[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-2015":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":9,"languages":9,"totalLinesOfCode":9,"stars":10,"forks":11,"watchers":12,"openIssues":13,"contributorsCount":13,"subscribersCount":13,"size":13,"stars1d":14,"stars7d":15,"stars30d":16,"stars90d":13,"forks30d":13,"starsTrendScore":17,"compositeScore":18,"rankGlobal":9,"rankLanguage":9,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":20,"topics":23,"createdAt":9,"pushedAt":9,"updatedAt":24,"readmeContent":25,"aiSummary":26,"trendingCount":13,"starSnapshotCount":13,"syncStatus":15,"lastSyncTime":27,"discoverSource":28},2015,"project-architect","ersinkoc\u002Fproject-architect","ersinkoc","Documentation-first project planning agent skill. Generates specs, implementation plans, tasks, and single-shot prompts for coding agents. Compatible with Claude Code, Cursor, Codex, and 40+ agents via agentskills.io.",null,144,17,137,0,1,2,6,3,3.77,"MIT License",false,"main",true,[],"2026-06-12 02:00:35","# Project Architect\n\nAn [Agent Skill](https:\u002F\u002Fagentskills.io) for **documentation-first project planning**. Transforms a project idea into implementation-ready blueprints and a single-shot coding agent prompt.\n\nCompatible with **40+ coding agents** including Claude Code, Cursor, Gemini CLI, GitHub Copilot, Codex, Roo Code, and more.\n\n## What It Does\n\nGiven a project idea, Project Architect walks you through an interactive discovery process and generates 5 interconnected documents:\n\n```\n[Discovery] -> SPECIFICATION.md -> IMPLEMENTATION.md -> TASKS.md -> BRANDING.md\n                 (The What)          (The How)          (The Work)   (Identity)\n                      |                   |                  |\n                      +-------------------+------------------+\n                                          |\n                                     PROMPT.md\n                               (Single-Shot Agent Prompt)\n```\n\n| Document | Purpose |\n|----------|---------|\n| **SPECIFICATION.md** | What the project is, features, data model, API surface |\n| **IMPLEMENTATION.md** | Tech stack, design patterns, directory structure, schemas |\n| **TASKS.md** | Ordered work items, each completable in a single agent session |\n| **BRANDING.md** | Name, colors, typography, voice (optional, for user-facing projects) |\n| **PROMPT.md** | Self-contained prompt to build the entire project from scratch |\n\n## Features\n\n- **Interactive tech stack advisor** -- presents options with trade-offs, lets you choose\n- **Design pattern recommendations** -- matched to your project's specific needs with code sketches\n- **Scales to project size** -- weekend hack gets 15 tasks, enterprise system gets 100+\n- **Agent-optimized output** -- every task lists exact files to create\u002Fmodify with acceptance criteria\n- **Pause-and-review flow** -- generates each document, waits for approval before continuing\n\n## Installation\n\n### Universal (any agent) via skills CLI\n\nThe easiest way to install, works with all [agentskills.io-compatible agents](https:\u002F\u002Fagentskills.io):\n\n```bash\nnpx skills add ersinkoc\u002Fproject-architect\n```\n\nThis auto-detects your coding agent and installs to the correct location.\n\n**Install for a specific agent:**\n\n```bash\nnpx skills add ersinkoc\u002Fproject-architect --agent claude-code\nnpx skills add ersinkoc\u002Fproject-architect --agent cursor\nnpx skills add ersinkoc\u002Fproject-architect --agent codex\n```\n\n**Install globally (all projects):**\n\n```bash\nnpx skills add ersinkoc\u002Fproject-architect --global\n```\n\n> Repository: [github.com\u002Fersinkoc\u002Fproject-architect](https:\u002F\u002Fgithub.com\u002Fersinkoc\u002Fproject-architect)\n\n### Claude Code (plugin mode)\n\nAdd to your project's `.claude\u002Fsettings.json`:\n\n```json\n{\n  \"plugins\": [\n    \"\u002Fabsolute\u002Fpath\u002Fto\u002Fproject-architect\"\n  ]\n}\n```\n\nOr add to `~\u002F.claude\u002Fsettings.json` for global availability.