cohere-multi-env-setup
Configure Cohere across development, staging, and production environments. Use when setting up multi-environment deployments, configuring per-environment API keys, model selection, and rate limit strategies. Trigger with phrases like "cohere environments", "cohere staging", "cohere dev prod", "cohere environment setup", "cohere config by env".
What this skill does
# Cohere Multi-Environment Setup
## Overview
Configure Cohere API v2 across dev/staging/prod with environment-specific API keys, model selection, and budget controls.
## Prerequisites
- Separate Cohere API keys per environment (trial for dev, production for staging/prod)
- Secret management solution (Vault, AWS Secrets Manager, GCP Secret Manager)
- Environment detection in application
## Environment Strategy
| Environment | API Key Type | Model | maxTokens | Caching |
|-------------|-------------|-------|-----------|---------|
| Development | Trial (free) | `command-r7b-12-2024` | 200 | Disabled |
| Staging | Production | `command-r-08-2024` | 1000 | Enabled |
| Production | Production | `command-a-03-2025` | 4096 | Enabled |
## Instructions
### Step 1: Configuration Structure
```typescript
// src/config/cohere.ts
type Environment = 'development' | 'staging' | 'production';
interface CohereEnvConfig {
chatModel: string;
embedModel: string;
rerankModel: string;
maxTokens: number;
cacheEnabled: boolean;
cacheTtlMs: number;
retries: number;
timeoutSeconds: number;
}
const configs: Record<Environment, CohereEnvConfig> = {
development: {
chatModel: 'command-r7b-12-2024', // Fastest, cheapest
embedModel: 'embed-v4.0',
rerankModel: 'rerank-v3.5',
maxTokens: 200, // Limit for dev
cacheEnabled: false, // See real responses
cacheTtlMs: 0,
retries: 1, // Fail fast in dev
timeoutSeconds: 30,
},
staging: {
chatModel: 'command-r-08-2024', // Mid-tier for testing
embedModel: 'embed-v4.0',
rerankModel: 'rerank-v3.5',
maxTokens: 1000,
cacheEnabled: true,
cacheTtlMs: 5 * 60 * 1000, // 5 minutes
retries: 3,
timeoutSeconds: 60,
},
production: {
chatModel: 'command-a-03-2025', // Best quality
embedModel: 'embed-v4.0',
rerankModel: 'rerank-v3.5',
maxTokens: 4096,
cacheEnabled: true,
cacheTtlMs: 15 * 60 * 1000, // 15 minutes
retries: 5,
timeoutSeconds: 120,
},
};
function detectEnvironment(): Environment {
const env = process.env.NODE_ENV ?? 'development';
if (['development', 'staging', 'production'].includes(env)) {
return env as Environment;
}
return 'development';
}
export function getCohereConfig(): CohereEnvConfig & { environment: Environment } {
const env = detectEnvironment();
return { ...configs[env], environment: env };
}
```
### Step 2: Environment-Aware Client
```typescript
// src/cohere/client.ts
import { CohereClientV2 } from 'cohere-ai';
import { getCohereConfig } from '../config/cohere';
let instance: CohereClientV2 | null = null;
export function getCohere(): CohereClientV2 {
if (!instance) {
const config = getCohereConfig();
if (!process.env.CO_API_KEY) {
throw new Error(`CO_API_KEY not set for ${config.environment} environment`);
}
instance = new CohereClientV2({
token: process.env.CO_API_KEY,
timeoutInSeconds: config.timeoutSeconds,
});
console.log(`[cohere] Initialized for ${config.environment} (model: ${config.chatModel})`);
}
return instance;
}
```
### Step 3: Secret Management
```bash
# --- Local Development ---
# .env.local (git-ignored)
CO_API_KEY=trial-key-for-dev
# --- GitHub Actions (CI) ---
gh secret set CO_API_KEY --body "production-key-for-ci"
# --- AWS Secrets Manager ---
aws secretsmanager create-secret \
--name cohere/staging/api-key \
--secret-string "staging-production-key"
aws secretsmanager create-secret \
--name cohere/production/api-key \
--secret-string "prod-production-key"
# --- GCP Secret Manager ---
echo -n "staging-key" | gcloud secrets create cohere-api-key-staging --data-file=-
echo -n "prod-key" | gcloud secrets create cohere-api-key-prod --data-file=-
# --- HashiCorp Vault ---
vault kv put secret/cohere/staging api_key="staging-key"
vault kv put secret/cohere/production api_key="prod-key"
```
### Step 4: Environment Guards
```typescript
// Prevent expensive operations in development
function guardExpensiveOperation(operation: string): void {
const config = getCohereConfig();
if (config.environment === 'development') {
// In dev, warn but don't block
console.warn(`[cohere] ${operation} using trial key — limited to 20 calls/min`);
}
}
// Prevent development keys in production
function validateKeyForEnv(): void {
const config = getCohereConfig();
const key = process.env.CO_API_KEY ?? '';
if (config.environment === 'production' && key.length < 30) {
throw new Error('Production requires a production API key (not trial)');
}
}
```
### Step 5: Per-Environment API Calls
```typescript
import { getCohereConfig } from '../config/cohere';
export async function chat(message: string): Promise<string> {
const config = getCohereConfig();
const cohere = getCohere();
const response = await cohere.chat({
model: config.chatModel, // Environment-specific model
messages: [{ role: 'user', content: message }],
maxTokens: config.maxTokens, // Environment-specific limit
});
return response.message?.content?.[0]?.text ?? '';
}
export async function embed(texts: string[]): Promise<number[][]> {
const config = getCohereConfig();
const cohere = getCohere();
const response = await cohere.embed({
model: config.embedModel,
texts,
inputType: 'search_document',
embeddingTypes: config.environment === 'development' ? ['float'] : ['int8'], // Cheaper in prod
});
return response.embeddings.float ?? response.embeddings.int8;
}
```
### Step 6: Docker Compose for Local Multi-Env Testing
```yaml
# docker-compose.yml
services:
app-dev:
build: .
environment:
- NODE_ENV=development
- CO_API_KEY=${CO_API_KEY_DEV}
ports:
- "3000:3000"
app-staging:
build: .
environment:
- NODE_ENV=staging
- CO_API_KEY=${CO_API_KEY_STAGING}
ports:
- "3001:3000"
```
## Output
- Per-environment Cohere configuration (model, tokens, timeout)
- Secret management across dev/staging/prod
- Environment guards preventing misuse
- Docker compose for local multi-env testing
## Error Handling
| Issue | Cause | Solution |
|-------|-------|----------|
| Trial key in production | Wrong secret | Validate key length at startup |
| Rate limited in dev | Trial key limits | Use 20 calls/min budget |
| Model not found | Typo in config | Validate model IDs at startup |
| Config merge fails | Missing environment | Default to development |
## Resources
- [Cohere API Keys](https://dashboard.cohere.com/api-keys)
- [Cohere Rate Limits](https://docs.cohere.com/docs/rate-limits)
- [12-Factor App Config](https://12factor.net/config)
## Next Steps
For observability setup, see `cohere-observability`.
Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.