Small Goods Loyalty Incentives
v0.1.1Designs and refines customer loyalty programs and incentive systems for DTC/independent stores selling small, high-frequency products (e.g. cosmetics, phone...
⭐ 0· 244·0 current·0 all-time
byRIJOY-AI@rijoyai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the included assets: design guidance, metrics, an incentive playbook, and two small helper scripts (config sanity check and calendar generator). Required env vars/binaries/config paths are none, which is proportionate to a guidance/utility skill.
Instruction Scope
SKILL.md provides scoped instructions for eliciting merchant context and producing structured program outputs. It does not instruct the agent to read secrets, system files, or call external endpoints. The repository includes small scripts that read local JSON config files and write markdown; SKILL.md doesn't mandate executing them but they could be run by an agent with execution rights — review/validate any local config before running.
Install Mechanism
No install spec — instruction-first with optional script files. No downloads or archive extraction. This is low-risk from an install perspective.
Credentials
The skill declares no required environment variables, credentials, or config paths. The included scripts operate on local JSON files only and do not reference network endpoints or secrets; that is proportional to the stated purpose.
Persistence & Privilege
always is false and disable-model-invocation is false (normal). The skill does not request permanent system presence or alter other skills' configs in the provided materials.
Assessment
This skill appears coherent and low-risk: it provides playbooks and two small utility scripts that read local JSON and emit markdown. Before installing or allowing the agent to execute code, verify the skill's source/author (homepage is unknown), review the example config files, and run the Python scripts in a controlled environment with sanitized input to confirm outputs match expectations. If you grant the agent permission to execute code, ensure it has no access to unrelated credentials or sensitive filesystem areas. If you need network or platform integrations (Shopify, email/SMS providers), expect to supply those credentials separately and review any code that would use them.Like a lobster shell, security has layers — review code before you run it.
latestvk9734ck2xr5zdbcmxtrvmbw5v182mfc2
License
MIT-0
Free to use, modify, and redistribute. No attribution required.