#SkillRepo stars
- 2641Fractal Architecturevnovakovits/claude-skillsApply heuristics from Mark Seemann's "Code That Fits in Your Head" (2021) — fractal architecture, working-memory limits, cyclomatic complexity ceilings, vertical slices, encapsulation through invariants, functional core / imperative shell, checklists, and sustainable software engineering. Use when designing, decomposing, sizing methods/classes, deciding what fits in working memory, or evaluating whether code is sustainable over the long term.5
- 2642Grokbolasblack/claude-skillsxAI Grok second opinion via the grok CLI — three modes. Review: independent diff review with a pass/fail gate. Challenge: adversarial pass that tries to break the code. Consult: ask Grok anything, with session continuity for follow-ups. Use when the user says "grok review", "grok challenge", "ask grok", or wants a second opinion from Grok.5
- 2643Guardrailsbolasblack/claude-skillsRendered guardrail framework: keep a repo's hard rules in one-rule-per-file GRL sources behind a compact router, and render only the rules a task needs. Use when gathering guardrail context before implementing or reviewing code, when creating, editing, retiring, or reviewing GRL rule files or .agents/guardrails/index.md, when running the guardrails CLI (validate, render, review-metadata, next-id), or when setting up, adopting, or bootstrapping a guardrail framework in a repo that does not have one yet. Do NOT use for ordinary lint rule authoring unless the lint rule backs a guardrail, for runt5
- 2644Hexagonal Clean Architecturevnovakovits/claude-skillsApply Alistair Cockburn's Hexagonal Architecture (Ports and Adapters), Jeffrey Palermo's Onion Architecture, and Robert C. Martin's Clean Architecture — the family of architectural styles that put the domain at the center, push frameworks and I/O to the edges, and enforce inward-pointing dependencies. Use when structuring a non-trivial application, separating business logic from delivery and persistence, deciding where ports live and how adapters plug in, or testing domain logic without spinning up infrastructure.5
- 2645Heyreach MasterFreddy-CHEN-ux/00_claude_skillsInternal resource library for HeyReach integration. Contains shared API client, operation scripts, and reference documentation.8
- 2646Hook DevelopmentFreddy-CHEN-ux/00_claude_skillsThis skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.8
- 2647Hubspot MasterFreddy-CHEN-ux/00_claude_skillsShared resource library for HubSpot integration skills. DO NOT load directly - provides common references (setup, API docs, error handling, authentication) and scripts used by hubspot-connect and individual HubSpot skills.8
- 2648Instructions DevelopmentFreddy-CHEN-ux/00_claude_skillsThis skill should be used when the user asks to "create CLAUDE.md", "initialize CLAUDE.md", "sync CLAUDE.md with code", "update documentation from codebase", "create .claude/rules/", "manage modular rules", "split large CLAUDE.md", or mentions project documentation setup. Manages complete lifecycle of project instructions including creation, synchronization with code patterns, and modular organization.8
- 2649Knowledge SyncFreddy-CHEN-ux/00_claude_skillsUse after completing a refactor, implementing a major feature, or when skills may be outdated. Analyzes code changes, identifies affected skills, and proposes updates to keep team knowledge current. Also use when you notice a skill contains outdated patterns. Ask clarifying questions if changes are confusing.8
- 2650Language Ext Csharpvnovakovits/claude-skillsApply the LanguageExt functional library for C# in its 4.x form (the Aff and Eff era, before version 5's K<F, A> redesign). Covers the core types (Option, Either, Validation, Fin, Aff, Eff, Seq), idioms for null elimination, errors as values, applicative vs monadic composition, async effect chaining with LINQ from-select, Prelude imports and railway-oriented style, common pitfalls (ValueUnsafe, mixing nulls with Option, running effects on the wrong thread), and how v3, v4 and v5 differ. Use when reading, writing or reviewing C# that uses LanguageExt, including any code with Option<>, Either<>,5
