Resource Designer
microsoft/terraform-provider-fabric
Research SDK contracts, design Terraform schema approach, and compose a GitHub issue for a new resource, data source, ephemeral resource, or enhancement to an existing resource.
Documentation-first project planning that produces implementation-ready blueprints and single-shot coding agent prompts.
Install Project Architect
$ npx skills add ersinkoc/project-architect --skill project-architect -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ersinkoc/project-architect project-architect --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "project-architect" agent skill from https://github.com/ersinkoc/project-architect/tree/main into .claude/skills/project-architect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-architect", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ersinkoc/project-architect --skill project-architect -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ersinkoc/project-architect project-architect --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "project-architect" agent skill from https://github.com/ersinkoc/project-architect/tree/main into .agents/skills/project-architect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-architect", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ersinkoc/project-architect --skill project-architect -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ersinkoc/project-architect project-architect --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "project-architect" agent skill from https://github.com/ersinkoc/project-architect/tree/main into .cursor/skills/project-architect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-architect", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ersinkoc/project-architect --skill project-architect -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ersinkoc/project-architect project-architect --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "project-architect" agent skill from https://github.com/ersinkoc/project-architect/tree/main into .gemini/skills/project-architect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-architect", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ersinkoc/project-architect project-architectInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ersinkoc/project-architect --skill project-architect -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "project-architect" agent skill from https://github.com/ersinkoc/project-architect/tree/main into .github/skills/project-architect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-architect", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ersinkoc/project-architect --skill project-architect -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ersinkoc/project-architect project-architect --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "project-architect" agent skill from https://github.com/ersinkoc/project-architect/tree/main into .opencode/skills/project-architect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-architect", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
project-architect- GitHub stars
- 259
- Token cost
- ~2.3k tokens
- SKILL.md length
- 840 words
- Files
- 13 (incl. references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Documentation-first project planning that produces implementation-ready blueprints and single-shot coding agent prompts.
- Works in 6 steps: Discovery & Elicitation → SPECIFICATION.md → IMPLEMENTATION.md → …
- User wants to: plan a project
- SKILL.md covers Output Pipeline, Reference Files, Workflow and Operating Rules, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Project Architect is an agent skill from ersinkoc/project-architect. Documentation-first project planning that produces implementation-ready blueprints and single-shot coding agent prompts. Generates 4 interconnected docs — SPECIFICATION.md, IMPLEMENTATION.md, TASKS.md, BRANDING.md — plus a self-contained PROMPT.md for autonomous execution by any coding agent. Includes interactive tech stack selection, design pattern recommendations, and architecture decisions with trade-off analysis. Trigger when user wants to: plan a project, create specs, architect a system, break work into…
Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including reference files (for example `README.md`, `plugin.json` and `references/agent-prompt.md`). Compatibility notes: Works with any coding agent that supports file read/write and user interaction. Optimized for WrongStack and Claude Code, also compatible with Cursor, Gemini…
It sits in Development, covering Project management and Design patterns. The repository describes itself as: Documentation-first project planning agent skill. Generates specs, implementation plans, tasks, and single-shot prompts for coding agents. Compatible with Claude Code, Cursor… The licence is MIT.
When your agent uses it
- User wants to: plan a project
- Architect a system
- Break work into tasks
- Choose a tech stack
Example prompts
- “plan my project”
- “spec this out”
- “architect”
- “/project-architect”
Requirements
- Compatibility (from SKILL.md): Works with any coding agent that supports file read/write and user interaction. Optimized for WrongStack and Claude Code, also compatible with Cursor, Gemini CLI, Codex, and other agentskills.io-compatible agents.
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 220653c. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
Works with any coding agent that supports file read/write and user interaction. Optimized for WrongStack and Claude Code, also compatible with Cursor, Gemini CLI, Codex, and other agentskills.io-compatible agents.
From compatibility in the SKILL.md frontmatter.
Context cost
Project Architect loads about 2.3k tokens when it runs, and up to ~21k if it reads all its reference files. Until then it costs about 211 tokens; SKILL.md has 840 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from ersinkoc/project-architect at commit 220653c, republished under its MIT licence (© ersinkoc). 840 words, ~2,268 tokens.
