Skills Explorer Add Skills

receiving-code-review

An agent skill by obra, from obra/superpowers. Tags: api, developer-tools, web.

What it does

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add obra/superpowers --skill receiving-code-review

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/obra/superpowers
cp -r superpowers/skills/receiving-code-review ~/.claude/skills/receiving-code-review

Safety box score

Grade B, low risk: 12 of 100 risk points, rated 2026-10-21. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is documentation-only: it teaches an agent how to respond to code review feedback and optionally reply in GitHub review threads. It does not ship runnable scripts or access local secrets, but it does strongly constrain the agent’s wording and behavior and can trigger outbound GitHub API replies.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution0 (none)The only file is plain markdown; there are no scripts, shell commands, or code execution paths shipped with the skill.
Network access1 (low)The GitHub thread-reply guidance mentions `gh api repos/{owner}/{repo}/pulls/{pr}/comments/{id}/replies`, which can send data to GitHub when used.
Filesystem reach0 (none)It does not instruct the agent to read, write, or delete files outside the normal code-review workflow.
Secrets & credentials0 (none)There is no request to access tokens, passwords, `.env` files, keychains, or other credential stores.
Privilege & persistence0 (none)No sudo, global installs, services, shell startup edits, or OS-level changes are requested.
Instruction hijack surface1 (low)The skill is highly prescriptive about agent phrasing and behavior (for example, `NEVER:` and `Just start working`), but it does not instruct prompt evasion or hidden instructions.
Irreversible actions1 (low)It can drive a bounded outward action—posting inline GitHub review replies—but only within the narrow context of responding to code review.
Transparency0 (none)All content is readable markdown; there are no binaries, encoded payloads, or remote fetches.

Before installing

Rated 2026-10-21 by an automated review of 1 file from the skill's repository.

Source

Repository
obra/superpowers (all skills from this repository)
Path
skills/receiving-code-review/SKILL.md
Branch
main
Updated
2026-09-19