Skip to main content
AI/MLjeremylongshore

grammarly-multi-env-setup

'Configure Grammarly across multiple environments.

Stars
2,267
Source
jeremylongshore/claude-code-plugins-plus-skills
Updated
2026-05-31
Slug
jeremylongshore--claude-code-plugins-plus-skills--grammarly-multi-env-setup
View on GitHubRaw SKILL.md

// install — copy + paste into any project

mkdir -p .claude/skills && curl -fsSL https://raw.githubusercontent.com/jeremylongshore/claude-code-plugins-plus-skills/HEAD/plugins/saas-packs/grammarly-pack/skills/grammarly-multi-env-setup/SKILL.md -o .claude/skills/grammarly-multi-env-setup.md

Drops the SKILL.md into .claude/skills/grammarly-multi-env-setup.md. Works with Claude Code, Cursor, and any agent that loads SKILL.md files from .claude/skills/.

Grammarly Multi-Environment Setup

Overview

Grammarly integration requires environment separation to isolate API credentials, enforce team-scoped style guides, and manage rate limits per tier. Development uses mock API responses for fast iteration without consuming quota, staging connects to the Grammarly sandbox for real grammar checks with test content, and production runs against the live API with full team configurations. Each environment has its own client credentials and style guide settings to prevent dev experiments from affecting production writing standards.

Environment Configuration

const grammarlyConfig = (env: string) => ({
  development: {
    clientId: process.env.GRAMMARLY_DEV_CLIENT_ID!, clientSecret: process.env.GRAMMARLY_DEV_CLIENT_SECRET!,
    baseUrl: "http://localhost:3100/mock-grammarly", useMockApi: true, concurrency: 1, intervalCap: 2,
  },
  staging: {
    clientId: process.env.GRAMMARLY_STG_CLIENT_ID!, clientSecret: process.env.GRAMMARLY_STG_CLIENT_SECRET!,
    baseUrl: "https://api.grammarly.com/sandbox", useMockApi: false, concurrency: 2, intervalCap: 5,
  },
  production: {
    clientId: process.env.GRAMMARLY_PROD_CLIENT_ID!, clientSecret: process.env.GRAMMARLY_PROD_CLIENT_SECRET!,
    baseUrl: "https://api.grammarly.com", teamId: process.env.GRAMMARLY_TEAM_ID!, concurrency: 5, intervalCap: 10,
  },
}[env]);

Environment Files

# Per-env files: .env.development, .env.staging, .env.production
GRAMMARLY_{DEV|STG|PROD}_CLIENT_ID=<client-id>
GRAMMARLY_{DEV|STG|PROD}_CLIENT_SECRET=<secret>
GRAMMARLY_BASE_URL={http://localhost:3100/mock|https://api.grammarly.com/sandbox|https://api.grammarly.com}
GRAMMARLY_TEAM_ID=<team-id>          # staging + production only

Environment Validation

function validateGrammarlyEnv(env: string): void {
  const suffix = { development: "_DEV", staging: "_STG", production: "_PROD" }[env];
  const required = [`GRAMMARLY${suffix}_CLIENT_ID`, `GRAMMARLY${suffix}_CLIENT_SECRET`];
  if (env === "production") required.push("GRAMMARLY_TEAM_ID");
  const missing = required.filter((k) => !process.env[k]);
  if (missing.length) throw new Error(`Missing Grammarly vars for ${env}: ${missing.join(", ")}`);
}

Promotion Workflow

# 1. Verify mock API coverage in dev
npm test -- --grep "grammarly" --env development

# 2. Run style guide checks against Grammarly sandbox
curl -X POST "https://api.grammarly.com/sandbox/check" \
  -H "Authorization: Bearer $GRAMMARLY_STG_TOKEN" -d @test-content.json

# 3. Compare suggestion quality between staging and baseline
node scripts/grammarly-diff.js --env staging --baseline expected-suggestions.json

# 4. Rotate credentials and deploy to production
GRAMMARLY_PROD_CLIENT_SECRET=$(vault read -field=secret grammarly/prod)
npm run deploy -- --env production

Environment Matrix

Setting Dev Staging Prod
API Endpoint Mock (localhost) Grammarly Sandbox Live API
Team Style Guide None Test guide Production guide
Rate Limit 1 concurrent / 2 per interval 2 / 5 5 / 10
Quota Tracking Disabled Enabled Enabled + alerts
User Scope Developer only QA team All team members

Error Handling

Issue Cause Fix
401 Unauthorized Client credentials expired or wrong env Rotate credentials in Grammarly developer console for target env
Rate limit 429 Concurrency exceeds tier plan Lower intervalCap or upgrade Grammarly plan
Mock API returns empty Local mock server not running Start mock with npm run mock:grammarly before dev tests
Style guide mismatch Team ID points to wrong guide Verify GRAMMARLY_TEAM_ID matches the intended style guide
Suggestions differ across envs Sandbox uses older model version Expected behavior; validate core rules only in staging

Prerequisites

  • Separate credentials, network destinations, and configuration revisions for sandbox, staging, and production.
  • A secret-manager reference per environment, protected promotion approval, synthetic fixtures, and a production rollback revision.

Instructions

  1. Validate the selected environment against an explicit allowlist before reading credentials or sending text.
  2. Apply versioned, idempotent configuration changes in sandbox and run synthetic retention and behavior probes.
  3. Promote to staging only with owner approval, bounded fixtures, and redacted observability compared with baseline.
  4. Canary one production integration after protected review; halt and restore the prior revision for a scope, retention, quota, or error regression.
  5. Record only environment, configuration revision, aggregate counts, and rollback result in the promotion receipt.

Output

Produce a promotion receipt with environment, configuration revision, synthetic test totals, staging/canary result, owner approval, and rollback reference. Exclude credentials, source text, and identities.

Examples

env=staging; config=r22; fixture=writing-v4; retention=none; behavior=pass; rollback=r21 is evidence for controlled promotion.

Resources

Next Steps

See grammarly-deploy-integration.