Download SKILL.mdSave it as
.claude/skills/project-architect/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.- name
- project-architect
- description
- Documentation-first project planning that produces implementation-ready blueprints and single-shot coding agent prompts. Generates 4 interconnected docs — SPECIFICATION.md, IMPLEMENTATION.md, TASKS.md, BRANDING.md — plus a self-contained PROMPT.md for autonomous execution by any coding agent. Includes interactive tech stack selection, design pattern recommendations, and architecture decisions with trade-off analysis. Trigger when user wants to: plan a project, create specs, architect a system, break work into tasks, choose a tech stack, get design pattern advice, generate a coding agent prompt, or do documentation-first development. Phrases: "plan my project", "spec this out", "architect", "help me plan", "what stack should I use", "generate a prompt", "break this into tasks", "project docs", "I want to build X".
- compatibility
- Works with any coding agent that supports file read/write and user interaction. Optimized for WrongStack and Claude Code, also compatible with Cursor, Gemini CLI, Codex, and other agentskills.io-compatible agents.
- license
- MIT
- metadata.author
- ersinkoc
- metadata.version
- 1.1.0
- metadata.category
- development
Project Architect
A documentation-first project planning system that produces implementation-ready blueprints and agent-ready prompts. The philosophy: think deeply, document thoroughly, then execute with zero ambiguity. The final PROMPT.md is self-contained and portable — hand it to WrongStack, Claude Code, or any agent that reads and writes files.
Output Pipeline
[Discovery] → SPECIFICATION.md → IMPLEMENTATION.md → TASKS.md → BRANDING.md
(The What) (The How) (The Work) (Identity)
↓ ↓ ↓
└────────────────────┴───────────────────┘
↓
PROMPT.md
(Single-Shot Agent Prompt)Each document feeds the next. The final PROMPT.md synthesizes all documents into a single prompt optimized for single-shot execution by any coding agent (WrongStack, Claude Code, Cursor, and others).
Reference Files
Read the appropriate reference file before generating each document:
| Phase | Reference File | When to Read |
|---|---|---|
| Discovery | ${CLAUDE_PLUGIN_ROOT}/references/elicitation-guide.md | Before asking any questions |
| Tech Stack | ${CLAUDE_PLUGIN_ROOT}/references/tech-stacks.md | When user needs stack selection help |
| Patterns | ${CLAUDE_PLUGIN_ROOT}/references/design-patterns.md | When making architecture decisions |
| Specification | ${CLAUDE_PLUGIN_ROOT}/references/specification-guide.md | Before generating SPECIFICATION.md |
| Implementation | ${CLAUDE_PLUGIN_ROOT}/references/implementation-guide.md | Before generating IMPLEMENTATION.md |
| Tasks | ${CLAUDE_PLUGIN_ROOT}/references/tasks-guide.md | Before generating TASKS.md |
| Branding | ${CLAUDE_PLUGIN_ROOT}/references/branding-guide.md | Before generating BRANDING.md |
| Prompt | ${CLAUDE_PLUGIN_ROOT}/references/agent-prompt.md | Before generating PROMPT.md |
Workflow
Phase 0: Discovery & Elicitation
Read ${CLAUDE_PLUGIN_ROOT}/references/elicitation-guide.md for the full question framework.
Before writing anything, understand the project through structured conversation.
Use AskUserQuestion tool aggressively for choices — the user should tap, not type,
whenever possible.
Minimum understanding before any document generation:
- What does this project do? (elevator pitch)
- Who is it for? (target audience)
- What's the project type? (web app, CLI, library, API, mobile, desktop, infra tool)
- What's the scope? (MVP vs full product)
- Tech stack direction (or "help me choose")
If the user says "help me choose a stack":
Read ${CLAUDE_PLUGIN_ROOT}/references/tech-stacks.md and run the interactive stack selection flow.
Present options with trade-offs using AskUserQuestion.
Phase 1: SPECIFICATION.md
Read ${CLAUDE_PLUGIN_ROOT}/references/specification-guide.md before generating.
Defines what the project is. Technology-aware but not implementation-detailed. After generating, pause for user review.
Phase 2: IMPLEMENTATION.md
Read ${CLAUDE_PLUGIN_ROOT}/references/implementation-guide.md AND ${CLAUDE_PLUGIN_ROOT}/references/design-patterns.md before generating.
