' translations are pushed on schedule | Map of Crowdin file ID to languages, {"1024": ["uk"]} |
A sync-settings write replaces the whole list for its provider and turns on a sync schedule when none is set. The schedule's frequency is in the app settings, and a settings write replaces the whole settings object too: a change is sent as the full current settings plus the change, and the reference says which values the path can carry. When the app offers new-integration-files in its settings, turning it on adds new platform items to auto-sync as they appear; that is how "every new blog post" is expressed.
A settings change is show-then-send:
- Read the current value: the sync settings for the same
provider, or the app settings. - Build the new value as the current value plus the change.
- Show the user the before and after and exactly what will be sent, in the form the reference gives for show-then-send.
- Send it when the user confirms. When the user is away, the run ends at step 3: report the prepared change and how to send it.
Files in this skill
4integration-sync skill questions
How do I install the integration-sync skill in Claude Code?
Run npx degit crowdin/skills/skills/integration-sync ~/.claude/skills/integration-sync. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the integration-sync skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
What can I do with the integration sync skill?
You can import platform content into Crowdin, push translations back to your platform, check for new content, monitor integration jobs, or set up sync schedules.
How do I know if a job failed?
A failed job is reported with its specific info. If it says 'Finished with errors', some work might have been delivered, but you must check the app's page in the Crowdin project for detailed error logs.
Does pushing translations overwrite my platform content?
Yes, a push request sends translations back to the platform and overwrites the existing content there.