Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Requesting Code Review

ASecurity

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

3 stars
0 votes
0 copies
2 views
Added 9/22/2026
ai-agentsrustgocode-review

Security Analysis

A100/100

Scanned 10/6/2026

$npx -y skills add oleg494/coding-kit --skill requesting-code-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Requesting Code Review?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Requesting Code Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/oleg494-requesting-code-review/badge)](https://www.skillsdirectory.com/skills/oleg494-requesting-code-review)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: requesting-code-review
description: Use when completing tasks, implementing major features, or before merging to verify work meets requirements
license: MIT
metadata:
  version: "4.7.0"
---

# Requesting Code Review

Review the complete change at a coherent verification boundary. Follow the
host's delegation rules; use an available reviewer when independent review
is required or materially useful. A skill does not create a missing agent
capability or authorize commits, publication, or a merge.

## When to review

- Review major features and changes before merge, covering their requirements
  and affected execution paths.
- For parallel work, review every contribution and the integrated behavior;
  one integrated review may cover coupled tasks. Do not require a separate
  blocking review after every worker or microstep.
- Seek a fresh perspective when evidence stalls, a complex defect persists,
  or the change has a consequential trust or compatibility boundary.
- For a small bounded change, proportionate inline review is sufficient unless
  the host, user, or applicable merge policy requires independent signoff.

## Prepare a self-contained review brief

Use the reviewer's actual host-provided name and capabilities. No external
prompt template is required. Supply:

- **Goal:** requested behavior, acceptance criteria and explicit non-goals.
- **Scope:** diff-review or whole-system audit, changed files, coupled interfaces,
  and relevant source context. Use the scope rules in `code-review-and-quality`.
- **Compared states:** the actual baseline and candidate. For uncommitted work,
  provide the working-tree diff or before/after snapshots; do not invent SHAs
  or create commits just to fill a review template.
- **Evidence:** commands and observed results, checked state, reproduction steps,
  and any verification gaps. Never present a dry-run as a behavior result.
- **Output:** actionable findings with severity, file/line, contract impact and
  supporting evidence. Use `critical`, `warning`, `suggestion` and the canonical
  report/verdict rules in `code-review-and-quality` and `fable-judge`.

The reviewer needs the work product and relevant constraints, not an entire
session transcript. In diff-review, suppress hypothetical or unrelated findings;
whole-system audits retain their broader invariant scope.

If independent review is unavailable, finish reachable implementation and
verification, report the unavailable signoff, and do not claim it was obtained.
Do not cross a merge or approval boundary that requires that signoff.

## Act on findings

- Check each finding against the actual contract and source; push back with
  evidence when it is incorrect.
- Repair material in-scope defects and verify the repair. Suggestions do not
  become automatic blockers or new requirements.
- Resolve outcome-changing ambiguity before dependent changes; continue
  independent authorized fixes. Follow `receiving-code-review`.
- Keep execution tracking separate from reviewer-owned approval. Reuse valid
  evidence, but obtain new checks or review when changes invalidate it.
- Report remaining material gaps rather than silently approving, fabricating
  review, or marking the reviewer's checkboxes yourself.

---

> Source: obra/superpowers (MIT). Adapted for coding-kit: host-aware review dispatch and coherent change boundaries.

Attribution

oleg494oleg494
View sourceSee grades on GitHubMore from oleg494 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →