QSR Weekly P&L Storyteller
v1.0.0Turns weekly restaurant KPIs into a plain-English financial narrative — what happened, why it matters, and what to do about it. Replaces staring at spreadshe...
⭐ 0· 59·0 current·0 all-time
byMcPherson AI@mcphersonai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description match the instructions: the skill asks for weekly KPI inputs, produces a narrative, and stores a simple weekly archive. It does not request unrelated credentials, binaries, or system access.
Instruction Scope
SKILL.md stays within the stated scope (collect numbers, generate narrative, maintain a running archive). It does instruct the agent to store each weekly report in memory; this is expected for trend comparisons but is a data‑retention/privacy consideration the user should be aware of. The instructions do not reference system files, environment variables, or external endpoints.
Install Mechanism
There is no install spec and no code to write to disk (instruction-only). This minimizes install-time risk.
Credentials
The skill requires no environment variables, credentials, or config paths. The level of access requested is proportional to the stated functionality.
Persistence & Privilege
always:false (normal). The skill intentionally builds a persistent weekly archive in agent memory to enable comparisons; combined with the platform's default ability to invoke skills autonomously, this means the agent could prompt the user weekly unless the user disables autonomous invocation or adjusts memory retention. This is expected but worth confirming.
Assessment
This is an instruction-only skill that legitimately asks you to provide weekly numbers and will store those weekly reports in the agent's memory to enable trend comparisons. Before installing: (1) confirm you are comfortable storing P&L data in the agent's memory and understand your platform's memory retention and sharing policies, (2) if you don't want the agent to prompt you autonomously on a schedule, consider disabling autonomous invocation or changing the skill's scheduling behavior, and (3) because there is no install or external integration, the main privacy risk is the stored report data — review/delete memory as needed. The static scanner had no code to analyze, which reduces code‑supply risk but also means you should verify the platform's memory settings if you handle sensitive financial data.Like a lobster shell, security has layers — review code before you run it.
latestvk975xtyr9v0c3x262vtn35at1h84m0ty
License
MIT-0
Free to use, modify, and redistribute. No attribution required.