- 2651Lean Software Developmentvnovakovits/claude-skillsApply Mary & Tom Poppendieck's seven principles of Lean Software Development from "Lean Software Development — An Agile Toolkit" (2003) and "Implementing Lean Software Development" (2006). Covers the seven principles (eliminate waste, amplify learning, decide as late as possible, deliver as fast as possible, empower the team, build integrity in, see the whole), the seven wastes of software (partially-done work, extra features, relearning, handoffs, task switching, delays, defects), value-stream mapping, set-based design, Real Options thinking, and the leadership mindset shift required for lean5
- 2652Linear ManagerFreddy-CHEN-ux/00_claude_skillsCreate, update, search, and comment on Linear issues. Use for project management and issue tracking during development.8
- 2653Pattern ExtractionFreddy-CHEN-ux/00_claude_skillsThree-tier system for documenting code patterns to optimize token usage8
- 2654Philosophy of Software Designvnovakovits/claude-skillsApply John Ousterhout's "A Philosophy of Software Design" (2018; 2nd ed. 2021) — design as the fight against complexity. Covers complexity's symptoms (change amplification, cognitive load, unknown unknowns) and causes (dependencies, obscurity), strategic vs tactical programming, deep vs shallow modules, information hiding and leakage, temporal decomposition, somewhat-general-purpose interfaces, different layer different abstraction, pass-through methods, pulling complexity downwards, defining errors out of existence, design it twice, comments as design, and the red-flags catalogue. Adds the de5
- 2655Pi Extension Devbolasblack/claude-skillsEnd-to-end workflow for developing, debugging, configuring, and shipping pi-coding-agent extensions and pi packages. Use when building or maintaining extensions, skills, prompt templates, themes, settings.json setups, provider integrations, or when updating this skill after pi releases. Do NOT use for general coding questions unrelated to pi extension development.5
- 2656Plugin DeveloperFreddy-CHEN-ux/00_claude_skillsCreate and maintain Claude Code plugins following established patterns8
- 2657Pragmatic Programmervnovakovits/claude-skillsApply the broad heuristics from Andy Hunt & Dave Thomas's "The Pragmatic Programmer" (1999, 20th-anniversary ed. 2019) — DRY, orthogonality, tracer bullets, reversibility, programming by coincidence, design by contract, broken windows, knowledge portfolio, good-enough software, and the dozens of tips that shape a craftsperson's everyday judgment. Use when stuck on a non-pattern-specific problem, when reasoning about engineering trade-offs, when picking up a new technology, when growing as a developer, or when articulating habits and stances that don't fit neatly into any single methodology.5
- 2658Pre Commit HooksFreddy-CHEN-ux/00_claude_skillsMANDATORY setup for all projects. Automated code quality enforcement before commits. Prevents bad code from entering repository.8
- 2659Product Development Flowvnovakovits/claude-skillsApply Don Reinertsen's "The Principles of Product Development Flow" (Celeritas, 2009), the quantitative case for flow in product work. Covers its 175 principles across eight areas (economics, queues, variability, batch size, WIP constraints, flow control under uncertainty, fast feedback, decentralised control) with verified codes; cost of delay and the SJF, HDCF and WSJF (CD3) sequencing rules; utilisation, Little's formula and why you control queue size rather than cycle time; the batch-size U-curve; congestion collapse; cadence; pooled versus dedicated capacity; and how to handle interrupt, 5
- 2660QA DebuggingFreddy-CHEN-ux/00_claude_skillsSystematic debugging methodologies, troubleshooting workflows, logging strategies, error tracking, performance profiling, stack trace analysis, and debugging tools across languages and environments. Covers local debugging, distributed systems, production issues, and root cause analysis.8
- 2661Refactoringvnovakovits/claude-skillsApply Martin Fowler's refactoring discipline — changing the internal structure of code without changing its observable behavior — using the named refactorings catalog (Extract Function, Move Method, Replace Conditional with Polymorphism, etc.) and the code-smells catalog (Long Method, Feature Envy, Primitive Obsession, etc.). Use when cleaning code under a test safety net, responding to a code smell, preparing code for a new feature, or as the third step of every TDD cycle.5
