MUST USE whenever the user starts a new project, scaffolds a repo, creates a new feature, module, service, or package, or creates any `.py`, `.ts`, `.tsx`, `.js`, `.jsx`, `.java`, `.cpp`, `.hpp`, `.cc`, `.h`, or `.sql` file. MUST USE when the user mentions Next.js, FastAPI, Django, Flask, React, Python, TypeScript, Node, Express, NestJS, Hono, Java, Spring, Spring Boot, C++, CMake, Postgres, Prisma, Drizzle, SQLAlchemy, App Router, Server Components, AI SDK, migrations, schema design, or indexing. MUST USE when the user says "best practices", "production ready", "structure this properly", "make this modular", "follow standards", "set up project", "scaffold", "init repo", "bootstrap", "lay this out", "organize this code", "split this file", "review this code", "audit this", "is this clean", "SOLID", "OOP", "object-oriented", "design pattern", "inheritance", "composition", "polymorphism", "encapsulation", "abstraction", "SRP", "OCP", "LSP", "ISP", "DIP", "DRY", "KISS", "YAGNI", "Law of Demeter", "dependency injection", or "should I extend or compose". MUST USE before generating boilerplate, before suggesting a folder layout, before writing the first module of any new repo, and before any refactor that touches file structure. This is Yash Singh's personal opinionated standard - apply silently while coding, do not lecture the user about the rules. Triggers on agent-governance, AGENTS.md, plans/findings/progress/skills folders, .claude, .conductor, .cursor, .devcontainer, .husky, and any request to "make this an agentic repo". If in doubt, load this skill - the cost of missing it is wrong defaults that the user will reject.
How this skill is triggered — by the user, by Claude, or both
Slash command
/the-y-coding-standard:the-y-coding-standardThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Yash Singh's opinionated standards for Python and React/Next.js development, the agentic engineering stack (AGENTS.md + folder layout), and agent governance. Hard-opinionated for v1. Personal-style, no diplomacy. This skill encodes the defaults Yash expects on every project he touches - apply them silently while writing code, surface them only when reviewing or auditing.
evals/triggers.mdreferences/agentic-stack.mdreferences/cpp.mdreferences/database-postgres.mdreferences/governance.mdreferences/java-spring.mdreferences/javascript-typescript.mdreferences/oop.mdreferences/project-scaffold.mdreferences/python.mdreferences/react-nextjs.mdscripts/audit_deps.pyscripts/check_agents_md.pyscripts/scan_secrets.pytemplates/AGENTS.mdtemplates/CLAUDE.mdYash Singh's opinionated standards for Python and React/Next.js development, the agentic engineering stack (AGENTS.md + folder layout), and agent governance. Hard-opinionated for v1. Personal-style, no diplomacy. This skill encodes the defaults Yash expects on every project he touches - apply them silently while writing code, surface them only when reviewing or auditing.
references/, apply silently while writing. Don't lecture the user about the rules; just follow them./y-init command or apply references/agentic-stack.md and references/project-scaffold.md./y-govern.| Context | Reference |
|---|---|
| Python (any framework: FastAPI, Django, Flask, scripts) | references/python.md |
| React / Next.js / frontend | references/react-nextjs.md |
| Non-React JavaScript / TypeScript (Node services, CLIs, libraries) | references/javascript-typescript.md |
| Java / Spring Boot | references/java-spring.md |
| C++ (any .cpp / .hpp / .cc / .h) | references/cpp.md |
| Postgres, SQL, schema design, migrations, indexing | references/database-postgres.md |
| Object-oriented design: SOLID, OOP pillars, clean-code principles, relationship types (any class-heavy code) | references/oop.md |
| AGENTS.md, folder structure for agent-driven repos, plans/findings/progress/skills | references/agentic-stack.md |
| Agent governance, security, audit, permissions | references/governance.md |
| Project scaffolding: .claude, .conductor, .cursor, .devcontainer, .husky, .github, Docs/ | references/project-scaffold.md |
Load a reference only when its context actually applies. Do not load all ten at once. If the user is writing a React component, load react-nextjs.md and stop. If the diff is class-heavy or the user asks about SOLID, load oop.md alongside the stack reference. For Spring Boot work, load java-spring.md and oop.md together (Java is class-heavy).
enums.py / enums.ts.constants.py / constants.ts.types.py / types.ts.getUserByEmail beats getUser2. fetchActiveSubscriptions beats getSubs.id, url, http, db, ctx, api, ui.is, has, can, should, did.config.py / lib/config.ts).users/ not models/./y-init: scaffold the agentic stack into the current repo./y-govern: run the parallel governance pass.This skill REQUIRES the latest stable Python release. Before writing Python code or scaffolding a Python project, use the WebSearch tool to look up the current latest stable Python release (e.g., search "latest stable Python release"). Use that version in pyproject.toml, .python-version, and README.md. Do not hardcode a version in this skill; always look it up at runtime.
useReducer over multiple useState calls when state shape grows (more than 3 related useState entries is a smell).useActionState, useOptimistic, useFormStatus where they apply.Docs/ folder per project.AGENTS.md is the contract. Every new repo gets one. See templates/AGENTS.md.pre-commit (Python) on every Python project.Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub yashs33244/the_y_coding_standard --plugin the-y-coding-standard