Architecture Decision Records (ADR) templates, sequential numbering, decision documentation patterns, and decision history management. Use when creating ADRs, documenting architectural decisions, tracking decision rationale, managing decision lifecycle, superseding decisions, searching decision history, or when user mentions ADR, architecture decision, decision record, decision tracking, or decision documentation.
/plugin marketplace add vanman2024/dev-lifecycle-marketplace/plugin install planning@dev-lifecycle-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
examples/example-adr-architecture.mdexamples/example-adr-index.mdexamples/example-adr-security.mdexamples/example-adr-superseded.mdexamples/example-adr-technology.mdscripts/create-adr.shscripts/list-adrs.shscripts/search-adrs.shscripts/supersede-adr.shscripts/update-adr-index.shtemplates/adr-frontmatter.yamltemplates/adr-index-template.mdtemplates/adr-template.mdtemplates/consequences-template.mdtemplates/decision-matrix.mdCRITICAL: The description field above controls when Claude auto-loads this skill.
Provides comprehensive Architecture Decision Record (ADR) management following Michael Nygard's ADR format. Includes automatic sequential numbering, decision lifecycle tracking, superseding workflows, and decision search capabilities.
scripts/create-adr.sh <title> [docs-path] to create a new ADR with automatic numberingNNNN-title-in-kebab-case.mdscripts/list-adrs.sh [docs-path] [--status=accepted|proposed|deprecated|superseded] to view all ADRsscripts/search-adrs.sh <search-term> [docs-path] to search ADR contentscripts/update-adr-index.sh [docs-path] to regenerate ADR indexdocs/adr/index.md or specified pathscripts/supersede-adr.sh <old-adr-number> <new-title> [docs-path] to supersede an ADRSee examples/ directory for detailed usage examples:
example-adr-technology.md - Technology choice ADR (database selection)example-adr-architecture.md - Architectural decision (microservices vs monolith)example-adr-security.md - Security decision (authentication strategy)example-adr-superseded.md - Superseded ADR with replacement linksexample-adr-index.md - Complete ADR index with multiple entries---
number: 0001
title: Use PostgreSQL for Primary Database
date: 2025-10-28
status: accepted
deciders: [Tech Lead, Backend Team]
consulted: [DevOps, Security Team]
informed: [Frontend Team, Product]
---
NNNN-title-in-kebab-case.md0001-use-postgresql.md, 0042-adopt-microservices.mdsupersede-adr.sh 0005 "New Decision Title"Recommended directory structure:
docs/
adr/
index.md # Master index of all ADRs
0001-first-decision.md
0002-second-decision.md
0003-third-decision.md
templates/
adr-template.md # Template for new ADRs
When evaluating multiple options:
templates/decision-matrix.md to structure comparisonThe search script supports:
"auth.*strategy"This skill is used by:
planning:adr-create command - Create new ADRs interactivelyplanning:adr-list command - List and filter ADRsplanning:adr-supersede command - Supersede existing ADRsAll scripts output in consistent formats:
Purpose: Comprehensive Architecture Decision Record management and documentation Used by: All planning agents and commands requiring decision tracking
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.