- 2662Refactoring to Patternsvnovakovits/claude-skillsApply Joshua Kerievsky's "Refactoring to Patterns" — the discipline of arriving at Gang of Four design patterns through refactoring driven by smells, not by upfront design. Includes the "refactor to / toward / away from a pattern" framing, the economic argument against pattern over-use, and the specific refactorings whose targets are named patterns (Factory, Strategy, Observer, Composite, Adapter, Template Method, State, Null Object). Use when a smell genuinely warrants a pattern, when undoing speculative pattern over-engineering, or when teaching the right time to introduce patterns.5
- 2663Repository Context CheckerFreddy-CHEN-ux/00_claude_skillsVerify developers are working in the right repository type (brain vs code)8
- 2664Responsibility Driven Designvnovakovits/claude-skillsApply Responsibility-Driven Design (RDD) by Rebecca Wirfs-Brock and Brian Wilkerson when designing classes, distributing behavior across objects, modeling a domain, or refactoring object-oriented code. Covers responsibilities, role stereotypes, CRC cards, collaborations, contracts, object neighborhoods, and the Tell-Don't-Ask principle.5
- 2665Semantic SearchFreddy-CHEN-ux/00_claude_skillsINVOKE BEFORE writing new code to find existing implementations (DRY). Also for codebase exploration and production data search. Run: docker exec arsenal-semantic-search-cli code-search find 'query8
- 2666Service Atlasvnovakovits/claude-skillsSurvey a service's codebase and publish a Miro "atlas" of it — a Pete Hodgson tech debt wall (value × cost cards), SIG-style health scorecard, hotspot treemap (churn × size), change coupling, pay-down roadmap, code quality metrics (cyclomatic complexity risk profile, unit size, parameters, duplication), system context map and coupling matrix (Khononov strength, efferent/afferent), domain logic leaking into the application layer, a Big Picture EventStorming, and one process-level EventStorming frame per pivotal phase. Grounds every claim in the code with parallel read-only agents, measures with5
- 2667Show Mebolasblack/claude-skillsMake the current discussion concrete with diagrams, code-shape sketches, and focused HTML artifacts. Use when the user asks to see a structure, flow, relationship, layout, or before-and-after change.5
- 2668Skill Routervnovakovits/claude-skillsPick the right engineering-practices skill, or sequence of skills, for the situation at hand. Maps common situations — a fuzzy idea, a feature to plan, code to write or test, a bug, legacy code, a design or architecture question, an event-sourced model, a review, a pull request, a slow team or process, product discovery, writing, an agent session that went wrong — to the skills in this plugin, and lays out the main flows through them (idea to shipped change, bug to fix, legacy change, design review, improving how a team works). Use when unsure which skill applies, when the user asks "which ski5
- 2669Software Architecture DesignFreddy-CHEN-ux/00_claude_skillsSystem design, architecture patterns, scalability tradeoffs, and distributed systems for production-grade software. Covers microservices, event-driven, CQRS, modular monoliths, and reliability patterns.8
- 2670Software BackendFreddy-CHEN-ux/00_claude_skillsProduction-grade backend API development with Node.js 24 LTS/25 Current (Express 5.x/Fastify 5.2/NestJS 11.x), Python 3.14+ (FastAPI 0.115+), Go 1.25+, Rust 1.92+ (Axum 0.8+), Prisma 6.x ORM, PostgreSQL 18. Includes GraphQL, TypeScript 5.9+ strict mode, modern logging (Pino/Winston), secret managers, PM2 process management, and Prisma Accelerate for serverless/edge deployments.8
- 2671Software Clean Code StandardFreddy-CHEN-ux/00_claude_skillsCanonical, cross-language clean code standard with stable rule IDs (CC-*) and language overlays. Single source of truth for clean code rules; code reviews cite CC-* IDs instead of restating rules.8
- 2672Software Code ReviewFreddy-CHEN-ux/00_claude_skillsPatterns, checklists, and templates for systematic code review with a focus on correctness, security, readability, performance, and maintainability.8
- 2673Software LocalisationFreddy-CHEN-ux/00_claude_skillsProduction-grade i18n/l10n patterns for React, Vue, Angular, and Node.js. Covers i18next, react-intl, vue-i18n, ICU message format, RTL support, TMS integration, and CI/CD translation workflows.8
- 2674Software MobileFreddy-CHEN-ux/00_claude_skillsProduction-grade mobile app development with Swift (iOS), Kotlin (Android), React Native, and WebView patterns, including UI/UX, navigation, state management, networking, local storage, push notifications, and App Store deployment.8