Translates specification into how to build it. This is where you:
- Recommend design patterns based on the project's needs (consult patterns reference)
- Define concrete directory structures with file-by-file purpose
- Choose dependencies with rationale
- Define module interfaces and data flows
- Include code snippets for critical patterns (signatures, types, structural examples)
Pattern Recommendations: Consult ${CLAUDE_PLUGIN_ROOT}/references/design-patterns.md and recommend specific
patterns with rationale. Don't just name-drop — show how each pattern applies to THIS project
with a short code sketch.
Phase 3: TASKS.md
Read ${CLAUDE_PLUGIN_ROOT}/references/tasks-guide.md before generating.
Converts implementation into ordered work items. Each task must be:
- Completable by a coding agent in a single session
- Self-contained with full context
- Ordered by strict dependency chain
- Include the exact files to create/modify
Phase 4: BRANDING.md (Optional)
Read ${CLAUDE_PLUGIN_ROOT}/references/branding-guide.md before generating.
Only generate if user wants it or the project is user-facing.
Phase 5: PROMPT.md (Always Generate)
Read ${CLAUDE_PLUGIN_ROOT}/references/agent-prompt.md before generating.
This is the most critical output. Synthesize all documents into a single-shot prompt that any coding agent (WrongStack, Claude Code, Cursor, …) can execute to build the entire project from scratch. The prompt must be completely self-contained, with inline code for complex patterns and an ordered checklist of every file to create.
Show full SKILL.md (364 more words)Show less
Operating Rules
Document order is sequential. SPEC → IMPL → TASKS → BRANDING → PROMPT. Never skip ahead.
Pause between documents. Present each doc, ask for approval before the next.
Use
AskUserQuestionfor decisions. Tech stack, database, auth, deployment — any decision with 2-4 clear options should use interactive selection, not freeform questions.Recommend, don't dictate. Present 2-3 options with trade-offs. Let user choose. If user says "you pick", choose and explain why.
Scale to project size. Weekend project = concise docs, 15-30 tasks. Enterprise platform = thorough docs, 100+ tasks. Match depth to ambition.
Always save as files. Every document goes to
./[project-name]/docs/in the current working directory as Markdown files. Use theWritetool to save them.Cross-reference between documents. IMPL references SPEC sections. TASKS reference IMPL modules. PROMPT inlines everything needed.
No filler. Every line must be specific to THIS project. Remove sections that would be generic boilerplate.
Design patterns are recommendations. When choosing patterns for IMPLEMENTATION.md, consult
${CLAUDE_PLUGIN_ROOT}/references/design-patterns.mdand match patterns to the project's specific needs. Include a brief "why this pattern" rationale for each recommendation.
Plugin-Aware Integration
Check if the user has other Claude Code plugins or skills installed. If they do:
- Frontend framework planner (react-app-planner, nextjs-app-planner, etc.) → Suggest using it for deeper framework decisions after architect docs are done
- Frontend design → Reference it for UI component guidance in IMPLEMENTATION.md
- Brand/design skills → Integrate into BRANDING.md generation
- MCP builder → If project includes an MCP server, note the skill for implementation phase
- Language-specific skills (typescript-mastery, etc.) → Incorporate coding standards from that skill into IMPLEMENTATION.md
Mention relevant skills naturally: "You have a react-app-planner skill — want me to use it for deeper React architecture decisions after we finish the high-level plan?"
Handling Partial Input
| Scenario | Action |
|---|---|
| Vague 1-liner | Full elicitation flow with AskUserQuestion |
| Detailed brief | Extract answers, ask only gaps |
| Existing spec uploaded | Validate, suggest improvements, continue from Phase 2 |
| "Just the spec" | Generate SPECIFICATION.md only, offer to continue later |
| "Skip to tasks" | Gather context, generate lightweight spec+impl, then tasks |
| "Just give me a prompt" | Condensed discovery → direct PROMPT.md generation |
| "Help me choose a stack" | Run tech stack advisor from ${CLAUDE_PLUGIN_ROOT}/references/tech-stacks.md |
| "What patterns should I use?" | Consult ${CLAUDE_PLUGIN_ROOT}/references/design-patterns.md, ask about project |
© ersinkoc, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 12 other files (references) in the repository root of ersinkoc/project-architect.
- SKILL.md
- .gitignore
- LICENSE
- README.md
- plugin.json
- references/agent-prompt.md
- references/branding-guide.md
- references/design-patterns.md
- references/elicitation-guide.md
- references/implementation-guide.md
- references/specification-guide.md
- references/tasks-guide.md
- references/tech-stacks.md
Open the folder on GitHubat commit 220653c
Compare with similar skills
Project Architect next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Project Architect this skillersinkoc/project-architect | 259 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Resource Designermicrosoft/terraform-provider-fabric | 128 | — | ~6k | Automated safety check: Pass | MPL-2.0 | |
| Vercel Composition Patternssupabase/supabase | 111k | 58 repos | ~726 | Automated safety check: Pass | MIT | |
| Swiftui View RefactorDimillian/Skills | 4k | 5 repos | ~2k | Automated safety check: Pass | MIT | |
| RTK Rust Design Patternsrtk-ai/rtk | 83k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| LoopX PR Program Managerloopx-project/loopx | 6.2k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
- Official
Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
Swiftui View Refactor
Dimillian/Skills
Refactor and review SwiftUI view files with strong defaults for small dedicated subviews, MV-over-MVVM data flow, stable view trees, explicit dependency injection, and correct Observation usage.
RTK Rust Design Patterns
rtk-ai/rtk
Describes seven Rust design patterns for the RTK CLI filter modules, with when to use each, RTK examples, and notes on when a pattern is overkill.
LoopX PR Program Manager
loopx-project/loopx
Tracks a group of pull or merge requests across repositories as durable LoopX state: inventory, reconcile changes, keep priorities and a roadmap, and monitor over time.
Effect Client Wrapper
UsefulSoftwareCo/executor
Pattern for wrapping third-party SDK clients (Stripe, Resend, AWS, etc.) with Effect.
Related
Categories
Questions about Project Architect
What does Project Architect do?
Documentation-first project planning that produces implementation-ready blueprints and single-shot coding agent prompts. Project Architect is an agent skill from ersinkoc/project-architect. Documentation-first project planning that produces implementation-ready blueprints and single-shot coding agent prompts.
When should I use Project Architect?
Project Architect fits situations like: user wants to: plan a project; architect a system; break work into tasks; choose a tech stack.
How do I install Project Architect in Claude Code?
Run `npx skills add ersinkoc/project-architect --skill project-architect -a claude-code`. Or copy the skill folder (the ersinkoc/project-architect repository) into .claude/skills/project-architect in your project. Claude Code loads it when a task matches its description.
How do I install Project Architect in Codex?
Run `npx skills add ersinkoc/project-architect --skill project-architect -a codex`. Or copy the skill folder (the ersinkoc/project-architect repository) into .agents/skills/project-architect in your project. Codex loads it when a task matches its description.
Can I use Project Architect in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ersinkoc/project-architect --skill project-architect -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/project-architect, .gemini/skills/project-architect, .github/skills/project-architect and .opencode/skills/project-architect in your project.
What does Project Architect need to run?
SKILL.md names no scripts, command-line tools or credentials: Project Architect is instructions for the agent only. Compatibility (from SKILL.md): Works with any coding agent that supports file read/write and user interaction. Optimized for WrongStack and Claude Code, also compatible with Cursor, Gemini CLI, Codex, and other agentskills.io-compatible agents. .
Does Project Architect access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Project Architect safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Project Architect use?
Project Architect is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Project Architect use?
About 2.3k tokens (SKILL.md is roughly 9.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 19k tokens, read only when the agent opens those files.
What are the alternatives to Project Architect?
Skills that share tags, products or a category with Project Architect: Resource Designer (microsoft/terraform-provider-fabric, 128 stars), Vercel Composition Patterns (supabase/supabase, 111k stars), Swiftui View Refactor (Dimillian/Skills, 4k stars) and RTK Rust Design Patterns (rtk-ai/rtk, 83k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Project Architect?
ersinkoc (a GitHub user) maintains it in ersinkoc/project-architect, which has 259 GitHub stars. The repository was last updated on October 3, 2026.
Source: ersinkoc/project-architect on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.