How do I install the Wordpress Workspace Transcription Smoke Test skill?

Run npx skillmds@latest add automattic/wordpress-workspace-transcription-smoke-test 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 Wordpress Workspace Transcription Smoke Test 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 Wordpress Workspace Transcription Smoke Test?

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 Wordpress Workspace Transcription Smoke Test free to use?

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

Who published Wordpress Workspace Transcription Smoke Test?

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

Wordpress Workspace Transcription Smoke Test by automattic

Name: Wordpress Workspace Transcription Smoke Test
Author: Automattic

Wordpress Workspace Transcription Smoke Test

Run or explain WordPress Workspace transcription endpoint smoke tests using the no-dependency shell script, bearer tokens, site IDs/domains, audio files, selected text, app context, proxy, envelope, and verbose curl debugging. Use when testing `/wpcom/v2/sites/{site}/ai/transcription` or diagnosing transcription endpoint failures.

Automattic Updated Sep 17, 2026

File contents

WordPress Workspace Transcription Smoke Test

Use this skill for direct endpoint testing of WordPress.com transcription.

Workflow

Use the existing script first.
- Script: Tools/wpcom-transcribe.sh
- Endpoint: POST /wpcom/v2/sites/{site}/ai/transcription
- Required: bearer token or auth header, site ID/domain, and audio file.
Keep it dependency-free.
- The script is POSIX shell plus curl.
- Do not add jq, Python, local OAuth flows, or extra dependencies unless the user explicitly asks.
Choose the narrowest invocation.
- Dictation: WPCOM_BEARER_TOKEN="$TOKEN" Tools/wpcom-transcribe.sh --site 123456 --file ./sample.mp3
- Command mode: add --intent command --selected-text "Rewrite this."
- Debug REST proxy: add --envelope.
- Network debugging: add --verbose and optional --proxy <url>.
- Custom context: add --app-context '<json>'.
Protect secrets.
- Never print token values.
- Prefer environment variables or redacted examples.
Interpret failures by layer.
- Local file and MIME detection.
- Auth header or token scope.
- Site ID/domain and selected-site permissions.
- Endpoint response body and HTTP status.
- Proxy, timeout, or WordPress.com API availability.

Product Notes

The app uses the same site-scoped endpoint for dictation and selected-text command mode.
The selected site may provide a server-side wp_guideline skill with slug transcribe, so connected apps share the same spelling, cleanup, and style rules.
The endpoint may create the Transcription guideline as a WordPress Guideline skill on first use.
Saving artifacts is controlled by the save_artifact field in app requests and should create WordPress Guideline artifacts on the selected site.

---name: wordpress-workspace-transcription-smoke-testdescription: Run or explain WordPress Workspace transcription endpoint smoke tests using the no-dependency shell script, bearer tokens, site IDs/domains, audio files, selected text, app context, proxy, envelope, and verbose curl debugging. Use when testing `/wpcom/v2/sites/{site}/ai/transcription` or diagnosing transcription endpoint failures.---# WordPress Workspace Transcription Smoke TestUse this skill for direct endpoint testing of WordPress.com transcription.## Workflow1. Use the existing script first. - Script: `Tools/wpcom-transcribe.sh` - Endpoint: `POST /wpcom/v2/sites/{site}/ai/transcription` - Required: bearer token or auth header, site ID/domain, and audio file.2. Keep it dependency-free. - The script is POSIX shell plus `curl`. - Do not add jq, Python, local OAuth flows, or extra dependencies unless the user explicitly asks.3. Choose the narrowest invocation. - Dictation: `WPCOM_BEARER_TOKEN="$TOKEN" Tools/wpcom-transcribe.sh --site 123456 --file ./sample.mp3` - Command mode: add `--intent command --selected-text "Rewrite this."` - Debug REST proxy: add `--envelope`. - Network debugging: add `--verbose` and optional `--proxy <url>`. - Custom context: add `--app-context '<json>'`.4. Protect secrets. - Never print token values. - Prefer environment variables or redacted examples.5. Interpret failures by layer. - Local file and MIME detection. - Auth header or token scope. - Site ID/domain and selected-site permissions. - Endpoint response body and HTTP status. - Proxy, timeout, or WordPress.com API availability.## Product Notes- The app uses the same site-scoped endpoint for dictation and selected-text command mode.- The selected site may provide a server-side `wp_guideline` skill with slug `transcribe`, so connected apps share the same spelling, cleanup, and style rules.- The endpoint may create the Transcription guideline as a WordPress Guideline skill on first use.- Saving artifacts is controlled by the `save_artifact` field in app requests and should create WordPress Guideline artifacts on the selected site.

Frequently asked questions