Skip to content
architecture-council logo

Architecture Council Skill

architecture-council

Orchestrates parallel specialized agents for major architectural decisions. Spawns perspective agents (Schema-Sage, Repo-Maven, Event-Oracle, etc.), collects findings to shared journal, synthesizes via Architect-Prime.

SKILL.md

Full skill instructions

Architecture Council Skill

Purpose

Orchestrate collaborative architectural analysis using specialized perspective agents. Used for major architectural decisions that benefit from multiple viewpoints and grounded research.

When to Invoke

SignalAction
"Need to make an architectural decision"Full council
"Design a new service architecture"Full council
"Should we use pattern X or Y?"Full council
"Create an ADR for..."Full council
"Review and revise specification"Full council

Council Composition

AgentDomainResearch FocusOutput Section
Schema-SageTypes & ValidationSchema patterns, type safetySchema Architecture
Repo-MavenPersistenceRepository patterns, SQLRepository Patterns
Event-OracleEvent SourcingEvents, EventLog, audit trailsEvent Architecture
Entity-WeaverCluster EntitiesEntities, aggregates, stateEntity Patterns
Infra-SmithInfrastructureDatabase, deployment, layersInfrastructure
Architect-PrimeSynthesisAll domains, integrationFinal spec/​ADR

Protocol

Phase 1: Council Assembly

1. Create shared journal file:
   thoughts/​shared/​journal/​YYYY-MM-DD-<topic>-council.md

2. Define section ownership per agent

3. Spawn agents IN PARALLEL with:
   - Assigned research documents
   - MCPs to query (deepwiki, exa)
   - Section template
   - Journal location

Phase 2: Research & Writing (Parallel)

Each agent:

  1. Reads assigned research documents
  2. Queries MCPs for grounded verification
  3. Extracts patterns relevant to their domain
  4. Writes findings to their journal thread
  5. Signals "READY FOR SYNTHESIS" when complete

Phase 3: Synthesis (Architect-Prime)

  1. Read all agent threads
  2. Identify:
    • Consensus patterns (all agree)
    • Conflicts (agents disagree)
    • Gaps (uncovered areas)
  3. Synthesize into final spec or ADR
  4. Resolve conflicts with rationale

Phase 4: External Enrichment (Optional)

For industry standards integration:

  1. Use exa/​playwright for external research
  2. Cross-reference with ISA-95, FDA, ISO, etc.
  3. Add regulatory grounding to spec

Phase 5: Deliverables

Research → Journal → Spec → ADR → WBS
ArtifactLocationPurpose
Journalthoughts/​shared/​journal/Raw agent findings
Specthoughts/​shared/​specs/Synthesized specification
ADRassets/​documents/Architectural Decision Record
WBSthoughts/​shared/​plans/Work Breakdown Structure

Journal Format

# <Topic> Architecture Council — Shared Journal

**Session**: YYYY-MM-DD
**Purpose**: <Goal of the council>
**Input**: <Research documents count>
**Output**: <Target spec location>

---

## Council Members

| Name | Domain | Research Docs | Section Ownership |
|------|--------|---------------|-------------------|
| Schema-Sage | Types | doc1.md, doc2.md | Section 3 |
| ... | ... | ... | ... |

---

## Protocol

1. Each agent reads their assigned research documents
2. Extract patterns relevant to their section
3. Write findings to their thread below (append only)
4. When ready, write "READY FOR SYNTHESIS"
5. Architect-Prime synthesizes all threads into final spec

---

## Thread: Schema-Sage

### Executive Summary
[Summary of findings]

### 1. Pattern Category
[Detailed findings with code examples]

### Recommendations for v3
[Actionable recommendations]

---

**READY FOR SYNTHESIS**

---

## Thread: Repo-Maven
[...]

## Thread: Event-Oracle
[...]

## Synthesis: Architect-Prime
[Final integration]

Agent Spawn Templates

Schema-Sage Spawn

You are Schema-Sage, the council's type system and validation specialist.

**Your Domain**: Schema patterns, branded types, validation, TaggedClass, transforms

**Research Documents**:
- <list of assigned docs>

**MCPs to Query**:
- deepwiki: Effect-TS/​effect (Schema module)

**Output Location**: <journal-path>#Thread: Schema-Sage

**Protocol**:
1. Read your assigned research documents
2. Query deepwiki to verify any uncertain patterns
3. Extract patterns with code examples
4. Write to your journal thread
5. Signal "READY FOR SYNTHESIS" when complete

See Agent Definitions

For full agent definitions, see:

  • .claude/​agents/​council/​schema-sage.md
  • .claude/​agents/​council/​repo-maven.md
  • .claude/​agents/​council/​event-oracle.md
  • .claude/​agents/​council/​entity-weaver.md
  • .claude/​agents/​council/​infra-smith.md
  • .claude/​agents/​council/​architect-prime.md

MCP Integration

deepwiki Queries

mcp__deepwiki__ask_question
  repoName: "Effect-TS/​effect"
  question: "Is my understanding of [PATTERN] correct? I believe..."

exa Research (External Standards)

mcp__exa__search
  query: "ISA-95 manufacturing operations management event sourcing"

playwright (Standards Scraping)

For regulatory documents:

mcp__playwright__navigate
  url: "https://www.isa.org/​standards-and-publications/​..."

Example Invocation

User Request

"We need to design the v3 service architecture for IIoT. Should we use event sourcing?"

Claude Response

I'll convene the Architecture Council to analyze this decision.

**Creating shared journal**: thoughts/​shared/​journal/​2026-01-25-v3-iiot-council.md

**Spawning council members in parallel**:

1. Schema-Sage → IIoT schema patterns
2. Repo-Maven → Repository patterns analysis  
3. Event-Oracle → Event sourcing fit assessment
4. Entity-Weaver → Entity/​aggregate patterns
5. Infra-Smith → Database and infrastructure

[Agents run in parallel, writing to journal]

**Synthesis phase**: Architect-Prime integrating findings...

**Deliverables**:
- Journal: thoughts/​shared/​journal/​2026-01-25-v3-iiot-council.md
- Spec: thoughts/​shared/​specs/​2026-01-25-v3-service-architecture.md
- ADR: assets/​documents/​iiot/​ADR-0012-event-sourcing-boundaries.md

Task Dependencies Pattern

Use task dependencies for ordered execution:

// Phase 1: Research (parallel)
const schemaSage = Task.create({ name: "schema-sage-research", ... })
const repoMaven = Task.create({ name: "repo-maven-research", ... })
const eventOracle = Task.create({ name: "event-oracle-research", ... })

// Phase 2: Synthesis (depends on all Phase 1)
const synthesis = Task.create({
  name: "architect-prime-synthesis",
  blockedBy: [schemaSage.id, repoMaven.id, eventOracle.id],
  ...
})

// Phase 3: ADR (depends on synthesis)
const adr = Task.create({
  name: "write-adr",
  blockedBy: [synthesis.id],
  ...
})

Related Skills

SkillIntegration
/​grounded-researchAgents use this for MCP queries
/​effect-patternsSchema-Sage expertise
/​effect-service-authoringEntity-Weaver expertise
/​research-councilLighter variant for pure research

Anti-Patterns

DON'T: Skip the journal

❌ Agents write directly to spec
✅ Agents write to journal, Prime synthesizes to spec

DON'T: Sequential agent execution

❌ Run Schema-Sage, wait, run Repo-Maven, wait...
✅ Spawn all agents in parallel

DON'T: Ungrounded assertions

❌ "I believe this is the pattern..."
✅ "[VERIFIED via deepwiki] The current pattern is..."

DON'T: Skip external research

❌ "Event sourcing seems right for IIoT"
✅ "[VERIFIED via ISA-95] Event sourcing aligns with activity model..."

Reference Materials

Canonical Council Session

  • Journal: thoughts/​shared/​journal/​2026-01-25-v3-architecture-council.md
  • Spec: thoughts/​shared/​specs/​2026-01-25-v3-service-architecture.md
  • ADR: assets/​documents/​iiot/​ADR-0012-event-sourcing-boundaries-iiot.md
  • WBS: thoughts/​shared/​plans/​2026-01-26-es-boundaries-wbs.md

Research Reports

  • thoughts/​shared/​reports/​2026-01-26-es-fits-iiot.md
  • thoughts/​shared/​reports/​2026-01-26-es-doesnt-fit-iiot.md

More skills from majiayu000

xiaohongshu logo
majiayu000/claude-arsenal

xiaohongshu

xiaohongshu

286 148
View
agent-task-conductor logo
majiayu000/claude-skill-registry

agent-task-conductor

Conduct multi-agent task orchestration and workflow coordination.

663 1
View
conductor-setup logo
majiayu000/claude-skill-registry

conductor-setup

Initialize project with Conductor artifacts (product definition,

663 1
View
animation-designer logo
majiayu000/claude-skill-registry

animation-designer

Expert in web animations, transitions, and motion design using Framer Motion and CSS

663 1
View
diagramming logo
majiayu000/claude-skill-registry

diagramming

Creates Mermaid and ASCII diagrams for flowcharts, architecture, ERDs, state machines, mindmaps, and more. Use when user mentions diagram, flowchart, mermaid, ASCII diagram, text diagram, terminal diagram, visualize, C4, mindmap, architecture diagram, sequence diagram, ERD, or needs visual docume...

663 1
View
h3-pg logo
majiayu000/claude-skill-registry-data

h3-pg

PostgreSQL bindings for H3 hexagonal grid system. Use when working with H3 cells in Postgres, including spatial indexing, geometry/geography integration, and raster analysis.

23 1
View
conductor-development logo
majiayu000/claude-skill-registry

conductor-development

Context-Driven Development skill for projects using Conductor. Use this skill when you detect a `conductor/` directory in the project, when working on tasks defined in a `plan.md` file, or when the user asks about tracks, specs, or plans. Automatically applies TDD workflow, tracks task completion...

663 1
View
conductor-status logo
majiayu000/claude-skill-registry

conductor-status

Display project status, active tracks, and next actions

663 1
View
dockerization logo
majiayu000/claude-skill-registry

dockerization

Official Stakpak application containerization standard operating procedure, a step-by-step guidline to properly dockerize applications. This is a rule book curated by the Stakpak Team.

663 1
View

Popular AI tools

Kaiber logo
Video

Kaiber

Generate, edit, and beat-sync AI video with leading models in one workspace.

Paid
View
Vimcal logo
Productivity

Vimcal

The world's fastest calendar for remote work

Free
View

Transform Your Design with AI Designer by ImgCreator.ai

Freemium
View
Akool AI logo
Content & writing

Akool AI

Revolutionizing Video Production with AI-Powered Creativity

Paid
View

Extend an image past the frame and let AI fill the new aspect ratio.

Freemium
View
StarByFace logo
Security

StarByFace

Discover your celebrity doppelgänger with StarByFace!

Free
View
C

ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.

Freemium
View
Opus Clip logo
Coding & apps

Opus Clip

Opus.ai: Revolutionize Your Web Experience

Free
View