Orchestrates multi-agent reviews for Architecture Decision Records (ADR) to reach consensus.

Install

mkdir -p .claude/skills/adr-review-diegosouzapw && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16430" && unzip -o skill.zip -d .claude/skills/adr-review-diegosouzapw && rm skill.zip

Installs to .claude/skills/adr-review-diegosouzapw

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Multi-agent debate orchestration for Architecture Decision Records. Automatically triggers on ADR create/edit/delete. Coordinates architect, critic, independent-thinker, security, analyst, and high-level-advisor agents in structured debate rounds until consensus.
263 charsno explicit “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Advanced

Key capabilities

  • Orchestrate multi-agent debate for ADR validation
  • Trigger review automatically on ADR create/edit/delete
  • Coordinate architect, critic, and security agents
  • Identify consensus and conflicts among agents
  • Propose updates for high-priority issues
  • Apply strategic validation checklist to ADRs

How it works

The skill orchestrates six specialized agents through structured debate rounds, identifying consensus and conflicts, and proposing updates until all agents accept or disagree-and-commit.

Inputs & outputs

You give it
ADR file path and change type (create, update, delete)
You get back
Debate log, updated ADR, and recommendations

When to use adr-review

  • Validating architectural changes
  • Reviewing ADR documentation
  • Reaching consensus on design decisions
  • Automated ADR quality checks

About this skill

ADR Review

Multi-agent debate pattern for rigorous ADR validation. Orchestrates 6 specialized agents through structured review rounds until consensus or 10 rounds maximum.

Quick Start

# Manual triggers:
/adr-review .agents/architecture/ADR-005-api-versioning.md
"review this ADR"
"validate ADR-005"

Automatic Detection: A Claude Code hook (Invoke-ADRChangeDetection.ps1) runs at session start and detects ADR changes, prompting you to invoke this skill. The pre-commit hook also detects staged ADR files and displays a reminder.

InputOutputConsensus Required
ADR file pathDebate log + Updated ADR6/6 Accept or D&C

File Triggers

PatternLocationEvents
ADR-*.md.agents/architecture/create, update, delete
ADR-*.mddocs/architecture/create, update, delete

Detection: .claude/skills/adr-review/scripts/Detect-ADRChanges.ps1

When to Use

MANDATORY Triggers (automatic):

  • Architect creates or updates an ADR
  • ANY agent modifies .agents/architecture/ADR-*.md

User-Initiated Triggers (manual):

  • User requests ADR review ("review this ADR", "validate this decision")
  • User requests multi-perspective validation for strategic decisions

Agent Roles

AgentFocusTie-Breaker Role
architectStructure, governance, coherence, ADR complianceStructural questions
criticGaps, risks, alignment, completenessNone
independent-thinkerChallenge assumptions, surface contrarian viewsNone
securityThreat models, security trade-offsNone
analystRoot cause, evidence, feasibilityNone
high-level-advisorPriority, resolve conflicts, break tiesDecision paralysis

Debate Protocol

PhasePurposeDetails
Phase 0Related work researchSearch issues/PRs for context
Phase 1Independent reviewEach agent reviews ADR
Phase 2ConsolidationIdentify consensus and conflicts
Phase 3ResolutionPropose updates for P0/P1 issues
Phase 4Convergence checkAgents vote: Accept/D&C/Block

Consensus: All 6 agents Accept OR Disagree-and-Commit. Max 10 rounds.

See references/debate-protocol.md for full phase details.

Deletion Workflow

PhasePurpose
D1Detection - identify deleted ADR
D2Impact assessment - find dependencies
D3Archival decision - archive accepted ADRs
D4Cleanup - update references

See references/deletion-workflow.md for full workflow.

Issue Resolution

PriorityRequirementGate
P0Must resolveBLOCKING
P1Resolve OR defer with issueBLOCKING
P2DocumentNon-blocking

See references/issue-resolution.md for deferral protocol.

Phase 4: Strategic Review (Principal-Level Validation)

After structural and technical review, apply strategic lenses:

Strategic Validation Checklist

Chesterton's Fence (Change Justification)

  • If removing/changing existing patterns: Original purpose documented
  • Investigation evidence provided (git archaeology, interviews, documentation)
  • Confirmation original problem no longer exists
  • Assessment: [PASS | FAIL | N/A]

Path Dependence (Irreversibility Recognition)

  • Historical constraints identified and documented
  • Reversibility assessment complete (rollback capability, vendor lock-in)
  • Migration/exit strategy defined if adding dependencies
  • Irreversible decisions explicitly flagged and justified
  • Assessment: [PASS | FAIL | N/A]

Core vs Context (Investment Prioritization)

  • Capability classified as Core (differentiating) or Context (commodity)
  • If building Context: Justification for not buying/outsourcing
  • If Core: Competitive differentiation explained
  • Assessment: [PASS | FAIL | N/A]

Second-System Effect (Over-Engineering Detection)

  • If replacing existing system: Scope boundaries explicit
  • Feature list justified (not "everything we didn't do last time")
  • Simplicity preservation strategy documented
  • Assessment: [PASS | FAIL | N/A]

Strategic Review Verdict

Overall Strategic Assessment: [APPROVED | CONCERNS | REJECTED]

Blocking Issues:

  • [Strategic issue 1 with required mitigation]
  • [Strategic issue 2 with required mitigation]

Recommendations:

  • [Strategic improvement 1]
  • [Strategic improvement 2]

Scripts

ScriptPurpose
Detect-ADRChanges.ps1Detect ADR file changes for auto-trigger
# Basic detection
& .claude/skills/adr-review/scripts/Detect-ADRChanges.ps1

# Compare to specific commit
& .claude/skills/adr-review/scripts/Detect-ADRChanges.ps1 -SinceCommit "abc123"

Verification Checklist

After skill invocation:

  • Debate log exists at .agents/critique/ADR-NNN-debate-log.md
  • ADR status updated (proposed/accepted/needs-revision)
  • All P0 issues addressed or documented
  • Dissent captured for Disagree-and-Commit positions
  • Recommendations provided to orchestrator

Anti-Patterns

AvoidWhyInstead
Single-agent ADR reviewMisses domain expertiseUse full 6-agent debate
Skipping Phase 0Duplicates existing workAlways research first
Ignoring D&C dissentLoses important contextDocument all reservations
Manual ADR monitoringError-proneUse Detect-ADRChanges.ps1
Deleting accepted ADRs without archiveLoses knowledgeAlways archive accepted ADRs

References

DocumentContent
debate-protocol.mdFull Phases 0-4 workflow
deletion-workflow.mdPhases D1-D4 workflow
issue-resolution.mdP0/P1/P2 handling and deferral
artifacts.mdOutput formats and templates
agent-prompts.mdDetailed agent prompt templates

When not to use it

  • When only a single agent review is desired
  • When skipping related work research
  • When ignoring dissent in Disagree-and-Commit positions

Limitations

  • Debate rounds are limited to a maximum of 10.
  • It requires all 6 agents to Accept or Disagree-and-Commit for consensus.
  • It does not allow single-agent ADR review.

How it compares

This workflow uses a multi-agent debate pattern for rigorous ADR validation, providing diverse perspectives automatically, unlike a single-person review.

Compared to similar skills

adr-review side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
adr-review (this skill)05moNo flagsAdvanced
confidence-check134moReviewBeginner
specification-architect139moReviewAdvanced
drift-analysis25moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

More by diegosouzapw

View all by diegosouzapw

helm-chart-scaffolding-v2

diegosouzapw

Helm Chart Scaffolding workflow skill. Use this skill when the user needs Comprehensive guidance for creating, organizing, and managing Helm charts for packaging and deploying Kubernetes applications and the operator should preserve the upstream workflow, copied support files, and provenance before

00

cc-skill-coding-standards-v2

diegosouzapw

Coding Standards & Best Practices workflow skill. Use this skill when the user needs Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development and the operator should preserve the upstream workflow, copied support files, and provenance before

00

worktree-setup

diegosouzapw

Automatically invoked after `git worktree add` to create data/shared symlink and data/local directory. Required before starting work in any new worktree.

00

parsehub-automation

diegosouzapw

Automate Parsehub tasks via Rube MCP (Composio). Always search tools first for current schemas.

00

signalwire-agents-sdk

diegosouzapw

Expert assistance for building SignalWire AI Agents in Python. Automatically activates when working with AgentBase, SWAIG functions, skills, SWML, voice configuration, DataMap, or any signalwire_agents code. Provides patterns, best practices, and complete working examples.

00

agent-sales-engineer

diegosouzapw

Expert sales engineer specializing in technical pre-sales, solution architecture, and proof of concepts. Masters technical demonstrations, competitive positioning, and translating complex technology into business value for prospects and customers.

00

You might also like

confidence-check

SuperClaude-Org

Pre-implementation confidence assessment (≥90% required). Use before starting any implementation to verify readiness with duplicate check, architecture compliance, official docs verification, OSS references, and root cause identification.

13114

specification-architect

adrianpuiu

A rigorous, traceability-first system that generates five interconnected architectural documents (blueprint.md, requirements.md, design.md, tasks.md, and validation.md) with complete requirements-to-implementation traceability. Use this skill when users need to architect systems, create technical specifications, or develop structured project documentation with guaranteed traceability.

1388

drift-analysis

avifenesh

This skill should be used when the user asks about "plan drift", "reality check", "comparing docs to code", "project state analysis", "roadmap alignment", "implementation gaps", or needs guidance on identifying discrepancies between documented plans and actual implementation state.

213

flow-next-plan-review

gmickel

Carmack-level plan review via RepoPrompt or Codex. Use when reviewing Flow epic specs or design docs. Triggers on /flow-next:plan-review.

11

rfc-check

meta-pytorch

Determine if proposed changes require an RFC. Use when planning significant changes, before starting major work, or when asked whether an RFC is needed.

11

feature-planning

mhattingpete

Break down feature requests into detailed, implementable plans with clear tasks. Use when user requests a new feature, enhancement, or complex change.

10

Search skills

Search the agent skills registry