- 2675Systematic DebuggingFreddy-CHEN-ux/00_claude_skillsUse when encountering bugs or unexpected behavior. Methodical approach to identify root cause: Reproduce → Isolate → Identify → Fix → Verify.8
- 2676Systematic DebuggingFreddy-CHEN-ux/00_claude_skillsUse for ANY bug, test failure, or unexpected behavior. Use BEFORE proposing fixes. Four phases: investigate, analyze, hypothesize, implement. Ensures understanding before attempting solutions.8
- 2677Test Driven DevelopmentFreddy-CHEN-ux/00_claude_skillsUse when adding features or fixing bugs. Follow RED/GREEN/REFACTOR cycle. Write failing test first, implement minimal code to pass, then refactor.8
- 2678Tidy Firstvnovakovits/claude-skillsApply Kent Beck's "Tidy First?" approach — small structure changes (tidyings) separated from behavior changes, sequenced as "first / after / later / never", informed by software design as an economic activity (coupling, cohesion, optionality, discount rate). Use when about to make a behavior change in messy code, when reviewing a tangled PR, when deciding whether to clean up now or later, or when thinking about software design as a long-running investment decision rather than a craft aesthetic.5
- 2679Toyota Wayvnovakovits/claude-skillsApply Jeffrey Liker's "The Toyota Way — 14 Management Principles from the World's Greatest Manufacturer" (2004; 2nd ed. 2021), the management system behind the Toyota Production System. Covers the 4P model (philosophy, process, people and partners, problem solving) and the 14 principles, the TPS house (just-in-time and jidoka on heijunka, standardised work and kaizen), the wastes (muda, mura, muri, unused creativity) mapped to software, and Toyota product development (chief engineer, set-based design, front-loading). Includes a review mode that scores a process, ways-of-working or governance d5
- 2680Two Axis Code Reviewvnovakovits/claude-skillsReview a branch or pull request on two separate axes, reported side by side and never merged into one ranking. Standards — does the diff follow this repository's written rules (CLAUDE.md, AGENTS.md, CONTRIBUTING, coding standards) plus a baseline of Fowler's code smells? Spec — does it do what the ticket, spec or plan asked, with nothing missing, nothing extra and nothing done wrongly? Draws on Boehm's verification vs validation ("building the product right" vs "building the right product"), Google's code-review practice and Matt Pocock's two-axis review. Covers pinning the diff to a merge bas5
- 2681User SegmentationFreddy-CHEN-ux/00_claude_skillsFramework for clustering users into behavioral segments and personas. Use when analyzing user cohorts, identifying patterns, and personalizing product features.8
- 2682Validate SystemFreddy-CHEN-ux/00_claude_skillsValidate Nexus-v3 system integrity and fix common issues automatically. Load when user mentions "validate system", "check system", or "fix problems". Runs comprehensive checks on folder structure, metadata files, and framework consistency with auto-repair capabilities.8
- 2683VioletconnectFreddy-CHEN-ux/00_claude_skillsVioletConnect core features - merchant onboarding application architecture8
- 2684Violetconnect PatternsFreddy-CHEN-ux/00_claude_skillsCode patterns for implementing VioletConnect features - Redux, axiosWrapper, AppContext, API routes8
- 2685Violetconnect WoocommerceFreddy-CHEN-ux/00_claude_skillsWooCommerce REST API authentication and credential-based onboarding patterns for VioletConnect8
- 2686WoocommerceFreddy-CHEN-ux/00_claude_skillsWooCommerce API and WordPress integration patterns8
- 2687Working Effectively with Legacy Codevnovakovits/claude-skillsApply Michael Feathers's techniques for changing code that lacks tests — characterization tests, seams (object/link/preprocessor), dependency-breaking refactorings (Sprout Method, Extract Interface, Subclass and Override, Wrap Method, Break Out Method Object), effect sketches, and the Legacy Code Change Algorithm. Use when modifying inherited code without test coverage, when adding features to brittle code, when fixing bugs in code you don't yet understand, or when carving test points out of a tightly-coupled mess.5
- 2688Build Python Librarynpow/claude-skillsImplements pip-installable Python libraries from scratch using src layout, pyproject.toml, and pytest. Use when the user asks to build, create, implement, or scaffold a Python library, package, pip package, middleware, SDK, or wrapper. Covers project scaffolding, proxy/wrapper patterns, provider-agnostic interfaces, async/sync support, and test infrastructure.5