glean-multi-env-setup
Use separate datasource names per environment (wiki_staging vs wiki_prod). Trigger: "glean multi env setup", "multi-env-setup".
Best use case
glean-multi-env-setup is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use separate datasource names per environment (wiki_staging vs wiki_prod). Trigger: "glean multi env setup", "multi-env-setup".
Teams using glean-multi-env-setup should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/glean-multi-env-setup/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How glean-multi-env-setup Compares
| Feature / Agent | glean-multi-env-setup | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use separate datasource names per environment (wiki_staging vs wiki_prod). Trigger: "glean multi env setup", "multi-env-setup".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
SKILL.md Source
# Glean Multi-Environment Setup
## Overview
Glean enterprise search requires environment isolation to prevent test data from polluting production search results. Each environment uses its own datasource names, API tokens, and connector configurations. Sandbox indexes synthetic test documents, staging indexes a curated subset of real documents for search quality validation, and production indexes the full corpus. Connector changes must be tested in staging before promotion to avoid breaking search relevance for end users.
## Environment Configuration
```typescript
const gleanConfig = (env: string) => ({
development: {
apiToken: process.env.GLEAN_API_TOKEN_DEV!, baseUrl: "https://sandbox.glean.com/api/v1",
datasourceSuffix: "_sandbox", indexingEnabled: true, searchQualityChecks: false,
},
staging: {
apiToken: process.env.GLEAN_API_TOKEN_STG!, baseUrl: "https://staging.glean.com/api/v1",
datasourceSuffix: "_staging", indexingEnabled: true, searchQualityChecks: true,
},
production: {
apiToken: process.env.GLEAN_API_TOKEN_PROD!, baseUrl: "https://app.glean.com/api/v1",
datasourceSuffix: "_prod", indexingEnabled: true, searchQualityChecks: false,
},
}[env]);
```
## Environment Files
```bash
# Per-env files: .env.development, .env.staging, .env.production
GLEAN_API_TOKEN_{DEV|STG|PROD}=<token>
GLEAN_BASE_URL=https://{sandbox|staging|app}.glean.com/api/v1
GLEAN_DATASOURCE_SUFFIX={_sandbox|_staging|_prod}
GLEAN_INSTANCE={sandbox|staging|production}
```
## Environment Validation
```typescript
function validateGleanEnv(env: string): void {
const suffix = { development: "_DEV", staging: "_STG", production: "_PROD" }[env];
const required = [`GLEAN_API_TOKEN${suffix}`, "GLEAN_BASE_URL", "GLEAN_INSTANCE"];
const missing = required.filter((k) => !process.env[k]);
if (missing.length) throw new Error(`Missing Glean env vars for ${env}: ${missing.join(", ")}`);
}
```
## Promotion Workflow
```bash
# 1. Index test documents in sandbox
curl -X POST "$GLEAN_BASE_URL/indexing/datasources/wiki_sandbox/documents" \
-H "Authorization: Bearer $GLEAN_API_TOKEN_DEV" -d @test-docs.json
# 2. Validate search quality in staging
curl "$GLEAN_BASE_URL/search" -H "Authorization: Bearer $GLEAN_API_TOKEN_STG" \
-d '{"query": "onboarding guide"}' | jq '.results[:3].title'
# 3. Compare relevance scores against baseline
node scripts/compare-search-quality.js --env staging --baseline baseline.json
# 4. Promote connector config to production
cp connectors/staging/*.json connectors/production/
curl -X POST "$GLEAN_BASE_URL/indexing/datasources/wiki_prod/crawl" \
-H "Authorization: Bearer $GLEAN_API_TOKEN_PROD"
```
## Environment Matrix
| Setting | Dev (Sandbox) | Staging | Prod |
|---------|---------------|---------|------|
| Data Source | Synthetic test docs | Subset of real docs | Full document index |
| Datasource Suffix | `_sandbox` | `_staging` | `_prod` |
| Connectors | Mock connectors | Real connectors | Real connectors |
| User Access | Developers only | QA + developers | All employees |
| Crawl Frequency | Manual | Daily | Continuous |
## Error Handling
| Issue | Cause | Fix |
|-------|-------|-----|
| Datasource not found | Suffix mismatch between env and config | Verify `GLEAN_DATASOURCE_SUFFIX` matches connector registration |
| 401 on indexing API | Token scoped to wrong instance | Regenerate token in the correct Glean admin console |
| Search returns stale results | Crawl not triggered after promotion | Manually trigger crawl via indexing API |
| Connector sync fails | OAuth credentials expired for data source | Re-authorize connector in Glean admin for the target env |
| Staging indexes prod data | Connector config copied without suffix update | Always update datasource names when promoting configs |
## Resources
- [Glean Developer Portal](https://developers.glean.com/)
- [Indexing API](https://developers.glean.com/api-info/indexing/getting-started/overview)
- [Search API](https://developers.glean.com/api/client-api/search/overview)
## Next Steps
See `glean-deploy-integration`.Related Skills
windsurf-multi-env-setup
Configure Windsurf IDE and Cascade AI across team members and project environments. Use when onboarding teams to Windsurf, setting up per-project Cascade configuration, or managing Windsurf settings across development, staging, and production contexts. Trigger with phrases like "windsurf team setup", "windsurf environments", "windsurf multi-project", "windsurf team config", "cascade rules per env".
