Agentic Skills & Commands

Resolve PR Review Comments

One Front Door for Agent Architecture, Config, and Setup

Which Dev Loop skill to run

GitHub Projects v2 Kanban Setup

File a GitHub Bug Issue

Unified Cleanup Command

Autonomous task execution (Codex lane)

Single Front Door for Deployment and Infra Provisioning

UI/Design Review and Refinement

Remove AI Slop From Code and Product

Environment Variable Management

Client Requirement Intake

Diagnose and Fix Failing Checks

Quick Task Capture

Autonomous task execution

Review and Land Open PRs Into the Trunk

Performance Analysis Command

Pull Request Lifecycle

One Front Door for PRDs and Feature Planning

Optimize Prompt (Lyra-Inspired)

Structured Verification Pass on Your Work

One Front Door for Improving Existing Code

One Front Door for Cut, Gate, and Cleanup

One Front Door for Every Code Review

ICP → revenue-ranked backlog → dated milestones

Security Scanning Command

One Front Door for Authoring and Maintaining Agent Skills

What Did I Get Done

Post Inline Suggested Changes on a PR

One Front Door for Running, Authoring, and Setting Up Tests

Run the Right Tests and Make Red Go Green

Re-pitch the last message

Applies WCAG 2.1 AA to web UI work and fixes what fails

Design and operate LLM-as-a-Judge evaluation systems using direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated quality assessment

Audit LLM and agent applications for wrapper regressions, prompt or memory contamination, tool discipline failures, hidden repair loops, and output rendering corruption

Automates browser interactions for web testing, form filling, screenshots, and data extraction

Audit AI agent instruction files (AGENTS.override.md, AGENTS.md, configured fallbacks, CLAUDE.md, hooks, and settings) across workspaces in read-only report mode

Single front door for agent/subagent architecture, config, and setup

Add or repair .agents/ project context for an existing repo

Audit and reduce AI agent token and inference spend through context discipline, prompt caching, model routing, batching, and workflow capture

Design AI loading, thinking, and progress indicator UX. Use when explicitly asked to improve AI waiting states, add thinking indicators, or design loading UX for AI interfaces

Design regression tests for AI-assisted development by targeting model blind spots such as sandbox versus production path drift, response-shape mismatches, untested bug fixes, and same-model review failures

Expert in RESTful API design, OpenAPI/Swagger documentation, versioning, error handling, and API best practices for NestJS applications

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, @agenticindiedev/ui)

Ask which Dev Loop skill or flow fits the current situation

Sweeps implemented frontend code across five dimensions at once

Expert in AWS infrastructure setup including EC2, VPC, security groups, Application Load Balancers, Route53 DNS, and SSL/TLS certificates

Validate Biome 2.3+ configuration and detect outdated patterns

File a GitHub issue of type Bug from a description

Validate Bun workspace configuration and detect common monorepo issues

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes

Improve unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to understand

Validate Clerk authentication configuration and detect deprecated patterns

Correctness, security, and spec-fidelity gate for incoming pull requests

Survey any codebase as a senior advisor, then hand back either prioritized self-contained implementation plans for OTHER models/agents to execute, or a written architecture and health analysis for humans

Shared vocabulary for designing deep modules

Generate raster images (icons, illustrations, textures, app icons) from a text prompt by driving the Codex CLI's image tool, then extracting the finished PNG from the Codex session rollout

Granular feedback on drafts without rewriting

Generate Conventional Commit messages from staged or unstaged git changes, split unrelated changes into logical commits, detect breaking changes, and optionally create commits after approval

Expert React/Next.js component architect specializing in creating consistent, reusable, and maintainable components for monorepo projects

Expert in browser extension content scripts, DOM integration, and safe page augmentation across modern web apps

Recognize, diagnose, and mitigate patterns of context degradation in agent systems

Supplementary context protocol for agents executing in a repo that has a CLAUDE.md / AGENTS.md (or equivalent config)

Explain or reason about foundational context engineering concepts

Improve context efficiency through context budgeting, observation masking, prefix or KV-cache strategy, partitioning, token-cost reduction, retrieval scoping, and extending effective context capacity without lowering answer quality

Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, automated anti-pattern detection, and actionable feedback

Advises engineering leadership on direction

Strip AI-generated slop from a codebase and product

Front door for a freshly reported failure

Audit a project's dependency supply chain

Run deployment workflows for web applications (staging, production)

Single front door for deployment and infra provisioning

Compose deployment workflows from smaller skills and repo signals, including trunk-based releases, CI quality gates, provider deployment, post-deploy verification, rollback, and failed-check diagnosis

Hunts design-token drift across a frontend

Single front door for UI/design review and refinement

Scaffolds a complete VS Code Dev Container configuration with Docker, docker-compose, and optional Claude Code CLI support

Expert in Docker, docker-compose, Dockerfile patterns, and container orchestration for NestJS and Next.js applications

Creates clear, concise technical documentation for software projects, runbooks, and developer guides

Build and sharpen a project's domain model

Deploys backend applications to EC2 instances using Docker, GitHub Actions CI/CD, and Tailscale for secure SSH access

Expert in error handling patterns, exception management, error responses, logging, and error recovery strategies for React, Next.js, and NestJS applications

Build evaluation frameworks for agent systems

Orchestrate autonomous AI development with task-based workflow and QA gates

Scoped debugging methodology for when a test or build fails during execution/stabilization

Scaffold a production-ready Expo React Native app with working screens, navigation, and optional Clerk auth

Capture a client or stakeholder feature request, turn it into a planner-ready PRD epic with scoped sub-issues, check for duplicate work, and place approved issues on a GitHub Projects kanban

Structured "done coding, now what?" workflow

Resolve git merge conflicts correctness-first, then prove the tree still builds

Create distinctive, production-grade frontend interfaces with high design quality

Fan-out PR review across three parallel dimension agents (structural, security, devex/flag-hygiene), adversarially verify every finding, and synthesize a single prioritized verdict via a strongest-tier judge

Initialize Shipshit.dev full-stack product workspaces through npx @shipshitdev/v0, then customize and verify the generated repo

Implements the fixes a PR review asked for

Diagnoses failing or setup-stuck GitHub Actions checks on a PR, identifies root cause, and proposes or applies targeted fixes

Collect and triage a GitHub work inbox from assigned issues, review requests, mentions, authored PRs with failing checks, and optional project filters

Create, update, and publish GitHub pull requests with a clean title, durable body, branch hygiene, validation notes, and safe push/PR gates

Configure GitHub Projects v2 kanban boards with Ship Shit Dev defaults

Review GitHub pull requests and post precise inline suggested changes with GitHub suggestion blocks

Guards day-to-day git work in an existing repository

Author, review, and harden GitHub Actions workflows using current official documentation, secure trigger patterns, least-privilege permissions, current action versions, and CI/CD validation

Design and review GraphQL schemas, resolvers, mutations, pagination, and data-loading patterns

Grill the user relentlessly about a plan, decision, or idea

Independent second-opinion code review through the Grok CLI. Builds a self-contained review prompt from the exact diff, runs one headless Grok invocation on the CLI's own default model and effort, then verifies every returned finding against the code before reporting

Apply opinionated styling to barebones HTML. Use when user has plain/unstyled HTML and wants to apply consistent visual styling

Sets up or verifies Husky git hooks to enforce test coverage above 80% (configurable) for Node.js/TypeScript projects

Discover and document a product's Ideal Customer Profile as a durable .agents/memory/icp.md

Guides construction of resilient data ingestion pipelines from paginated APIs

Repo-grounded discovery interview that produces a handoff brief for PRD writing, feature intake, or planning

Scaffolds a production-ready static landing page with working email capture form, analytics, and responsive design

Reworks the structure underneath a UI

Set up Biome (default) or ESLint + Prettier, Vitest testing, and pre-commit hooks for any JavaScript/TypeScript project

Design prompts, schemas, validation, and recovery logic for reliable machine-readable model outputs

Creates MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools

Design and implement memory architectures for agent systems that persist state across sessions, maintain entity consistency, and reason over structured knowledge

Review and land open pull requests through one /merge command

Scaffolds, clones, and deploys config-driven NextJS landing pages that use a shared UI components package

Verify MongoDB Atlas setup and configuration for backend applications

Database schema design, indexing, and migration guidance for MongoDB-based applications

Sets up production monitoring for NestJS and Next.js apps

Design multi-agent architectures for complex tasks

NestJS architecture, modules, DI, guards, interceptors, pipes, MongoDB/Mongoose integration, auth, and production patterns

Queue job management patterns, processors, and async workflows for video/image processing

NestJS testing mechanics with Jest

Validate Next.js 16 configuration and detect/prevent deprecated patterns

Expert in creating clear, comprehensive technical documentation with Nextra (Next.js-based docs framework), MDX, and modern documentation patterns

Audits a whole private repository once, at the decision to make it public

Design and maintain TypeScript packages in a monorepo, including exports and build configuration

Backend, database, and infrastructure performance expert covering API response times, query and index optimization, N+1 elimination, caching and background jobs, server profiling, and build/asset delivery

Initialize Playwright end-to-end testing for Next.js and React projects

Runs the last pass over a functionally complete feature

Operate a production Postgres database

Reads a pull request's review threads and returns a digest

Single front door for product specs, PRDs, and feature planning

PRD completeness validation

Files work into a tracker — turns a feature, bug, or finished PRD into GitHub issues, linked sub-issues, or local task files, slicing epics into thin vertical slices sized for one PR each and tagged AFK or HITL. Starts once the requirements are settled; authoring the PRD document itself is `prd-writer`

Authors the PRD document itself

Audit an application for production readiness using local evidence from code, CI, config, migrations, runtime checks, observability, and deployment paths

Selects the correct project initialization route and orchestrates setup

Expert guide on prompt engineering patterns, best practices, and optimization techniques

