Explore skills

Enforces running tests, linters, builds and confirming fresh output before claiming work complete, fixed, or ready for commits/PRs.

Processes code review feedback technically: verify suggestions against codebase, clarify unclear items, push back if questionable, implement after evaluation—not blind agreement.

Enforces strict TDD workflow: Red (failing test), Green (minimal code), Refactor for features, bugfixes, refactors. Includes examples and verification steps.

Verifies tests pass on completed feature branch, presents options to merge locally, create GitHub PR, keep as-is or discard; executes choice and cleans up worktree.

Guides root cause investigation for bugs, test failures, unexpected behavior, performance issues, and build failures before proposing fixes.

Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.

Generates distinctive, production-grade frontend UIs for components, pages, or apps with bold aesthetics, unique typography, motion, and layouts avoiding generic styles.

Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.

Provides idiomatic Go patterns and best practices for writing, reviewing, refactoring Go code, and designing packages. Covers simplicity, zero values, interfaces, and error handling.

Provides Go testing patterns with TDD: table-driven tests, subtests, benchmarks, fuzzing, and coverage for reliable, idiomatic tests.

Applies Pythonic idioms, PEP 8 standards, type hints, and best practices for readable, robust Python code during writing, review, refactoring, and package design.

Provides Python testing strategies using pytest: TDD cycle, fixtures, mocking, parametrization, assertions, exception handling, and coverage measurement.

Provides Django security best practices for production settings, authentication, authorization, CSRF/XSS/SQL injection protection, and secure deployment.

Caches expensive file processing (PDFs, text extraction, images) using SHA-256 content hashes for path-independent, auto-invalidating JSON storage in Python.

Guides TDD in Django with pytest-django, factory_boy, fixtures, mocking, coverage for testing models, views, serializers, DRF APIs.

Provides Django patterns for project structure, split settings, DRF REST APIs, ORM best practices, caching, signals, middleware, and production setups.

Guides TDD for Spring Boot with JUnit 5, Mockito, MockMvc, Testcontainers, JaCoCo. Covers unit, web, integration, persistence tests for features, bugs, refactors.

Provides deployment strategies (rolling, blue-green, canary), multi-stage Dockerfiles for Node.js, health checks, rollback plans, and production checklists for web apps.

Provides REST API design patterns for resource naming, URL structures, HTTP methods/status codes, pagination, filtering, errors, versioning, and rate limiting.

Implements Playwright E2E testing patterns: Page Object Model, test organization, configuration, reporters, artifacts, and CI/CD integration for stable suites.

Scans .claude/ directory for security vulnerabilities, misconfigurations, and injection risks in CLAUDE.md, settings.json, MCP servers, hooks, and agents using AgentShield.

Provides Docker Compose setups for local dev stacks with databases and caching, multi-stage Dockerfiles for dev/prod, and patterns for security, networking, volumes, healthchecks.

Integrates Apple's FoundationModels for on-device LLM in iOS 26+ apps: text generation, @Generable structured output, tool calling, snapshot streaming.

Provides JPA/Hibernate patterns for Spring Boot entity design, relationships, N+1 prevention, query optimization, transactions, auditing, pagination, indexing, and pooling.

Provides decision framework and Python code for hybrid regex-LLM parsing of structured text like quizzes, forms, and invoices—prioritize regex, LLM for edge cases.

Enforces C++ Core Guidelines for writing, reviewing, and refactoring modern C++ code (C++17+), promoting RAII, immutability, type safety, and idiomatic practices.

Provides Python patterns for LLM API cost optimization: model routing by complexity, immutable budget tracking, narrow retries, prompt caching. For apps calling Claude/GPT with budgets.

Delivers PostgreSQL patterns for indexing, schema design, query optimization, Row Level Security, UPSERT, pagination, and anti-pattern detection. Includes SQL examples and cheat sheets.

Implements thread-safe data persistence in Swift using actors: in-memory cache with atomic JSON file storage for offline-first apps.

Applies Spring Security best practices for authn/authz, input validation, CSRF, secrets, headers, rate limiting, and dependency security in Java Spring Boot services.

Provides Spring Boot patterns for REST APIs, controller-service-repository layers, JPA repositories, transactions, DTO validation, and exception handling in backend services.

Provides Swift 6.2 concurrency patterns: single-threaded async defaults, @concurrent background offloading, isolated MainActor conformances to eliminate data-race errors.

Runs phased verification: build, types, lint, tests with coverage, security scans for secrets/console.log, and git diff review before PRs or after changes.

Implements iOS 26 Liquid Glass effects—blur, reflection, interactive morphing—for SwiftUI, UIKit, and WidgetKit in buttons, cards, containers, and widgets.

Runs Spring Boot verification pipeline: build, static analysis, tests with coverage, security scans before PRs, changes, or deployment.

Provides SwiftUI patterns for @Observable state management, view composition, NavigationStack navigation, environment injection, and performance optimization in iOS/macOS apps.

Implements protocol-based DI in Swift for mocking file system, network, iCloud, and APIs to enable deterministic tests with Swift Testing and concurrency.

Assists writing, fixing, configuring C++ tests with GoogleTest/GoogleMock and CMake/CTest. Diagnoses flaky tests, failures, and adds coverage/sanitizers.

Dispatches parallel agents to independently fix multiple unrelated issues like failing tests in separate files or subsystems without shared state.

Creates consistent pitch decks, one-pagers, investor memos, financial models, accelerator apps, and fundraising materials from a single source of truth.

Conducts market research, competitive analysis, investor diligence, and tech scans with sourced findings, contrarian views, and decision recommendations.

Triggers research for existing libraries, tools, and patterns before coding new features. Searches npm, PyPI, MCP/skills, GitHub; evaluates matches and decides adopt/extend/build.

Manages long-lived agent workloads with runtime lifecycle, observability, safety controls, metrics tracking, incident response, and integrations for PM2, systemd, containers, CI/CD.

Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.

Provides process, architecture, review, hiring, and testing guidelines for engineering teams relying on AI code generation.

Guides agentic engineering workflows: eval-first loops, 15-min task decomposition, model routing (Haiku/Sonnet/Opus), AI code reviews, and cost tracking.

Translates visa document images to English via OCR (Vision/EasyOCR/Tesseract), rotates via EXIF, and generates bilingual A4 PDFs with original and translation.

Operate NanoClaw v2 REPL: manage persistent markdown sessions, switch models, load skills, branch/search/compact/export sessions, view metrics. Use when running/extending claw.js.

Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).

Tests local web apps with Python Playwright: manages server lifecycles via helpers, captures screenshots, inspects DOM, automates UI interactions for frontend verification.

Generates zero-dependency, animation-rich HTML presentations from scratch, PPT/PPTX conversions, or existing slides. For talks, pitches, workshops via visual style exploration.

Implements eval-driven development (EDD) for Claude Code with capability/regression evals, pass@k metrics, and code/model/human graders for measuring agent reliability.

Orchestrates large features via RFC decomposition into verifiable work units in a multi-agent DAG, with quality gates, merge queues, complexity tiers, and recovery. Use for complex, multi-pass tasks.

Provides Perl testing patterns with Test2::V0, Test::More, prove runner, Devel::Cover coverage, mocking, and TDD for new code, suites, reviews, and debugging.

Provides Kotlin Coroutines and Flow patterns for Android/KMP: structured concurrency, StateFlow, operators, combining flows, error handling, and testing.

Provides guidelines and examples for writing internal company communications including 3P updates, newsletters, FAQs, status reports, leadership updates, project updates, and incident reports.

Enforces TDD workflow ensuring 80%+ coverage with unit, integration, and E2E (Playwright) tests for new features, bug fixes, and refactoring.

Generates production-grade web UIs—components, pages, dashboards—with bold, distinctive aesthetics in HTML/CSS/JS, React, or Vue. Use for creative, polished frontend code.

Applies Perl security patterns: taint mode, input validation, safe process/file ops, DBI queries, and web defenses against XSS/SQLi/CSRF.

Applies Modern Perl 5.36+ idioms like v5.36 pragma, subroutine signatures, postfix dereferencing when writing, reviewing, refactoring, or designing Perl code.

Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.

Conducts multi-source web research with firecrawl and exa MCPs: searches, scrapes pages, synthesizes cited reports. For deep dives, competitive analysis, tech evaluations, or due diligence.

Executes pre-written implementation plans: critically reviews, follows bite-sized steps exactly, runs verifications, tracks progress with checkpoints, uses git worktrees, stops on blockers.

Resolves freight exceptions including delays, damages, losses, and carrier disputes via classification workflows, escalation protocols, claims filing, and carrier-specific strategies.

Provides patterns for shared UI in Compose Multiplatform across Android, iOS, Desktop, and Web: state management with ViewModels/StateFlow, navigation, theming, and performance.

Implements Clean Architecture in Android and Kotlin Multiplatform projects: module layouts, dependency rules, UseCases, Repositories, domain models, and data layers with Room, SQLDelight, Ktor.

Provides production scheduling expertise for job sequencing, line balancing, changeover optimization, bottleneck resolution, and disruptions in discrete/batch manufacturing with ERP/MES.

Provides guidance on returns authorization, receipt inspection, condition grading, disposition routing, refund processing, fraud detection, and warranty claims in e-commerce operations.

Delivers expertise for HS tariff classification, customs documentation, duty optimization, restricted party screening, and trade compliance across jurisdictions.

Provides expertise on electricity/gas procurement, tariff optimization, demand charge management, renewable PPA evaluation, hedging, load profiling, and multi-facility energy strategies.

Codifies expertise for managing carrier portfolios, negotiating freight rates, tracking performance, running RFPs, scorecards, and building freight strategies in transportation logistics.

Provides demand forecasting, safety stock optimization, replenishment planning, and promotional lift estimation for multi-location retailers managing 300-800 SKUs.

Guides NCR investigations, root cause analysis, CAPA management, SPC interpretation, and supplier quality control in FDA/IATF16949/AS9100 regulated manufacturing.

Analyzes raw prompts, identifies intent/gaps, recommends ECC components, and generates optimized prompts ready to paste. Auto-triggers on 'optimize prompt' or similar phrases.

Audits Claude skills and commands for quality via Quick Scan (changed files only) or Full Stocktake modes, using bash scripts, checklists, and subagent evaluation.

Guides Kotlin TDD testing with Kotest specs, MockK mocking, coroutine/property-based tests, Ktor testApplication, and Kover coverage.

Neural searches for web content, code examples from GitHub/Stack Overflow, company intel, and people via Exa tools. Activates for current info, technical refs, or research queries.

Delivers idiomatic Kotlin patterns for null safety, immutability, sealed classes, coroutines, Flows, extensions, DSL builders, and Gradle DSL. Use when writing, reviewing, refactoring, or designing Kotlin code.

Guides users through structured workflow for co-authoring documentation via context gathering, iterative refinement, and reader testing for specs, proposals, and decision docs.

Runs Laravel verification pipeline: env/Composer checks, linting (Pint), static analysis (PHPStan), tests with coverage, security audits, migrations, deploy readiness.

Applies Anthropic's brand colors, Poppins/Lora typography, and accents to PPTX files and visuals using python-pptx for on-brand styling.

Provides Laravel patterns for controllers, services, Eloquent ORM, routing, queues, events, caching, and API resources in production apps.

Generates step-by-step plans for multi-session engineering projects with self-contained step contexts, dependency graphs, parallel detection, and adversarial review. Use for complex multi-PR tasks.

Guides Next.js 16+ Turbopack for faster dev via incremental bundling, FS caching, and HMR; covers webpack comparison, bundle analysis, and production builds.

Initializes Vite + React + TypeScript projects with Tailwind CSS and shadcn/ui, bundles to single HTML artifact for Claude.ai. For complex UIs with state, routing, components.

Provides Rust testing patterns for unit, integration, async, property-based tests, mocking, and coverage using TDD workflow with tools like proptest, mockall, rstest.

Provides Claude API patterns for Python/TS: messages, streaming, tools, vision, caching, agents. Activates on anthropic/@anthropic-ai/sdk imports or API queries.

Guides TDD workflow for Laravel with PHPUnit/Pest: unit/feature/integration tests, factories, DB strategies (RefreshDatabase), fakes, and 80%+ coverage targets.

Dispatches code-reviewer subagent to evaluate code changes via git SHAs after tasks, major features, or before merging, with focused context on implementation and requirements.

Applies 10 preset or custom color/font themes to artifacts including slides, documents, reports, and HTML landing pages.

Generates algorithmic art philosophies and p5.js sketches with seeded randomness, particles, flows, and interactive parameters for generative art requests.

Guides Laravel security best practices for authn/authz, validation, CSRF/mass assignment protection, file uploads, secrets, rate limiting, session hardening, and secure deployments.

Provides Kotlin patterns for JetBrains Exposed ORM: DSL/DAO queries, coroutine transactions, HikariCP pooling, Flyway migrations, repository pattern.

Guides creation of effective Claude Code skills with principles on conciseness, degrees of freedom, anatomy, and bundling resources for workflows/tools.

Provides Ktor server patterns for routing DSL, plugins (auth, CORS, serialization), Koin DI, WebSockets, services, and testApplication testing.

Generates AI images (Nano Banana), videos (Seedance, Kling, Veo 3), speech (CSM-1B), and audio via fal.ai MCP tools. Handles prompts, uploads, async jobs for media tasks.