Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/LIDR-academy/lidr-specboot/llms.txt

Use this file to discover all available pages before exploring further.

This guide walks you through installing Specboot into an existing project, customizing it for your codebase, and wiring it up to OpenSpec so you can run your first AI-assisted, spec-driven workflow in under 10 minutes.
1

Install OpenSpec Globally (Prerequisite)

Specboot is designed to be used alongside OpenSpec, the spec-driven development framework that powers the /ff, /apply, /verify, and /archive command flow. Install it globally before proceeding.
npm install -g @fission-ai/openspec@latest
OpenSpec requires Node.js 20.19.0 or higher. Once installed, navigate to your project directory and run:
cd your-project
openspec init
This creates the initial OpenSpec scaffolding (config.yml and supporting directories) inside your project. You will update config.yml in Step 4 after Specboot is installed.
2

Bootstrap Specboot into Your Project

Run the Specboot CLI from inside your project directory. It copies all template files and automatically creates the symlink structure — no manual linking required.
npx @lidr/lidr-specboot
To target a specific directory rather than the current working directory, pass the path as an argument:
npx @lidr/lidr-specboot /path/to/your/project
After the command completes, you will see a summary like:
  lidr-specboot
  Augmented Spec-driven development powered by OpenSpec

  Target: /your/project

  Files copied  42
  Symlinks      18
  Skipped       0

  Next steps:
  1. Update docs/ to match your project (stack, API, data model)
  2. openspec init
  3. /enrich-us  ->  /ff  ->  /apply
Specboot creates the following structure:
your-project/
├── docs/
│   ├── base-standards.md        # Single source of truth for all agents
│   ├── backend-standards.md
│   ├── frontend-standards.md
│   ├── documentation-standards.md
│   ├── api-spec.yml
│   └── data-model.md
├── ai-specs/
│   ├── agents/                  # Role definitions (backend, frontend, etc.)
│   └── skills/                  # Reusable skill workflows
├── AGENTS.md  -> docs/base-standards.md
├── CLAUDE.md  -> docs/base-standards.md
├── codex.md   -> docs/base-standards.md
└── GEMINI.md  -> docs/base-standards.md
Claude Code users: You can use the Claude Code plugin as an alternative installation method. Run the same npx @lidr/lidr-specboot command through the Claude Code agent. Note that this only handles the file copy and symlink creation — it does not install OpenSpec, does not run openspec init, and does not customize docs/ for you. You still need to complete Steps 1, 3, and 4.
3

Customize docs/ for Your Project (Mandatory)

This step is required. The files Specboot installs in docs/ are generic reference examples from the LIDR project. If you skip this step, every AI agent will operate on generic technical context instead of your real project’s stack, domain language, and architecture.Update the following files to reflect your project’s specifics:
FileWhat to update
docs/base-standards.mdCore principles, language rules, coding conventions
docs/backend-standards.mdYour API patterns, database technology, security rules, testing requirements
docs/frontend-standards.mdYour framework (React, Vue, etc.), UI/UX guidelines, state management
docs/documentation-standards.mdDoc structure, formatting conventions, AI standards
docs/api-spec.ymlYour actual API endpoints (OpenAPI 3.0 format)
docs/data-model.mdYour real database schemas and domain entities
You can automate this with your AI copilot using the following prompt:
Following the same base structure already present in docs/, update all technical
context documents according to this project's specifics.

Requirements:
- Keep the same document set and file names in docs/.
- Replace generic content with this project's real stack, architecture patterns,
  coding conventions, and domain terminology.
- Update backend, frontend, and documentation standards to reflect actual
  practices used by this team.
- Update docs/api-spec.yml and docs/data-model.md so they match the real
  endpoints and entities of this project.
- Ensure all references are internally consistent and aligned across docs/.
- Keep everything in English and make guidance implementation-ready for AI agents.
4

Point OpenSpec config.yml to Your docs/ and ai-specs/

After running openspec init and customizing docs/, update your project’s config.yml to reference the Specboot paths. This is what gives OpenSpec the technical context it needs to generate accurate specs and implement them autonomously.Use the following prompt with your copilot to automate the update:
Update my openspec config.yml context to reference this repository's docs
and ai-specs structure.

Requirements:
- Use docs/base-standards.md as the single source of truth.
- Include docs/backend-standards.md, docs/frontend-standards.md,
  docs/documentation-standards.md.
- Include docs/api-spec.yml and docs/data-model.md.
- Tell the agent to adopt ai-specs/agents/backend-developer.md for backend
  work and ai-specs/agents/frontend-developer.md for frontend work.
- Mention ai-specs/skills as workflow guidance.
- Keep all paths relative to the project root.
The resulting config.yml will look similar to this — replace the example tech stack details with your own:
context: |
  Tech stack: TypeScript, Node.js, Express, Prisma, Domain-Driven Design (DDD)
  Architecture: Clean Architecture with Domain, Application, and Presentation layers
  We use conventional commits
  Domain: LTI (Leadership. Technology. Impact) ATS platform
  All code, comments, documentation, and technical artifacts must be in English

  Project specs (single source of truth): All artifact creation and implementation
  MUST follow the project's technical context in ai-specs/. Read and apply these
  when creating or implementing:
  - docs/base-standards.md — core principles, TDD, language standards, links to
    backend/frontend/docs standards
  - docs/backend-standards.md — API, database, testing, security (backend changes)
  - docs/frontend-standards.md — React, UI/UX (frontend changes)
  - docs/api-spec.yml — API contracts and endpoint definitions
  - docs/data-model.md — domain and data model
  - docs/documentation-standards.md — docs structure and maintenance
  For implementation: adopt the relevant agent from ai-specs/agents/ (e.g.
  backend-developer.md for backend, frontend-developer.md for frontend).
  Use ai-specs/skills/ for workflow guidance when applicable.

# Per-artifact rules (optional)
# Add custom rules for specific artifacts.
rules:
  # Global: apply ai-specs when creating any artifact
  _global:
    - Before creating any artifact, read and apply docs/base-standards.md
    - For backend-related artifacts, read docs/backend-standards.md and adopt
      guidelines from ai-specs/agents/backend-developer.md
    - For frontend-related artifacts, read docs/frontend-standards.md and adopt
      guidelines from ai-specs/agents/frontend-developer.md
    - Use docs/api-spec.yml and docs/data-model.md for API and data consistency
      in specs and tasks
Once config.yml is saved, verify the setup by confirming your copilot loads the right file on startup:
  • Claude / Cursor → reads CLAUDE.md → docs/base-standards.md
  • GitHub Copilot → reads codex.md → docs/base-standards.md
  • Gemini → reads GEMINI.md → docs/base-standards.md
You are ready to run your first OpenSpec workflow:
/enrich-us SCRUM-10
/ff SCRUM-10
/apply SCRUM-10
/verify SCRUM-10
/adversarial-review SCRUM-10
/archive SCRUM-10
/commit

​
Next Steps

OpenSpec Workflow Guide

Learn the full /enrich-us → /ff → /apply → /verify → /archive command flow and how each step maps to a spec artifact.

Customization Guide

Detailed guidance on adapting docs/, agents, and skills to your project’s real architecture, domain, and tooling.

Build docs developers (and LLMs) love

Get started for freeTalk to us