ClawHub

Superpowers Receiving Code Review

v1.0.0

Use when receiving code review feedback to verify, clarify, and evaluate technical correctness before implementing or responding, avoiding performative agree...

⭐ 0· 77·0 current·0 all-time
by@demo112
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the content: the SKILL.md is a code-review reception playbook. Its recommended actions (verify against the codebase, ask clarifying questions, push back technically) are appropriate for the stated purpose.
✓
Instruction Scope
Instructions stay within the scope of receiving and evaluating code review feedback. The doc tells the agent/human to read feedback, check the codebase (e.g., grep), verify behaviour, and respond — all expected for this purpose. There is no instruction to read unrelated system files or exfiltrate data.
✓
Install Mechanism
No install spec and no code files; the skill is instruction-only, so nothing is written to disk and no external packages or downloads are required.
✓
Credentials
The skill declares no environment variables, credentials, or config paths. The few implied requirements (access to the repository/codebase to verify suggestions) are proportional and consistent with the described purpose.
✓
Persistence & Privilege
always is false and there are no actions that alter other skills or system-wide settings. Note: the platform default allows autonomous invocation, which is normal; this skill does not request elevated persistence.
Assessment
This skill is coherent and appears safe in isolation. Before installing, confirm the agent's permissions: it will sensibly need access to your repository or code files to perform the suggested verifications, and (if your platform allows autonomous invocation) you may want to restrict automatic runs so the agent doesn't post replies or make changes without human review. If you have strict data governance, run it in a workspace that has only the repositories you intend it to access.

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

latestvk977ttxehzbfdqn0q1ta79vykd83jvv7

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments