Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Deploy Grammarly integrations to Vercel, Fly.io, and Cloud Run platforms. Use when deploying Grammarly-powered applications to production, configuring platform-specific secrets, or setting up deployment pipelines. Trigger with phrases like "deploy grammarly", "grammarly Vercel", "grammarly production deploy", "grammarly Cloud Run", "grammarly Fly.io".
.claude/skills/jeremylongshore-grammarly-deploy-integration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -8% | 0% |
Deploy a containerized Grammarly writing assistant integration service with Docker. This skill covers building a production image that connects to the Grammarly Text API for checking grammar, clarity, and tone across submitted text. Includes environment configuration for OAuth client credentials, health checks that verify API token exchange and text analysis endpoints, and rolling update strategies for zero-downtime deployments serving real-time writing feedback.
dockerfileFROM node:20-slim AS builder WORKDIR /app COPY package*.json ./ RUN npm ci COPY tsconfig.json ./ COPY src/ ./src/ RUN npm run build FROM node:20-slim RUN addgroup --system app && adduser --system --ingroup app app WORKDIR /app COPY --from=builder /app/dist ./dist COPY --from=builder /app/node_modules ./node_modules COPY package*.json ./ USER app EXPOSE 3000 HEALTHCHECK --interval=30s --timeout=5s --retries=3 \ CMD curl -f http://localhost:3000/health || exit 1 CMD ["node", "dist/index.js"]
bashexport GRAMMARLY_CLIENT_ID="client_xxxxxxxxxxxx" export GRAMMARLY_CLIENT_SECRET="secret_xxxxxxxxxxxx" export GRAMMARLY_BASE_URL="https://api.grammarly.com/ecosystem/api" export LOG_LEVEL="info" export PORT="3000" export NODE_ENV="production"
typescriptimport express from 'express'; const app = express(); app.get('/health', async (req, res) => { try { const tokenRes = await fetch(`${process.env.GRAMMARLY_BASE_URL}/v1/oauth/token`, { method: 'POST', headers: { 'Content-Type': 'application/x-www-form-urlencoded' }, body: new URLSearchParams({ grant_type: 'client_credentials', client_id: process.env.GRAMMARLY_CLIENT_ID!, client_secret: process.env.GRAMMARLY_CLIENT_SECRET!, }), }); if (!tokenRes.ok) throw new Error(`Grammarly OAuth returned ${tokenRes.status}`); res.json({ status: 'healthy', service: 'grammarly-integration', timestamp: new Date().toISOString() }); } catch (error) { res.status(503).json({ status: 'unhealthy', error: (error as Error).message }); } });
bashdocker build -t grammarly-integration:latest .
bashdocker run -d --name grammarly-integration \ -p 3000:3000 \ -e GRAMMARLY_CLIENT_ID -e GRAMMARLY_CLIENT_SECRET -e GRAMMARLY_BASE_URL \ grammarly-integration:latest
bashcurl -s http://localhost:3000/health | jq .
