← Back to Skills Marketplace
Creem Store Agent
by
Dmitrii Malakhov
· GitHub ↗
· v1.0.0
· MIT-0
109
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install creem-store-agent
Description
AI-powered Creem store monitor — alerts, churn analysis, autonomous actions via Telegram
README (SKILL.md)
Creem Store Agent
AI-powered monitoring for your Creem store. Sends real-time Telegram alerts for sales, subscriptions, disputes, and refunds. Uses Claude AI to analyze churn events and autonomously recommend retention actions.
Commands
/creem-status— Check store connection and webhook status/creem-report— Daily revenue summary (MRR, churn, new sales)
Features
- Real-time alerts: Formatted Telegram notifications for all Creem events
- AI churn analysis: Claude Haiku analyzes cancellations and recommends retention actions
- Autonomous actions: Create retention discounts or pause subscriptions via inline buttons
- Event deduplication: Handles Creem webhook retries gracefully
- HMAC verification: Validates webhook signatures for security
Setup
- Install:
clawhub install creem-store-agent - Set environment variables (see
.env.example) - Expose webhook URL:
ngrok http 3000(development) - Register webhook in Creem dashboard:
https://your-ngrok-url.ngrok.io/webhook/creem
Environment Variables
| Variable | Description |
|---|---|
CREEM_API_KEY |
Creem API key (test: creem_test_xxx) |
CREEM_WEBHOOK_SECRET |
Webhook signing secret from Creem dashboard |
TELEGRAM_BOT_TOKEN |
Telegram bot token from @BotFather |
TELEGRAM_CHAT_ID |
Telegram chat ID for notifications |
ANTHROPIC_API_KEY |
Anthropic API key for Claude Haiku |
Usage Guidance
This skill appears to do exactly what it claims: receive and verify Creem webhooks, analyze churn with Anthropic/Claude, notify via Telegram, and optionally call Creem to create discounts or pause subscriptions. Before installing or enabling it for production, consider the following:
- Financial impact: the agent can auto-execute retention actions (create discounts or pause subscriptions) when LLM confidence ≥ 80%. If you don't want automatic changes, keep it in manual-approval mode or lower privileges on the Creem API key.
- Test in sandbox: run the demo with test Creem credentials and a test Telegram chat to confirm behavior and button flows before connecting to a live store.
- Least privilege: create a Creem API key scoped as narrowly as possible (if Creem supports scoped keys) and rotate it regularly. Limit the Telegram bot's chat permissions and keep TELEGRAM_CHAT_ID restricted to authorized operators.
- Monitor and logs: ensure you have visibility (logs/alerts) for every auto-executed action so you can audit and revert if needed.
- Review dependencies and run tests: the repo includes tests and uses common npm packages; run npm audit and the included test suite locally if you want extra confidence.
If you want to be extra cautious, omit ANTHROPIC_API_KEY (fallback rule-based behavior is present) or disable autonomous execution in configuration before connecting to a production Creem key.
Capability Analysis
Type: OpenClaw Skill
Name: creem-store-agent
Version: 1.0.0
The creem-store-agent bundle is a legitimate AI-powered monitoring tool for the Creem payment platform. It implements security best practices, including HMAC-SHA256 webhook signature verification with timing-safe comparisons in src/webhook-handler.ts and event deduplication. The code logic is transparent, follows its stated purpose of churn analysis and Telegram notifications, and includes an extensive test suite. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
Capability Assessment
Purpose & Capability
Name/description align with required binaries and environment variables. CREEM_API_KEY, CREEM_WEBHOOK_SECRET, TELEGRAM_BOT_TOKEN/CHAT_ID, and ANTHROPIC_API_KEY are all plausibly required for: verifying webhooks, calling Creem SDK, sending Telegram messages, and calling Anthropic. The code imports/uses the listed SDKs (creem, @anthropic-ai/sdk, node-telegram-bot-api) and implements the features described (webhook handler, LLM analyzer, action executor).
Instruction Scope
SKILL.md and code instruct the agent to register an HTTP webhook route, verify HMAC signatures, fetch context from Creem, call Anthropic for analysis, and send Telegram messages; these are within the stated scope. Important behavioral detail: the skill can autonomously auto-execute billing-impacting actions (create discounts, pause subscriptions) when the LLM confidence >= 80%. This is a deliberate capability but has real financial impact and should be considered by operators. Demo code also reads a local .env for convenience (development only).
Install Mechanism
There is no installer that downloads arbitrary code at runtime — the repository is instruction-and-code based and relies on normal npm packages declared in package.json (creem, @anthropic-ai/sdk, node-telegram-bot-api). No suspicious download URLs or extract steps are present in the provided metadata.
Credentials
Requested environment variables (CREEM_API_KEY, CREEM_WEBHOOK_SECRET, TELEGRAM_BOT_TOKEN, TELEGRAM_CHAT_ID, ANTHROPIC_API_KEY) are directly required by the functionality. No unrelated credentials (cloud provider keys, DB passwords, etc.) are requested. CREEM_API_KEY is defined as primaryEnv which matches the skill's ability to act on subscriptions/discounts.
Persistence & Privilege
The skill registers an HTTP route (ctx.api.registerHttpRoute) and runs code that can autonomously call Creem APIs to modify subscriptions or create discounts. It does not request 'always: true' and uses in-memory pending state (no persistent system-wide config changes). The combination of autonomous invocation with write-capable Creem credentials is intended but increases blast radius — operators should be aware and control the auto-execute threshold and credentials provided.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install creem-store-agent - After installation, invoke the skill by name or use
/creem-store-agent - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: AI-powered Creem store monitor with churn analysis and autonomous retention actions
Metadata
Frequently Asked Questions
What is Creem Store Agent?
AI-powered Creem store monitor — alerts, churn analysis, autonomous actions via Telegram. It is an AI Agent Skill for Claude Code / OpenClaw, with 109 downloads so far.
How do I install Creem Store Agent?
Run "/install creem-store-agent" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Creem Store Agent free?
Yes, Creem Store Agent is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Creem Store Agent support?
Creem Store Agent is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Creem Store Agent?
It is built and maintained by Dmitrii Malakhov (@malakhov-dmitrii); the current version is v1.0.0.
More Skills