Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Configure Grammarly CI/CD integration with GitHub Actions and testing. Use when setting up automated testing, configuring CI pipelines, or integrating Grammarly tests into your build process. Trigger with phrases like "grammarly CI", "grammarly GitHub Actions", "grammarly automated tests", "CI grammarly".
.claude/skills/jeremylongshore-grammarly-ci-integration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 61% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -8% | 0% |
Set up CI/CD for Grammarly text analysis integrations: run unit tests with mocked grammar check and suggestion responses on every PR, validate live API connectivity for text scoring on merge to main. Grammarly's Text API provides writing quality scores, grammar corrections, and tone detection, so CI pipelines verify content quality gates, documentation linting, and automated writing feedback workflows.
yaml# .github/workflows/grammarly-ci.yml name: Grammarly CI on: pull_request: paths: ['src/**', 'docs/**', 'tests/**'] push: branches: [main] jobs: unit-tests: runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 - uses: actions/setup-node@v4 with: { node-version: '20' } - run: npm ci - run: npm test -- --reporter=verbose integration-tests: if: github.ref == 'refs/heads/main' needs: unit-tests runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 - uses: actions/setup-node@v4 with: { node-version: '20' } - run: npm ci - run: npm run test:integration env: GRAMMARLY_CLIENT_ID: ${{ secrets.GRAMMARLY_CLIENT_ID }} GRAMMARLY_CLIENT_SECRET: ${{ secrets.GRAMMARLY_CLIENT_SECRET }}
typescript// tests/grammarly-service.test.ts import { describe, it, expect, vi } from 'vitest'; import { checkDocumentation } from '../src/grammarly-service'; vi.mock('../src/grammarly-client', () => ({ GrammarlyClient: vi.fn().mockImplementation(() => ({ checkText: vi.fn().mockResolvedValue({ overall_score: 87, alerts: [ { type: 'grammar', message: 'Subject-verb disagreement', offset: 12, length: 5, replacements: ['are'] }, { type: 'clarity', message: 'Consider simplifying', offset: 45, length: 20, replacements: ['use'] }, ], tone: { formal: 0.8, confident: 0.7 }, }), getSuggestions: vi.fn().mockResolvedValue({ suggestions: [{ text: 'Rephrase for clarity', category: 'engagement' }], }), })), })); describe('Grammarly Service', () => { it('checks documentation quality and returns score', async () => { const result = await checkDocumentation('The data is ready for review.'); expect(result.overall_score).toBeGreaterThan(80); expect(result.alerts).toHaveLength(2); }); });
typescript// tests/integration/grammarly.integration.test.ts import { describe, it, expect } from 'vitest'; const hasCredentials = !!process.env.GRAMMARLY_CLIENT_ID; describe.skipIf(!hasCredentials)('Grammarly Live API', () => { it('analyzes text via Text API', async () => { const tokenRes = await fetch('https://api.grammarly.com/v1/oauth/token', { method: 'POST', headers: { 'Content-Type': 'application/json' }, body: JSON.stringify({ client_id: process.env.GRAMMARLY_CLIENT_ID, client_secret: process.env.GRAMMARLY_CLIENT_SECRET, grant_type: 'client_credentials', }), }); expect(tokenRes.status).toBe(200); const { access_token } = await tokenRes.json(); expect(access_token).toBeDefined(); }); });
| CI Issue | Cause | Fix | |----------|-------|-----| | 401 Unauthorized | Invalid client credentials | Regenerate at developer.grammarly.com | | OAuth token expired | Token TTL exceeded | Implement token refresh before each test run | | Score below threshold | Content quality regression | Set minimum score in CI config (e.g., 75) and fix flagged alerts | | Rate limit (429) | Too many text check requests | Batch text submissions and add throttling | | Empty suggestions | Text too short for analysis | Ensure test inputs are at least 50 characters |
For deployment, see grammarly-deploy-integration.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→fail | 16,147 | 15,802 | -2% | 1 | 1 | 0% | 3,302 | 4,479 | +36% | 0 | 0 | — |
case-04 | pass→pass | 12,252 | 1,970 | -84% | 1 | 1 | 0% | 1,505 | 1,534 | +2% | 0 | 0 | — |
case-05 | pass→pass | 3,552 | 6,860 | +93% | 1 | 1 | 0% | 716 | 1,546 | +116% | 0 | 0 | — |
case-06 | pass→pass | 6,285 | 3,316 | -47% | 1 | 1 | 0% | 1,497 | 1,926 | +29% | 0 | 0 | — |
case-07 | fail→pass | 8,194 | 1,747 | -79% | 1 | 1 | 0% | 1,826 | 1,489 | -18% | 0 | 0 | — |
case-08 | fail→fail | 17,144 | 11,922 | -30% | 1 | 1 | 0% | 2,806 | 2,771 | -1% | 0 | 0 | — |
case-09 | pass→fail | 9,203 | 12,262 | +33% | 1 | 1 | 0% | 1,917 | 2,736 | +43% | 0 | 0 | — |
case-10 | fail→pass | 10,257 | 6,661 | -35% | 1 | 1 | 0% | 935 | 1,508 | +61% | 0 | 0 | — |
case-11 | fail→pass | 12,026 | 9,504 | -21% | 1 | 1 | 0% | 1,454 | 1,513 | +4% | 0 | 0 | — |
case-12 | fail→pass | 8,772 | 2,697 | -69% | 1 | 1 | 0% | 2,007 | 1,736 | -14% | 0 | 0 | — |
case-14 | fail→pass | 11,602 | 8,224 | -29% | 1 | 1 | 0% | 1,870 | 1,718 | -8% | 0 | 0 | — |
case-15 | pass→pass | 14,404 | 10,882 | -24% | 1 | 1 | 0% | 2,371 | 3,023 | +27% | 0 | 0 | — |
case-16 | pass→fail | 22,281 | 13,014 | -42% | 1 | 1 | 0% | 2,461 | 3,302 | +34% | 0 | 0 | — |
case-17 | fail→fail | 16,271 | 21,159 | +30% | 1 | 1 | 0% | 2,558 | 4,070 | +59% | 0 | 0 | — |
case-18 | fail→pass | 13,758 | 7,235 | -47% | 1 | 1 | 0% | 1,332 | 1,463 | +10% | 0 | 0 | — |
case-13 | pass→pass | 9,736 | 6,701 | -31% | 1 | 1 | 0% | 2,220 | 2,581 | +16% | 0 | 0 | — |
case-01 | fail→fail | 17,419 | 18,715 | +7% | 1 | 1 | 0% | 3,254 | 4,193 | +29% | 0 | 0 | — |
case-02 | fail→fail | 16,778 | 21,312 | +27% | 1 | 1 | 0% | 3,489 | 4,663 | +34% | 0 | 0 | — |
case-19 | fail→pass | 8,487 | 11,407 | +34% | 1 | 1 | 0% | 1,326 | 3,321 | +150% | 0 | 0 | — |
case-20 | pass→pass | 14,890 | 10,706 | -28% | 1 | 1 | 0% | 1,934 | 3,370 | +74% | 0 | 0 | — |
case-21 | fail→fail | 23,275 | 18,615 | -20% | 1 | 1 | 0% | 3,483 | 5,061 | +45% | 0 | 0 | — |
case-22 | pass→pass | 10,907 | 12,115 | +11% | 1 | 1 | 0% | 2,085 | 2,544 | +22% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +23 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.