bashdocker build -t grammarly-integration:v2 . && \ docker stop grammarly-integration && \ docker rm grammarly-integration && \ docker run -d --name grammarly-integration -p 3000:3000 \ -e GRAMMARLY_CLIENT_ID -e GRAMMARLY_CLIENT_SECRET -e GRAMMARLY_BASE_URL \ grammarly-integration:v2
| Issue | Cause | Fix | |-------|-------|-----| | 401 Unauthorized | Invalid client credentials | Regenerate credentials in Grammarly Developer Hub | | 403 Forbidden | App not approved for API access | Submit app for review in Grammarly partner portal | | 400 Bad Request | Text below 30-word minimum | Validate input length before sending to API | | 429 Rate Limited | Exceeding API rate limits | Cache results for identical text; implement backoff | | Token exchange fails | Incorrect grant_type or URL | Verify OAuth endpoint and client_credentials flow |
See grammarly-webhooks-events.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 14,418 | 17,378 | +21% | 1 | 1 | 0% | 2,879 | 3,653 | +27% | 0 | 0 | — |
case-02 | fail→pass | 18,333 | 13,270 | -28% | 1 | 1 | 0% | 3,406 | 3,159 | -7% | 0 | 0 | — |
case-03 | fail→pass | 16,843 | 14,539 | -14% | 1 | 1 | 0% | 3,733 | 3,490 | -7% | 0 | 0 | — |
case-04 | fail→pass | 6,352 | 7,120 | +12% | 1 | 1 | 0% | 1,200 | 1,560 | +30% | 0 | 0 | — |
case-05 | fail→pass | 14,906 | 8,518 | -43% | 1 | 1 | 0% | 2,041 | 1,884 | -8% | 0 | 0 | — |
case-06 | pass→pass | 12,475 | 12,336 | -1% | 1 | 1 | 0% | 2,543 | 2,583 | +2% | 0 | 0 | — |
case-07 | fail→pass | 16,518 | 4,981 | -70% | 1 | 1 | 0% | 2,264 | 2,084 | -8% | 0 | 0 | — |
case-08 | pass→pass | 21,717 | 18,797 | -13% | 1 | 1 | 0% | 2,367 | 3,520 | +49% | 0 | 0 | — |
case-09 | pass→pass | 14,692 | 8,847 | -40% | 1 | 1 | 0% | 2,650 | 1,497 | -44% | 0 | 0 | — |
case-10 | fail→pass | 13,721 | 5,179 | -62% | 1 | 1 | 0% | 1,541 | 2,162 | +40% | 0 | 0 | — |
case-11 | pass→pass | 13,614 | 10,279 | -24% | 1 | 1 | 0% | 1,617 | 2,109 | +30% | 0 | 0 | — |
case-12 | pass→pass | 11,474 | 12,196 | +6% | 1 | 1 | 0% | 1,981 | 2,377 | +20% | 0 | 0 | — |
case-13 | fail→fail | 18,820 | 16,426 | -13% | 1 | 1 | 0% | 2,326 | 3,005 | +29% | 0 | 0 | — |
case-14 | fail→pass | 16,343 | 8,813 | -46% | 1 | 1 | 0% | 2,014 | 1,654 | -18% | 0 | 0 | — |
case-15 | pass→pass | 16,955 | 15,295 | -10% | 1 | 1 | 0% | 2,003 | 2,795 | +40% | 0 | 0 | — |
case-16 | pass→pass | 5,621 | 8,285 | +47% | 1 | 1 | 0% | 1,027 | 1,592 | +55% | 0 | 0 | — |
case-17 | fail→pass | 10,060 | 5,619 | -44% | 1 | 1 | 0% | 1,730 | 2,104 | +22% | 0 | 0 | — |
case-18 | pass→pass | 6,202 | 8,809 | +42% | 1 | 1 | 0% | 1,133 | 1,623 | +43% | 0 | 0 | — |
case-19 | pass→pass | 9,803 | 8,820 | -10% | 1 | 1 | 0% | 1,651 | 1,630 | -1% | 0 | 0 | — |
case-20 | pass→pass | 15,075 | 17,328 | +15% | 1 | 1 | 0% | 2,648 | 2,895 | +9% | 0 | 0 | — |
case-21 | pass→pass | 17,729 | 21,025 | +19% | 1 | 1 | 0% | 2,594 | 3,792 | +46% | 0 | 0 | — |
case-22 | pass→pass | 11,065 | 10,780 | -3% | 1 | 1 | 0% | 2,180 | 3,066 | +41% | 0 | 0 | — |
case-23 | pass→pass | 8,965 | 10,620 | +18% | 1 | 1 | 0% | 1,906 | 2,825 | +48% | 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. 23 cases were attempted. The headline lift of +35 percentage points is the difference between those two pass rates over the 23 comparable cases.
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.