webflow-multi-env-setup
Configure Webflow across development, staging, and production environments with per-environment API tokens, site IDs, and secret management via Vault/AWS/GCP. Trigger with phrases like "webflow environments", "webflow staging", "webflow dev prod", "webflow environment setup", "webflow config by env".
vercel-multi-env-setup
Configure Vercel across development, preview, and production environments with scoped secrets. Use when setting up per-environment configuration, managing environment-specific variables, or implementing environment isolation on Vercel. Trigger with phrases like "vercel environments", "vercel staging", "vercel dev prod", "vercel environment setup", "vercel env scoping".
veeva-multi-env-setup
Veeva Vault multi env setup for enterprise operations. Use when implementing advanced Veeva Vault patterns. Trigger: "veeva multi env setup".
vastai-multi-env-setup
Configure Vast.ai GPU cloud across dev, staging, and production environments. Use when isolating GPU pools per team, managing API key separation by env, or implementing spending controls per deployment tier. Trigger with phrases like "vastai environments", "vastai staging", "vastai dev prod", "vastai multi-env".
supabase-multi-env-setup
Configure Supabase across development, staging, and production with separate projects, environment-specific secrets, and safe migration promotion. Use when setting up multi-environment deployments, isolating dev from prod data, configuring per-environment Supabase projects, or promoting migrations through environments. Trigger: "supabase environments", "supabase staging", "supabase dev prod", "supabase multi-project", "supabase env config", "database branching".
speak-multi-env-setup
Configure Speak across dev, staging, and production with separate API keys and mock modes. Use when implementing multi env setup, or managing Speak language learning platform operations. Trigger with phrases like "speak multi env setup", "speak multi env setup".
snowflake-multi-env-setup
Configure Snowflake across dev, staging, and production with account-level isolation, zero-copy clones, and environment-specific RBAC. Trigger with phrases like "snowflake environments", "snowflake staging", "snowflake dev prod", "snowflake clone", "snowflake environment setup".
windsurf-workspace-setup
Initialize Windsurf workspace with project-specific AI rules. Activate when users mention "create windsurfrules", "setup workspace", "configure project ai", "initialize windsurf workspace", or "migrate to windsurf". Handles workspace configuration and team standardization. Use when working with windsurf workspace setup functionality. Trigger with phrases like "windsurf workspace setup", "windsurf setup", "windsurf".
windsurf-multi-file-editing
Manage multi-file edits with Cascade coordination. Activate when users mention "multi-file edit", "edit multiple files", "cross-file changes", "refactor across files", or "batch modifications". Handles coordinated multi-file operations. Use when working with windsurf multi file editing functionality. Trigger with phrases like "windsurf multi file editing", "windsurf editing", "windsurf".
shopify-multi-env-setup
Configure Shopify apps across development, staging, and production environments with separate stores, API credentials, and app instances. Trigger with phrases like "shopify environments", "shopify staging", "shopify dev vs prod", "shopify multi-store", "shopify environment setup".
salesforce-multi-env-setup
Configure Salesforce across Developer, Sandbox, and Production environments with proper org management. Use when setting up multi-environment deployments, configuring per-environment credentials, or implementing sandbox-to-production promotion flows. Trigger with phrases like "salesforce environments", "salesforce sandbox", "salesforce dev prod", "salesforce org management", "salesforce sandbox types".