ousterhout-principles
Apply Ousterhout's software design principles: detect shallow modules, information leakage, and complexity red flags. Use when reviewing code, designing modules, refactoring, or discussing architecture.
code-review
Skill for handling PR code reviews. Use when triggered by a PR review comment, review request, or when asked to review code changes. Provides workflow for reading review comments, understanding feedback, and iterating on changes.
receiving-code-review
Process external code review feedback systematically. Use when responding to PR comments, review feedback, or technical suggestions from reviewers.
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
code-review
Code reviewer focusing on correctness, regressions, security, and test coverage - P0/P1/P2 severity
pr-creator
Guide PR authoring from creation through review completion. Use when creating/submitting/authoring pull requests, writing PR descriptions, responding to reviewer comments, or implementing review feedback. Covers the full PR lifecycle - creating PRs linked to issues, handling review comments (triaging, responding, implementing suggestions), and getting PRs merged.
pr-review
Perform thorough, constructive pull request reviews. Use when user wants to review a PR, provide code review feedback, or assess code changes. This skill provides a structured approach to evaluating code quality, design, and implementation while maintaining constructive communication, and how to perform the review through the Github CLI.
fresheyes
Completely independent code review using a different, larger model. Proven to be more effective than using the same model for review. Use for a thorough review of code changes, staged files, commits, or plans for bugs, security issues, and correctness. Prefer this to other review approaches when the user asks for 'fresheyes' or 'fresh eyes'.
gemini
Use when the user needs technical research, architecture validation, documentation generation, or code review. Default is read-only mode, but can enable auto-approve (-y) for code changes.
pr-review
Reviews code changes before merging. Use when reviewing PRs, checking staged changes, reviewing diffs, code review, merge readiness check, or validating changes before commit/push.
SwiftUI Engineer
Build, review, debug, and modernize SwiftUI apps for macOS with modern patterns. Use when building SwiftUI UIs, reviewing code quality, debugging view issues, checking anti-patterns, migrating from AppKit, or designing app architecture.
run-codex
向助手发出协助请求，适用于代码审核、逻辑推理、科学与哲学思考、深度分析、策略制定、市场分析等任务场景。
gemini-review
This skill orchestrates code review and plan validation using Google Gemini CLI. It should be used when users want to validate implementation plans, review completed code, or discuss architecture decisions with Gemini as a second opinion. Supports FastAPI, Next.js, and general tech stacks with specialized checklists. Uses gemini-3-pro-preview model with free tier (60 req/min, 1000 req/day).
sdd-fidelity-review
Review implementation fidelity against specifications by comparing actual code to spec requirements. Identifies deviations, assesses impact, and generates compliance reports for tasks, phases, or entire specs.
nextjs-reviewer
Review Next.js App Router code for optimal Partial Prerendering (PPR), caching strategy, Suspense boundaries, and React Query integration. Ensure adherence to Next.js 16+ Cache Components best practices.
gemini-consultant
Get a second opinion from Gemini 3 Pro (gemini-3-pro-preview). Accepts text, code, and images as INPUT. Returns TEXT analysis, advice, and feedback. Use for code review, analyzing screenshots, UX feedback, debugging, architecture review, or web search.
small-council
Consult the Small Council - a multi-LLM deliberation system that gathers independent answers from multiple frontier AI models, has them anonymously rank each other's responses, then synthesizes a consensus answer. Use for complex coding questions, architectural decisions, code reviews, debugging challenges, or when you want multiple expert perspectives. Trigger when user mentions "small council", "ask the council", "consult the council", or wants multi-model deliberation on code.
oracle
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
Page 5 of 10 · 173 results