Project Architecture
Use this skill whenever the user wants to start a new software/app project, plan or review its architecture, or set up agent context files (AGENT.md) for a codebase. Trigger it whenever the user mentions "architecture", "project scope", "PRD", "monolith", "modular monolith", "AGENT.md", "CLAUDE.md", scaffolding a new project's folder structure, or asks how to organize/structure a codebase before or during building it — even if they don't use those exact words but describe wanting to plan out a new app, a new module, or how a codebase should be laid out. Also use it when the user is partway thr
Install
npx skills add Jithnkn/project-architecture --skill project-architecturegit clone --depth 1 https://github.com/Jithnkn/project-architecture.git /tmp/project-architecture
mkdir -p ~/.claude/skills
cp -r /tmp/project-architecture/. ~/.claude/skills/project-architecturePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Project Architecture Flow This skill turns a project idea into a right-sized architecture: it gathers the scope and PRD, analyzes them to decide how much structure the project actually needs, and produces the docs and AGENT.md context files that keep that structure legible to future agents (and humans) working on it. ## Why this exists The single biggest architecture mistake in either direction is picking the wrong amount of structure: over-engineering a small tool into a multi-module system nobody needs, or letting a genuinely multi-domain product sprawl inside one undifferentiated codebase where an agent has to read everything to change anything. The scope/PRD analysis below exists to make that call deliberately, with reasoning the user can see and override, instead of defaulting to whatever's fastest to type. The other recurring failure mode this skill addresses is context loss across a growing codebase. A single AGENT.md file works fine until a project has real module boundaries — at that point an agent working inside one module needs local context without having to re-read the whole system, but it *also* needs to know when something it just changed reaches outside its module. That's why the modular tier uses a root AGENT.md plus one per module, with an explicit escalation path between them (see "Cross-Module Impact Log" below) — the module-local file is the fast path for day-to-day work, the root file is what stops modules from silently drifting apart.
Details
- Skill name
project-architecture- Repository
- Jithnkn/project-architecture
- License
- MIT
- Repo updated
- 20 August 2026
FAQ
What does the Project Architecture skill do?
Use this skill whenever the user wants to start a new software/app project, plan or review its architecture, or set up agent context files (AGENT.md) for a codebase. Trigger it whenever the user mentions "architecture", "project scope", "PRD", "monolith", "modular monolith", "AGENT.md", "CLAUDE.md", scaffolding a new project's folder structure, or asks how to organize/structure a codebase before or during building it — even if they don't use those exact words but describe wanting to plan out a new app, a new module, or how a codebase should be laid out. Also use it when the user is partway thr
How do I install the Project Architecture skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add Jithnkn/project-architecture --skill project-architecture. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Project Architecture popular?
It lives in Jithnkn/project-architecture, which has 10 GitHub stars and 2 forks.
Related skills
Opencode Automator
9alphaparkinc/genpark-skill-opencode-automator
OpenCode Automator — High-performance execution agent that utilizes dynamic code generation (Python/JS) to automate complex, multi-step workflows with mathematical precision and API reliability.
Port2browser
10infinuts/port2browser
Assess and port games to browsers through engine exports, source/framework ports, web-wrapper adaptation, compatible open runtimes or authorized reconstruction. Use for HTML5/WebAssembly game ports, engine feasibility, browser platform adaptation and playtesting with scoped evidence.
Ahrefs Domain Rating Free
9AIGC-Hackers/ahrefs-domain-rating-free-skill
Use when checking Ahrefs Domain Rating, DR, website authority, domain authority, backlink profile strength, or free Ahrefs public API data for a domain or URL without an API key.
Cover Xiaohongshu
12chaoshouli/cover-xiaohongshu
Codex 中的小红书封面设计与图片生成进化 Skill。唤醒词:小红书封面生成、小红书封面拆解。读取文章或结构化入参,通过目标提取、多路构图尝试、Judge 改进器和记忆更新,生成小红书封面提示词,或在 Codex 中调用图片生成能力产出小红书封面图;也可拆解样图排版方法,丰富可复用排版库以提升后续生成多样性。支持 prompt_mode、image_mode、production_mode,支持10种构图风格、真人出镜、多参考图:图1固定为人脸,图2起为UI截图、产品图等素材。关键词:小红书封面、小红书封面生成、小红书封面拆解、小红书封面设计、封面生成、提示词生成、封面优化、排版库。
Codemap
10beadnall/codemap
Turns a codebase into an explorable isometric architecture diagram — a self-contained HTML artifact with blocks on a grid, a component index, a what-it-does/how-it's-built panel, and real data snippets travelling along the edges that the reader can stop and inspect. Use this whenever someone asks for a codemap by name — "create a codemap", "codemap this repo", "make a codemap of github.com/owner/name" — and equally when they want to see, map, diagram or visually explain how a system fits together: "diagram this codebase", "show me the architecture", "map how this works", "visualise the data fl
Symphony
11broomva/symphony
Rust orchestration engine for coding agents. Polls issue trackers (Linear, GitHub), creates isolated per-issue workspaces, and runs coding agent sessions with lifecycle hooks, retry/backoff, concurrency control, and a live HTTP dashboard. Includes control metalayer (CONTROL.md / setpoints) for grounded development workflows.
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.