← Back to Skills Marketplace
50
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install raai-price-probe-dogovornaya-20260421
Description
Automation skill for raai-price-probe-dogovornaya-20260421.
Usage Guidance
This package looks like a real AI support product, but there are notable inconsistencies you should resolve before installing:
- Metadata mismatch: the registry lists no required env vars, yet SKILL.md requires ANTHROPIC_API_KEY and OPENAI_API_KEY and lists several optional credentials. Treat that as a red flag: confirm with the author which credentials are actually needed and why both LLM keys are required.
- Do not run install.sh or smoke-test.sh until you have inspected their contents. build.sh appears benign, but install.sh and the smoke-test were not shown — they could modify the system, create network connections, or write credentials to disk.
- If you must test, run inside an isolated environment (throwaway VM or container) and avoid running as root. Provide least-privilege credentials (scoped tokens) and avoid reusing high-privilege keys.
- Ask the publisher for a clear install spec and an explanation of what install.sh does, where credentials are stored, and whether any external endpoints are contacted. Prefer packages whose registry metadata and SKILL.md align.
If you provide the contents of install.sh and test/smoke-test.sh, I can re-evaluate and give more specific guidance.
Capability Analysis
Type: OpenClaw Skill
Name: raai-price-probe-dogovornaya-20260421
Version: 0.0.1
The bundle is a comprehensive AI-driven customer support system (AI-Support PRO) designed for the OpenClaw platform. It contains detailed prompt instructions (SKILL.md) for ticket categorization, SLA tracking, sentiment analysis, and CRM integration, alongside standard utility scripts (install.sh, build.sh) for deployment and verification. No evidence of malicious intent, data exfiltration, or harmful prompt injection was found; all components are logically aligned with the stated purpose of automating support operations and managing customer service workflows.
Capability Tags
Capability Assessment
Purpose & Capability
The SKILL.md describes an AI-driven customer-support system (categorization, SLA, CRM integration) and the optional environment variables (Telegram, Bitrix24, amoCRM, Google Sheets) are coherent with that purpose. However the registry metadata shown at the top of the package claims no required environment variables or credentials, while SKILL.md explicitly declares required API keys (ANTHROPIC_API_KEY, OPENAI_API_KEY). This mismatch is an inconsistency in the package metadata vs runtime instructions.
Instruction Scope
SKILL.md and README instruct the operator to fill config.yaml and to run install.sh and test/smoke-test.sh (quick-start explicitly uses 'bash install.sh' and 'bash test/smoke-test.sh'). The instruction set references external integrations and API keys (expected) but also gives the agent/runner discretion to run included shell scripts. The runtime instructions do not appear to ask for unrelated system data, but they do rely on user-run scripts whose behaviour is not fully visible here.
Install Mechanism
The registry lists 'No install spec — instruction-only', yet the package contains build.sh, install.sh and test/smoke-test.sh. build.sh contents are visible and appear benign (local zipping, no network downloads). install.sh and smoke-test.sh contents were not provided in the excerpt; README instructs running install.sh. The presence of executable installation/test scripts without a declared install mechanism is an install-surface inconsistency and increases risk (you should inspect install.sh before running).
Credentials
SKILL.md declares required API keys: ANTHROPIC_API_KEY and OPENAI_API_KEY (and optional TELEGRAM_BOT_TOKEN, BITRIX24_WEBHOOK_URL, AMOCRM_API_KEY, GOOGLE_SHEETS_CREDENTIALS_JSON). Those variables are plausible for an AI helpdesk that can use multiple LLM providers and CRMs. The concern is the mismatch between the package-level requirements (none) and these declared runtime env vars—this can lead to unnoticed credential prompts or unclear handling of secrets. Requiring two large-model provider keys is not itself malicious but should be justified (fallback/ensemble); verify why both are required.
Persistence & Privilege
always:false and there are no declared config paths or automatic persistent privileges. However the package includes installation and smoke-test scripts which, if executed, could create files or services on the host. The package does not declare an automatic persistent presence, but running install.sh may grant persistence—inspect the script before execution and avoid running as root.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install raai-price-probe-dogovornaya-20260421 - After installation, invoke the skill by name or use
/raai-price-probe-dogovornaya-20260421 - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.0.1
price field probe
Metadata
Frequently Asked Questions
What is raai-price-probe-dogovornaya-20260421?
Automation skill for raai-price-probe-dogovornaya-20260421. It is an AI Agent Skill for Claude Code / OpenClaw, with 50 downloads so far.
How do I install raai-price-probe-dogovornaya-20260421?
Run "/install raai-price-probe-dogovornaya-20260421" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is raai-price-probe-dogovornaya-20260421 free?
Yes, raai-price-probe-dogovornaya-20260421 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does raai-price-probe-dogovornaya-20260421 support?
raai-price-probe-dogovornaya-20260421 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created raai-price-probe-dogovornaya-20260421?
It is built and maintained by RAAIPRO (@raaipro); the current version is v0.0.1.
More Skills