\n\n### Manual installation (any agent)\n\nClone the repo and copy\u002Fsymlink the skill directory into your agent's skills folder:\n\n| Agent | Skills Directory |\n|-------|-----------------|\n| Claude Code | `.claude\u002Fskills\u002F` or `~\u002F.claude\u002Fskills\u002F` |\n| Cursor | `.cursor\u002Fskills\u002F` or `~\u002F.cursor\u002Fskills\u002F` |\n| GitHub Copilot | `.github\u002Fskills\u002F` |\n| Codex | `.codex\u002Fskills\u002F` |\n| Gemini CLI | `.gemini\u002Fskills\u002F` |\n| OpenCode | `.opencode\u002Fskills\u002F` |\n| Generic | `.agents\u002Fskills\u002F` or `~\u002F.agents\u002Fskills\u002F` |\n\n```bash\n# Example: install for Claude Code globally\ngit clone https:\u002F\u002Fgithub.com\u002Fersinkoc\u002Fproject-architect.git\nln -s $(pwd)\u002Fproject-architect ~\u002F.claude\u002Fskills\u002Fproject-architect\n\n# Example: install for Cursor in a project\nln -s $(pwd)\u002Fproject-architect .cursor\u002Fskills\u002Fproject-architect\n```\n\n## Usage\n\nStart a conversation with your coding agent and describe what you want to build:\n\n```\n> plan my project: a CLI tool for managing dotfiles across machines\n```\n\nOr use any of these trigger phrases:\n\n- \"plan my project\"\n- \"spec this out\"\n- \"architect a system for...\"\n- \"help me plan\"\n- \"what stack should I use\"\n- \"generate a prompt\"\n- \"break this into tasks\"\n- \"I want to build X\"\n\n## Workflow\n\n1. **Discovery** -- Agent asks structured questions about your project (type, scope, stack, features)\n2. **SPECIFICATION.md** -- Generated and presented for review\n3. **IMPLEMENTATION.md** -- Tech decisions, patterns, directory structure\n4. **TASKS.md** -- Ordered work breakdown with file lists and acceptance criteria\n5. **BRANDING.md** -- Optional identity guide (colors, typography, voice)\n6. **PROMPT.md** -- Everything synthesized into a single executable prompt\n\nYou review and approve each document before the next is generated.\n\n## Partial Workflows\n\nYou don't have to run the full pipeline:\n\n| What You Say | What Happens |\n|-------------|-------------|\n| \"Just the spec\" | Generates SPECIFICATION.md only |\n| \"Skip to tasks\" | Lightweight spec + impl, then detailed tasks |\n| \"Just give me a prompt\" | Condensed discovery, straight to PROMPT.md |\n| \"Help me choose a stack\" | Interactive tech stack selection only |\n| \"What patterns should I use?\" | Design pattern consultation |\n\n## Reference Files\n\nThe skill includes detailed guides that inform each generation phase:\n\n| File | Purpose |\n|------|---------|\n| `references\u002Felicitation-guide.md` | Question framework for project discovery |\n| `references\u002Ftech-stacks.md` | Interactive tech stack selection with trade-offs |\n| `references\u002Fdesign-patterns.md` | Pattern catalog with selection guide |\n| `references\u002Fspecification-guide.md` | Template and rules for SPECIFICATION.md |\n| `references\u002Fimplementation-guide.md` | Template and rules for IMPLEMENTATION.md |\n| `references\u002Ftasks-guide.md` | Template and rules for TASKS.md |\n| `references\u002Fbranding-guide.md` | Template and rules for BRANDING.md |\n| `references\u002Fclaude-code-prompt.md` | Template and rules for PROMPT.md |\n\n## Project Structure\n\n```\nproject-architect\u002F\n├── SKILL.md                             # Skill definition (agentskills.io format)\n├── plugin.json                          # Claude Code plugin manifest\n├── LICENSE                              # MIT License\n├── README.md                            # This file\n└── references\u002F\n    ├── elicitation-guide.md             # Discovery question framework\n    ├── tech-stacks.md                   # Tech stack advisor\n    ├── design-patterns.md               # Pattern catalog\n    ├── specification-guide.md           # Spec template\n    ├── implementation-guide.md          # Implementation template\n    ├── tasks-guide.md                   # Tasks template\n    ├── branding-guide.md                # Branding template\n    └── claude-code-prompt.md            # Prompt template\n```\n\n## Compatibility\n\nThis skill follows the [Agent Skills specification](https:\u002F\u002Fagentskills.io\u002Fspecification) and is compatible with:\n\n- **Claude Code** (plugin + skill)\n- **Cursor**\n- **GitHub Copilot**\n- **OpenAI Codex**\n- **Gemini CLI**\n- **Roo Code**\n- **OpenCode**\n- **Kiro**\n- **And 30+ more agents** via [agentskills.io](https:\u002F\u002Fagentskills.io)\n\n## License\n\nMIT\n","Project Architect 是一个以文档为先的项目规划工具，能够将项目构想转化为详细的实施蓝图和一次性编码代理提示。其核心功能包括通过交互式流程生成五个相互关联的文档：SPECIFICATION.md、IMPLEMENTATION.md、TASKS.md、BRANDING.md 以及 PROMPT.md，覆盖了从项目定义到技术选型、任务分解直至品牌设计的全过程，并且特别优化了与40多种编码代理（如Claude Code, Cursor等）的兼容性。它适合用于需要快速启动并保持良好文档记录的各种规模软件开发项目中，无论是个人的小型实验还是企业级系统构建都能从中受益。","2026-06-11 02:47:36","CREATED_QUERY"]