From speak-pack
Configure Speak CI/CD integration with GitHub Actions and automated testing. Use when setting up automated testing, configuring CI pipelines, or integrating Speak language learning tests into your build process. Trigger with phrases like "speak CI", "speak GitHub Actions", "speak automated tests", "CI speak".
How this skill is triggered — by the user, by Claude, or both
Slash command
/speak-pack:speak-ci-integrationThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Integrate Speak language learning API validation into CI/CD pipelines. Covers pronunciation analysis endpoint testing, lesson content validation, API response format verification, and regression testing for language assessment accuracy.
Integrate Speak language learning API validation into CI/CD pipelines. Covers pronunciation analysis endpoint testing, lesson content validation, API response format verification, and regression testing for language assessment accuracy.
Read(${CLAUDE_SKILL_DIR}/references/implementation-guide.md)| Issue | Cause | Solution |
|---|---|---|
| API key invalid | Secret not set | Add SPEAK_API_KEY to repo secrets |
| Audio fixture too large | Uncompressed WAV | Compress to 16-bit mono |
| Lesson validation fails | Missing required field | Check schema and fix JSON files |
| Flaky pronunciation test | Audio quality varies | Use consistent test recordings |
- name: Speak API health check
env:
SPEAK_API_KEY: ${{ secrets.SPEAK_API_KEY }}
run: |
curl -s -H "Authorization: Bearer $SPEAK_API_KEY" \
https://api.speak.com/v1/languages | jq '.languages | length'
See CI/CD implementation details for output format specifications.
npx claudepluginhub bulozb/claude-code-plugins-plus-skills --plugin speak-packGuides 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.
4plugins reuse this skill
First indexed Jul 11, 2026