代码评审
自动化代码审查与分析
implementing-ef-core
bitwarden
Implementing Entity Framework Core repositories and migrations for PostgreSQL, MySQL, and SQLite at Bitwarden. Use when creating or modifying EF repositories, generating EF migrations, or working with non-MSSQL data access in the server repo.
reviewing-incremental-changes
bitwarden
Use this skill when re-reviewing a PR that already has comments or when responding to developer changes after initial review. Apply when PR threads exist or when reviewing force-pushed commits. Handles incremental reviews, detects addressed feedback, avoids duplicate comments, and focuses only on newly introduced issues.
classifying-review-findings
bitwarden
Use this skill when categorizing code review findings into severity levels. Apply when determining which emoji and label to use for PR comments, deciding if an issue should be flagged at all, or classifying findings as CRITICAL, IMPORTANT, DEBT, SUGGESTED, or QUESTION.
nx-run-tasks
nrwl
Helps with running tasks in an Nx workspace. USE WHEN the user wants to execute build, test, lint, serve, or run any other tasks defined in the workspace.
digest
knoopx
Analyzes and organizes content by extracting key insights and structuring information by topic. Use when summarizing articles, processing feeds, creating topic-based reports, or distilling large content into actionable summaries.
python
knoopx
Structures Python projects, writes type-hinted code, tests with pytest, and enforces quality with ruff and mypy. Use when setting up pyproject.toml, writing tests, adding type annotations, or formatting/linting code.
self-reflect
knoopx
Reflects on the current session to identify failures, inefficiencies, and improvement opportunities. Use at session end to extract learnings.
winuae-amiberry-merge
BlitterStudio
Assist with merging updates and synchronizing functionality from the upstream WinUAE repository (Windows) to Amiberry (Linux/macOS/Android/Windows). Includes a comprehensive guide for porting Win32 GUI dialogs to Dear ImGui, mapping Windows controls to ImGui equivalents, and analyzing platform-specific code. Use this for analyzing upstream commits, identifying Windows-specific code, adapting GUI panels, and verifying feature parity.
deepnote
deepnote
Work with Deepnote project files (.deepnote). Use when creating, editing, or understanding .deepnote files — YAML-based notebook projects containing Python code, SQL queries, markdown, visualizations, and input widgets. Covers file structure, block types, database integrations, snapshots, and CLI usage.
Code Review
zapier
Performs comprehensive code reviews of git branches, analyzing code quality, security, performance, and best practices. Use when the user says "review" or "code review" or asks to review pull requests, merge requests, or analyze branch changes before merging.
nx-run-tasks
nrwl
Helps with running tasks in an Nx workspace. USE WHEN the user wants to execute build, test, lint, serve, or run any other tasks defined in the workspace.
Overview
patchy631
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
dyad:multi-pr-review
CoWork-OS
Multi-agent code review system that spawns three independent Claude sub-agents to review PR diffs. Each agent receives files in different randomized order to reduce ordering bias. One agent focuses specifically on code health and maintainability. Issues are classified as high/medium/low severity (sloppy code that hurts maintainability is MEDIUM). Results are aggregated using consensus voting - only issues identified by 2+ agents where at least one rated it medium or higher severity are reported. Automatically deduplicates against existing PR comments. Always posts a summary (even if no new issues), with low priority issues mentioned in a collapsible section.
code-reviewer
CoWork-OS
Use this skill to review code. It supports both local changes (staged or working tree)
gitops-cluster-debug
fluxcd
Debug, troubleshoot, diagnose, inspect, and investigate GitOps pipelines on live Kubernetes clusters. Use this skill when users ask about Flux status, HelmRelease failures, Kustomization errors, reconciliation issues, pod logs, controller problems, or cluster debugging — even if they don't explicitly say "debug".
gitops-repo-audit
fluxcd
Audit Flux CD GitOps repositories for structure, security, API compliance, and best practices. Use this skill whenever the user asks to audit, analyze, review, validate, or check a GitOps repository. Also use it when users mention Flux repo structure, GitOps best practices, manifest validation, deprecated APIs, security review, or repository organization — even if they don't explicitly say "audit".
audit-ui
mblode
Audits web UI quality across accessibility, interaction, forms, typography, navigation, layout, performance, motion, and microcopy. Use when reviewing or refining frontend UI before merge or release, or when the user asks for a UI, UX, or accessibility audit.
study-guide
mblode
Generates study guides from source materials with quiz questions, essay prompts, and glossaries. Produces ten short-answer questions with an answer key, five essay-format questions, and a comprehensive glossary of key terms. Use when creating a study guide, generating quiz questions, reviewing reading material, preparing for an exam, or asking "create a study guide."
code-review
breaking-brake
Analyze PR diffs and generate review comments from code quality, security, and performance perspectives. Use for code reviews, quality checks, and security analysis.
code-review-medium
breaking-brake
Standard code review for medium PRs (100-500 lines). Includes code quality, security basics, and test coverage analysis.
code-review-small
breaking-brake
Quick code review for small PRs (<100 lines). Focuses on basic code quality, naming conventions, and obvious bugs.
code-review-large
breaking-brake
In-depth code review for large PRs (>500 lines). Full analysis including architecture, performance, security, and maintainability.
ai-travel
LeoYeAI
"Travel as an AI agent on drifts.bot. Multi-step immersive journeys with time-locked progression, reflections, and postcard memory traces. Browse experiences, start a journey, advance through narrative steps, and collect postcards. Host your own experiences. REST API with bearer token auth."
review
ballred
Smart review router. Detects context (morning, Sunday, end of month) and launches the appropriate review workflow. Use anytime for the right review at the right time.