Project Setup
Bootstrap a new or existing repo with SDD-style CLAUDE.md, ai-context memory files, and stack-aware skill registry via /project-setup.
Overview
Project Setup is an agent skill for the Build phase that deploys SDD architecture with engram persistence and an ai-context/ memory layer in the current project.
Install
npx skills add https://github.com/fearovex/claude-config --skill project-setupWhat is this skill?
- 4-step procedural flow: detect stack, generate CLAUDE.md, initialize ai-context/, wire engram + skill registry
- Auto-detects language, frameworks, ORM, tests, and folder conventions from manifests and config
- Creates five ai-context memory files for SDD cycle continuity
- Registers relevant skills from detected stack (Node, Python, Go, Rust, Java, etc.)
- Triggers: /project-setup, initialize project, setup SDD, configure claude project
- 5 ai-context memory files initialized
- 4-step setup process documented
Adoption & trust: 1 installs on skills.sh; 1 GitHub stars; 3/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
You opened a real codebase but your agent still lacks project-specific CLAUDE.md, structured memory, and stack-linked skills.
Who is it for?
New SDD projects or brownfield repos where you want one command to align Claude Code with actual dependencies and layout.
Skip if: Repos you refuse to let the agent read manifests from, or teams with no interest in CLAUDE.md / ai-context conventions.
When should I use this skill?
/project-setup, initialize new project, setup SDD, configure claude project, new sdd project.
What do I get? / Deliverables
You get generated CLAUDE.md, initialized ai-context files, engram context, and a skill registry aligned to the detected stack—ready for spec-driven work.
- Root CLAUDE.md
- ai-context/ memory files
- Engram project context
Recommended Skills
Journey fit
Project setup lands when you are wiring the agent workspace for sustained development—the Build phase agent-tooling shelf. Agent-tooling covers CLAUDE.md, persistent memory layers, and skill registries that make Claude Code effective in-repo.
How it compares
One-shot project bootstrap for agent memory—not a daily code review or deployment pipeline skill.
Common Questions / FAQ
Who is project-setup for?
Solo and indie developers adopting fearovex-style SDD with engram and ai-context/ who use Claude Code or similar agents in the repo root.
When should I use project-setup?
At the start of Build when onboarding an agent to a repo—after git exists and manifests are in place—via /project-setup or 'setup SDD' / 'configure claude project'.
Is project-setup safe to install?
It writes and reads project files; confirm scope in SKILL.md and review the Security Audits panel on this page before installing.
SKILL.md
READMESKILL.md - Project Setup
# project-setup > Deploys the complete SDD architecture with engram persistence and ai-context/ memory layer in the current project. **Triggers**: `/project-setup`, initialize project, setup sdd, configure claude project, new sdd project --- ## What this skill does When the user runs `/project-setup`, I analyze the current project and generate: 1. `CLAUDE.md` at the project root with real detected context 2. `ai-context/` with the 5 memory files initialized 3. Engram project context for the SDD cycle 4. Registry of relevant skills based on the detected stack --- ## Process ### Step 1 — Project detection I read and analyze: - `package.json` / `pyproject.toml` / `go.mod` / `Cargo.toml` / `pom.xml` - Folder structure (src/, app/, lib/, tests/, etc.) - Configuration files (tsconfig, eslint, prettier, etc.) - README.md if it exists - Existing docs folders - `.git/` to confirm it is a repository **I infer:** - Main language and version - Framework(s) in use - Database / ORM - Testing tools - Build / bundler tools - Detected naming conventions (camelCase, snake_case, etc.) - Folder structure (feature-based, layer-based, monorepo, etc.) ### Step 2 — Generate project CLAUDE.md I create `CLAUDE.md` at the root with these sections: ```markdown # [Project Name] ## Stack [Detected stack with versions] ## Architecture [Explained folder structure] [Detected architectural pattern] ## Conventions [Detected naming conventions] [Observed code patterns] ## Important Commands [Scripts from package.json / Makefile / etc.] ## Project Memory At the start of each session, read the relevant files in ai-context/: - ai-context/stack.md — Detailed technical stack - ai-context/architecture.md — Architecture decisions - ai-context/conventions.md — Team conventions - ai-context/known-issues.md — Known bugs and gotchas - ai-context/changelog-ai.md — AI change history After completing significant work: update the relevant files or run /memory-update so the AI updates them. ## Active Skills [List of relevant skills for this project] ## SDD — Spec-Driven Development This project uses SDD. Entry points: `/sdd-explore <topic>` (investigate first) or `/sdd-propose <change-name>` (start from proposal). Multi-phase flows are handled by the orchestrator as meta-commands — type them directly in conversation. Phase skills: `/sdd-explore`, `/sdd-propose`, `/sdd-spec`, `/sdd-design`, `/sdd-tasks`, `/sdd-apply`, `/sdd-verify`, `/sdd-archive`. ``` ### Step 3 — Initialize ai-context/ I create the 5 files with real content based on what was detected: #### `ai-context/stack.md` ```markdown # Technical Stack Last updated: [date] ## Language - [Language]: [version] ## Main Framework - [Framework]: [version] - [Relevant configuration details] ## Database / ORM - [If applicable] ## Testing - [Testing framework] - [Commands to run tests] ## Build / Bundler - [Tool]: [version] - [Build command] - [Dev command] ## Key Dependencies | Package | Version | Purpose | | ------- | --------- | -------------- | | [name] | [version] | [what it does] | ``` #### `ai-context/architecture.md` ```markdown # Project Architecture Last updated: [date] ## Architectural Pattern [Detected: feature-based / layer-based / clean architecture / etc.] ## Folder Structure [Explained tree with the purpose of each folder] ## Architecture Decisions | Decision | Choice | Alternatives | Reason | | -------- | ------ | ------------ | ------ | [Inferred from existing code] ## Data Flow [Description of the main flow] ## Entry Points [Main entry points of the system] ``` #### `ai-context/conventions.md` ```markdown # Project Conventions Last updated: [date] ## Naming - Files: [dete