Build a throwaway prototype to answer a design question

Runs an interactive localhost QA session that accepts issues, screenshots, routes, and browser evidence; reproduces and fixes each defect; verifies the result; and creates one local commit per fix

Runs a structured multi-phase verification pass on completed AI agent work

Generates minimal HTML pages to review structured data in a browser with maximum readability

Tones down visually aggressive or overstimulating designs, reducing intensity while preserving quality

Diagnose slow React components and apply targeted render-time fixes

Provides 41 prioritized performance rules for React Hook Form across form configuration, field subscription, controlled components, validation, and field arrays

Master React Native 0.79.5 components, styling, performance optimization, and mobile UI best practices with real-world examples

Modern React patterns and principles

Architectural refactoring guide for React applications covering component architecture, state architecture, hook patterns, component decomposition, coupling and cohesion, data flow, and refactoring safety

React Testing Library mechanics for testing React components and hooks

Evaluate incoming code-review feedback with technical rigor before implementing any change

Redis caching, rate limiting, session storage, pub/sub, and production integration patterns for TypeScript, Next.js, NestJS, and Prisma applications

Systematic approach to safely refactoring code with tests

Single front door for improving existing code

Cuts the release itself — derives the next semantic version from commits since the last tag, writes plain-English patch notes, previews the plan, then on confirmation creates an annotated tag plus GitHub release, or dispatches the repo's guarded release workflow where production sits behind a workflow_dispatch promote gate

Verify a release branch is provably merged into the trunk (default branch) via the squash-aware GitHub PR merge oracle, then prune merged local and remote feature branches and stale git worktrees

Single front door for releases

Holds a release at the gate — opens or reuses a release PR into the trunk, runs local format, lint, and type-check, watches required GitHub checks through to green, and summarizes the failing run's root cause when they are not

Single front door for code review

Turn a product's ICP into a revenue-ranked roadmap

Turn a revenue-ranked roadmap into tracked GitHub Milestones with due dates, assign issues to them, and report burndown

Automatically detects and documents user preferences, coding standards, and workflow rules from conversation

Generate incremental local code modules following existing codebase patterns

Run a self-contained security audit workflow for web applications and APIs, covering scoping, reconnaissance, manual testing, API review, hardening, and reporting

Expert in application security, OWASP Top 10, authentication, authorization, data protection, and security best practices for React, Next.js, and NestJS applications

Sets up an `## Agent skills` routing block in CLAUDE.md/AGENTS.md plus docs/agents/ so the dev-loop skills (executing-plans, feature-intake, prd-writer, qa-reviewer) know this repo's GitHub issue tracker, kanban label vocabulary, and domain doc layout

Provides shadcn/ui component library best practices and patterns

Sets up shadcn/ui with Tailwind CSS v4 CSS-first configuration

Plan the UX and UI for a feature before writing code

Extracts valuable workflows, patterns, and domain knowledge from conversations and persists them as reusable SKILL.md files

Measure whether agents actually follow a skill, rule, command, or agent definition by deriving expected behaviors, running representative scenarios, and comparing observed action timelines against the spec

Guide for creating effective skills

Single front door for authoring and maintaining agent skills

Search local, marketplace, repository, package, GitHub, and web sources before creating a new skill or custom implementation

Enforces a spec → plan → execute → verify loop before writing code, preventing "looks right" failures

Modernize a project's stack — outdated dependencies, dead/unused packages, deprecated packages, and framework-pattern drift (old patterns lingering after a major upgrade)

Summarize what you personally shipped over a time window from git history

Implement Stripe payment processing, subscription management, webhook handling, and customer management in Next.js and NestJS applications

Perform a structural and maintainability review of a PR or codebase diff

Full four-phase root-cause loop

Designs optimal filtering UX for data tables

Provides Tailwind CSS v4 performance optimization and best practices guidelines

Validate Tailwind CSS v4 configuration and detect/prevent Tailwind v3 patterns

Test-driven development workflow for feature work and bug fixes

Inventories a real codebase and ranks its technical debt into a register scored by interest (how often it hurts) over principal (effort to fix), every item anchored to a file-and-line or a metric

Single front door for testing

Run a project's tests at the right scope

Installs Vitest testing infrastructure and GitHub Actions CI/CD for TypeScript projects (Next.js, NestJS, React)

Framework-agnostic testing strategy

Toolkit for styling artifacts with a theme

Design tools that agents can use effectively, including when to reduce tool complexity

Turborepo monorepo build system guidance

Resolves TypeScript and JavaScript problems across type-level programming, performance, monorepo management, migration, and modern tooling

TypeScript refactoring and modernization guidelines from a principal specialist perspective

Deploy a Next.js app to Vercel and manage its environment

Enforce evidence-based completion

Re-pitch the last message in plain English using the project's CONTEXT.md vocabulary

Generate an interactive bash wizard that walks a human through steps only they can perform

Orchestrates comprehensive performance audits across full-stack monorepos

Create an isolated git worktree from the correct base branch and check it out into a clean, gitignored directory

Turn a spec or requirements doc into a comprehensive, bite-sized implementation plan