Superpowers Verification
v1.0.0Use when about to claim any work is complete, fixed, passing, or successful - requires running fresh verification commands and reading actual output before m...
⭐ 0· 262·2 current·2 all-time
by@axelhu
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name, description, and SKILL.md all describe the same goal: require running fresh verification commands and providing command output/evidence before claiming success. The skill requests no unrelated binaries, env vars, or config paths.
Instruction Scope
Instructions explicitly tell the agent to identify and run the appropriate verification commands, check exit codes, and include evidence. This is in-scope for a verification skill, but it is intentionally open-ended — it gives the agent discretion to choose and execute commands in the environment, which could access sensitive files or data depending on what commands are chosen.
Install Mechanism
No install spec and no code files are provided (instruction-only). Nothing will be written to disk by an installer.
Credentials
The skill declares no required environment variables, credentials, or config paths. The only implied requirement is permission for the agent to run commands and read their outputs, which is proportional to the stated purpose.
Persistence & Privilege
always is false and the skill does not request persistent or cross-skill privileges. It does not modify other skills or system-wide settings.
Assessment
This skill is a coherent checklist for verifying work before claiming success. Before using it, confirm that the agent runtime you run it in is trusted and sandboxed: the skill gives the agent freedom to pick and execute verification commands, and those commands could read sensitive files or outputs. If you need stricter controls, consider adding a whitelist of allowed commands, limiting working directories, or reviewing generated command outputs before sharing them externally. Since the skill is instruction-only, it does not install software or request credentials.Like a lobster shell, security has layers — review code before you run it.
latestvk97d23tr0zfy46rmjjb053de4n83mbcj
License
MIT-0
Free to use, modify, and redistribute. No attribution required.