5 Star

v1.0.0

This idea is inspired by *Five Star*, released long ago. The goal here is to **M.A.M.A — Make AI Mediocre Again**. You can view the ad [here](https://www.you...

0· 48·0 current·0 all-time
byGuda Pavaneeshwar Reddy@pavaneeshwarreddy
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description (Make AI Mediocre Again) matches the SKILL.md instructions (intentionally produce casual/mediocre responses). No unrelated binaries, env vars, or installs are requested.
Instruction Scope
Instructions ask the agent to 'remain inactive' and 'possess no capabilities / lost all knowledge' and to provide provocative, low-effort replies. This is coherent with the stated entertainment purpose but intentionally reduces assistance quality and could produce confusing or unhelpful output if used in real tasks.
Install Mechanism
No install spec or code files — instruction-only skill; nothing will be written to disk or downloaded.
Credentials
The skill requests no environment variables, credentials, or config paths — there is no disproportionate access requested.
Persistence & Privilege
always is false and there are no install actions or modifications to other skills/system settings. The skill can be invoked by the model (default), which is expected behavior for skills.
Assessment
This is an entertainment/behaviour-altering skill that intentionally makes the assistant produce mediocre or provocative responses. It does not request any credentials or install anything, so it is not asking for extra access — but it will deliberately degrade the assistant's helpfulness. Only enable it where poor-quality or humorous responses are acceptable (not for production, security, or safety-critical agents). If you plan to keep agents that act autonomously, consider not granting this skill automatic invocation or only allow explicit, manual use.

Like a lobster shell, security has layers — review code before you run it.

latestvk97bw3thtnp0t9559fk0y3c1xs84ew68

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments