Refactor and improve code quality across a project using parallel specialized sub-agents with a safety-first iterative approach.
Review local changes or a pull request using the shared multi-perspective review workflow.
Run the reusable low-level review engine directly on the current diff or on explicitly supplied review context.
Plan, implement, and review a feature request, bug fix, or change specification.
Stress-test a plan, design, or architecture with a relentless structured interview.
Refactor and improve code quality across an entire project using parallel specialized sub-agents. Covers Go, TypeScript/React, Python, Rust, Database, Shell/Build, K8s/Config, and Observability domains with a safety-first iterative approach. Use when the user wants to improve code quality, readability, maintainability, or modernize a codebase without breaking functionality.
Review pull requests and local changes with reusable multi-perspective review workflows. Use when the user asks to review a PR, review local changes, review-pr, review-change, code review, or merge request review.
Execute a three-phase Plan -> Code -> Review workflow with iterative implementation until the review passes. Enforces production-readiness with extensive logging, comprehensive testing (unit + E2E), multi-agent code review, and build validation. Metrics and tracing are added when the project already has that infrastructure. Use when the user asks to build a feature, fix a bug, or make a structured change and wants planning, production-grade coding, and review in one workflow.
Stress-test a plan, design, or architecture by conducting a relentless structured interview. Leverages review perspectives for systematic dimension coverage and explores the codebase to ask sharper questions. Use when a user wants to pressure-test an idea, get grilled on a design, or mentions "grill me".
Investigate a running production application for bugs, performance issues, stability problems, and optimization opportunities by analyzing pod logs and distributed traces. Spawns parallel specialist sub-agents, cross-references memory for recurring issues, and produces a prioritized improvement plan.
Requires secrets
Needs API keys or credentials to function
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A collection of AI agent skills and slash commands for day-to-day software development. These plugins supercharge your AI coding assistant with structured workflows for feature development, code review, PR comment resolution, and Jira integration.
Built on the open Agent Skills standard — works with Claude Code, Cursor, and any editor that supports the standard.
Option A — Plugin Marketplace (recommended)
Run these slash commands inside a Claude Code session:
/plugin marketplace add SchSeba/ai-plugins
/plugin install ai-plugins@ai-plugins
The install syntax is
<plugin-name>@<marketplace-name>. Both areai-pluginsin this case — the plugin name comes fromplugin.jsonand the marketplace name from the GitHub repo name.
Claude Code will prompt you to choose an installation scope:
| Scope | Effect | When to use |
|---|---|---|
| User | Available in all your projects | You want these skills everywhere (recommended) |
| Project | Shared with collaborators via .claude/plugins.json | Team-wide adoption for a specific project |
| Local | Per-user, per-repo (not committed) | Personal testing in a single repo |
Once installed, the skills are namespaced under the plugin name. For example:
/ai-plugins:develop-feature Add JWT authentication
/ai-plugins:code-review review-pr https://github.com/owner/repo/pull/42
Option B — Skills Directory
Clone the repo into your Claude skills directory for auto-loading without the marketplace:
git clone https://github.com/SchSeba/ai-plugins.git ~/.claude/skills/ai-plugins
Skills loaded this way are available directly (without namespacing):
/develop-feature Add JWT authentication
Option C — Plugin Directory (development/testing only)
For local development or testing changes to the plugin:
git clone https://github.com/SchSeba/ai-plugins.git
claude --plugin-dir ./ai-plugins
Option A — Remote Rule from GitHub (recommended)
https://github.com/SchSeba/ai-pluginsCursor will pull the skills and commands automatically.
Option B — Copy skills to your project
git clone https://github.com/SchSeba/ai-plugins.git
# Project-level (available in this project only):
cp -r ai-plugins/skills/* .cursor/skills/
cp -r ai-plugins/commands/* .cursor/commands/
# User-level (available across all projects):
cp -r ai-plugins/skills/* ~/.cursor/skills/
cp -r ai-plugins/commands/* ~/.cursor/commands/
| Skill | Description | Command |
|---|---|---|
| develop-feature | Plan → Code → Review workflow with iterative implementation | /develop-feature |
| code-review | Multi-perspective code review for PRs and local changes | /code-review |
| review-engine | Reusable review engine (shared by other skills) | /review-engine |
| pr-comment-resolver | Resolve PR review comments one-by-one with user approval | /pr-comment-resolver |
| jira-cli | Query Jira tasks and epics | /jira-cli |
| write-a-skill | Create new agent skills with proper structure, conventions, and registration | /write-a-skill |
A three-phase development workflow: Plan → Code → Review with automated iteration until the review passes.
The agent plans the implementation, writes production-grade code with tests, then reviews its own work. If the review finds issues, it loops back to coding and fixes them — up to 3 iterations.
+----------+ +----------+ +----------+
| PLAN | --> | CODE | --> | REVIEW |
+----------+ +----------+ +----------+
^ |
| changes |
| requested |
+----------------+
Usage:
/develop-feature Add user authentication with JWT tokens
/develop-feature Fix the race condition in the connection pool cleanup
/develop-feature Refactor the payment service to use the strategy pattern
npx claudepluginhub schseba/ai-plugins --plugin ai-pluginsAccess thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques