MultiSpec

Multi-domain specification orchestration for humans and AI agents.

Overview

MultiSpec bridges the gap between organizational intent (MRD, PRD, UXD) and executable specifications for AI coding agents. It provides:

• ✍️ Domain-specific authoring - Separate specs for PM, UX, Engineering
• 📣 GTM synthesis - LLM-generated press releases, FAQs, narratives (Working Backwards)
• ⚙️ Technical synthesis - LLM-generated TRD, IRD from source specs
• 📊 Structured evaluation - Per-domain LLM judges with customizable rubrics
• 🔄 Reconciliation - Conflict detection and tradeoff resolution
• 📦 Target adapters - Export to SpecKit, GSD, GasTown, GasCity, OpenSpec

Installation

go install github.com/plexusone/multispec/cmd/multispec@v0.2.0

Quick Start

# Initialize a new project
multispec init user-onboarding

# Validate project structure
multispec lint

# Check project status
multispec status
multispec status --format json
multispec status --format html > status.html

Directory Structure

docs/specs/
├── CONSTITUTION.md                    # Repo-level governance
├── ROADMAP.md                         # Cross-project priorities
└── {project}/                         # kebab-case project name
    ├── source/                        # Human-authored specs
    │   ├── mrd.md
    │   ├── prd.md
    │   └── uxd.md
    ├── gtm/                           # LLM-generated GTM docs
    │   ├── press.md
    │   ├── faq.md
    │   └── narrative.md
    ├── technical/                     # LLM-generated technical docs
    │   ├── trd.md
    │   └── ird.md
    ├── eval/                          # All evaluations
    │   ├── mrd.eval.json
    │   ├── prd.eval.json
    │   └── ...
    ├── .graphize/                     # Requirement graph
    ├── spec.md                        # Reconciled execution spec
    ├── current-truth.md               # Post-ship state
    ├── status.html                    # Readiness report
    ├── index.md                       # MkDocs page
    └── multispec.yaml                 # Configuration

Document Lifecycle

HUMAN-AUTHORED (Source)
  MRD.md → PRD.md → UXD.md
           ↓
LLM-GENERATED (GTM) ← Working Backwards
  press.md → faq.md → narrative.md
           ↓
LLM-GENERATED (Technical)
  trd.md → ird.md
           ↓
RECONCILIATION
  All approved specs → spec.md
           ↓
TARGET EXPORT
  spec.md → SpecKit | GSD | GasTown | GasCity | OpenSpec
           ↓
POST-SHIP ALIGNMENT
  spec.md + reality → current-truth.md

CLI Commands

Command	Description	Status
init <project>	Initialize a new project with standard directory structure	Implemented
lint [project]	Validate directory structure and naming conventions	Implemented
status	Show project status and readiness gates	Implemented
targets	List available export targets	Implemented
eval [type]	Evaluate specs using LLM judges	Implemented
synthesize <type>	Generate specs from source docs	Implemented
reconcile	Generate unified execution spec	Implemented
approve <type>	Approve a spec for reconciliation	Implemented
export <target>	Export to target execution system	Implemented (SpecKit)
graph <cmd>	Manage requirement graphs (extract, export, query)	Implemented
serve	Start MCP server for AI integration	Implemented

Status Command

The status command shows project readiness with multiple output formats:

# Terminal output with readiness gates
multispec status -p myproject

# JSON for programmatic use
multispec status -p myproject --format json

# HTML report with traffic light indicator
multispec status -p myproject --format html > status.html

# Markdown for embedding in docs
multispec status -p myproject --format markdown

# CI mode - exits non-zero if not ready
multispec status -p myproject --ci

Readiness Gates

Gate	Description
Required specs present	All required source specs (mrd, prd, uxd, trd) exist
Evaluations passing	No blocking evaluation findings
Approvals obtained	All required specs have approvals
Execution spec generated	spec.md has been created

MCP Server

MultiSpec includes an MCP (Model Context Protocol) server for integration with AI coding assistants like Claude Code and Kiro CLI.

# Run MCP server directly
multispec-mcp

MCP Tools

Tool	Status	Description
list_projects	Implemented	List all multispec projects
get_project_status	Implemented	Get project readiness status
start_draft	Implemented	Initialize a new draft
update_draft	Implemented	Save draft content
eval_draft	Implemented	Evaluate draft against rubric
finalize_draft	Implemented	Promote draft to final spec
get_draft	Implemented	Retrieve current draft
discard_draft	Implemented	Delete a draft
get_spec	Implemented	Get specification content
get_eval	Implemented	Get evaluation results
run_eval	Implemented	Run evaluation against rubric
synthesize	Implemented	Generate a spec
reconcile	Implemented	Generate execution spec
approve	Implemented	Approve a specification
export	Implemented	Export to target system

Export Targets

Target	Description
speckit	GitHub Spec-Kit format
gsd	Get Shit Done (PLAN.md, STATE.md)
gastown	GasTown formulas and beads
gascity	GasCity city.toml configuration
openspec	OpenSpec portable format (future)

Dependencies

• structured-evaluation - Rubric and evaluation types
• graphize - Requirement graph extraction

Development

# Build
make build

# Test
make test

# Lint
make lint

# Install locally
make install

Project Status

See ROADMAP.md for detailed implementation status and CHANGELOG.md for release history.

Current Version: v0.2.0

Phase	Status
Phase 0: Foundation	Complete
Phase 1: Directory Structure	Complete
Phase 2: Evaluation Engine	Complete
Phase 3: GTM & Technical Synthesis	Complete
Phase 4: Reconciliation Engine	Complete
Phase 5: Target Adapters	Partial (SpecKit)
Phase 6: Claude Code Integration	Complete
Phase 7: Graphize Integration	Complete
Phase 8: Advanced Features	Not Started

License

MIT