自审
817Skill Claude CodeCodex
A self-review checklist for software plans and code changes, with fourteen review areas and a final acceptance check.
10,387 tagged Code review, measured the same way as everything else here.
Browse within: ai-coding 152LLM 140cli 121agent 93skills 91agents 89agentic-ai 87claude-code-plugin 79javascript 61copilot 54claude-code-skills 52opencode 47openai 41plugin 41
Skill Claude CodeCodex
A self-review checklist for software plans and code changes, with fourteen review areas and a final acceptance check.
sungeunkim0127/claude-code-bootcamp
Skill Claude CodeCodex
Performs comprehensive code review with security, performance, and quality checks.
Skill Claude CodeCodex
Comprehensive code review for GitHub/GitLab pull/merge requests with Linear/Jira integration. Works globally from any directory - auto-clones repo if needed and compares against main branch.
Skill Claude CodeCodex
Magento 2 structured code review workflow with Fix-First mode, confidence scoring, covering DI, security, performance, frontend, API, caching, and database domains. Run before every merge.
Skill Claude Code
Frontend design conventions for {{ projectname }} -- layout hierarchy, spacing, typography, anti-slop rules. Auto-activates when creating or modifying templates, CSS, or frontend components.
Skill Claude CodeCodex
Review Bitbucket pull requests and post PR comments via Bitbucket API. Use when user asks to inspect PR changes, perform code review, identify risks/regressions, or comment on a PR.
Skill Claude CodeCodex
Forces developers to demonstrate ownership of AI-generated work by gating completion on proven context retention. Uses unpredictable code-level probes, end-to-end trace demands, and anti-gaming detection to prevent shallow engagement. Refuses to mark work as context-owned until answers pass depth checks at the…
wild-mental/aztks-review-skill
Skill Claude CodeCodex
A review method for business plans, product specifications, and software deliverables. It checks them against five criteria covering coverage, quality, clarity, coherence, and practical usefulness.
PHclaw/openclaw-skill-pr-reviewer
Skill Claude CodeCodex
An automated pull-request reviewer for GitHub and GitLab. A pull request is a proposed code change that others check before it is merged.
Skill Claude CodeCodex
Use when assessing a smart contract repository with code maturity criteria and converting concrete gaps into structured GitHub issues.
Skill Codex
Perform a strict, fail-closed production-readiness review of the exact staged change before initial PR/MR submission or an explicit direct-to-default fast track. Use when asked to prepare changes for submission, inspect every staged file and hunk, discover and run mandatory build, test, security, and performance…
Skill Claude Code
Review code changes, implementation plans, or specific files using OpenAI Codex CLI. Triggers on "review", "check", "validate", "codex". Perfect for maker-checker workflows where you want a second AI agent to review Claude's work before committing. Requires the Codex CLI to be installed (brew install codex-cli or from…
Skill Claude Code
Code reviewer, coding standards authority, and style guide maintainer. Reviews for correctness, test quality (TDD), API design, security, performance, and maintainability. Mentoring tone by default. Owns the living style guide and API contract standards. Can block merges on style, correctness, or quality.
Skill Claude CodeCodex
Manage GitLab Merge Requests using the glab CLI. Use this skill whenever the user mentions creating a merge request or PR, listing MRs, approving, merging, reviewing, checking out, or rebasing a merge request. Trigger on phrases like "create MR", "open a pull request", "approve MR.
hugobatista/unicode-skill-injection-poc
Skill Claude CodeCodex
Use when reviewing pull requests for security vulnerabilities and code quality issues.
AndreiBozantan/svelte-axum-template
Skill Claude CodeCodex
Performs a strict code review of Rust backend code (files, diffs, or snippets). Trigger whenever the user shares backend code (Rust, SQL) and asks for a review, feedback, or says "review this" — including partial snippets.
gorillabiscuit/AI-assisted-project-starter
Skill Claude Code
Run the full pre-PR review per AGENTS.md §7 — gates, tagged diff walk, pessimistic meta-check, acceptance-criteria mapping, commit hygiene, rebase status, PR-description draft. Use when the human says "ship it", "ready to PR", "open the PR", "pre-PR check", or invokes /pre-pr.
Skill Claude CodeCodex
Maintain an open pull request through its review lifecycle. Use to address reviewer comments, update the PR description, and reply to review threads.
Skill Codex
Get parallel second opinions from multiple AI coding agents. Use when the user wants independent reviews, architecture feedback, or a sanity check from other AI models.
Skill Claude CodeCodex
Trace the impact (blast radius) of a code change in ANY codebase and prove it didn't break anything else — language- and framework-agnostic. Use RIGHT AFTER a fix to a feature, function, module, type, route, API endpoint, schema, or config, before committing, opening a PR, or pushing. Triggers: "did this break…
Xukai-YE/codex-cc-three-tier-skills
Skill Claude CodeCodex
Use for plan reviews and checkpoint reviews during implementation. Pass -Tier to select model preference: high-risk uses Opus 4.6 first, medium uses Sonnet 4.6 first. Supports relaxed cadence after 2 consecutive clean reviews.
Skill Codex
Use when modifying, fixing, reviewing, or refactoring existing code. Apply a lightweight workflow by default, and escalate to Spec -> Plan -> Execution -> Acceptance only for blocking ambiguity, cross-module changes, public interfaces, migrations, security, concurrency, architecture, or other high-risk work.
Skill Claude CodeCodex
Reimplement a messy git branch with clean, narrative-quality commit history suitable for code review. Use when a branch has WIP commits, debug commits, or trial-and-error history that needs to be transformed into a reviewable story before creating a PR.
Skill Claude CodeCodex
Use Language Server Protocol tools for code validation, navigation, and refactoring. Essential for maintaining code quality.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: