.claude/skills/adr/SKILL.md
--- context: fork --- # /adr Create a new Architecture Decision Record (ADR) following the official YourOrg ADR process. ## Usage ``` /adr <title> /adr <title> for <project> ``` ## Examples ``` /adr API Gateway Selection /adr Kafka vs EventBridge for Project - MyDataIntegration /adr Standalone Laptop for Offline Database Build ``` ## Instructions ### 1. Parse Command and Initial Setup Parse the command for: - **title**: The ADR name (required) - **project**: Related project (optional)
npx skillsauth add DavidROliverBA/ArchitectKB .claude/skills/adrInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Create a new Architecture Decision Record (ADR) following the official YourOrg ADR process.
/adr <title>
/adr <title> for <project>
/adr API Gateway Selection
/adr Kafka vs EventBridge for Project - MyDataIntegration
/adr Standalone Laptop for Offline Database Build
Parse the command for:
IMPORTANT: Before creating a new ADR, search for existing organisational ADRs that may constrain or inform this decision.
Search the vault for relevant ADRs:
+Sync/Org-ADRs/ for ADRs with authority: organizationalstatus: acceptedDisplay found ADRs to the user:
📋 Relevant Organisational ADRs Found:
**Must Follow** (authority: organizational):
- [[ADR - API Gateway Selection]] - Mandates Kong for API management
- [[ADR - Cloud Provider Selection]] - Requires AWS for new services
**Consider** (authority: team, related domain):
- [[ADR - Kafka Event Patterns]] - Event-driven patterns for integration
- [[ADR - Data Product Standards]] - Data exchange formats
Would you like to reference any of these in your new ADR's `dependsOn` field?
Store selected references for later inclusion in frontmatter.
CRITICAL STEP: Before creating an ADR, check if a relevant guardrail already exists.
Ask the user:
"Before creating this ADR, have you checked if there's an existing guardrail that covers this decision? If a guardrail exists, you should follow it instead of creating an ADR."
If user confirms no guardrail exists, proceed to step 4.
Ask the user to select the ADR type (explain each):
Question: "What type of ADR is this?"
Options:
Technology_ADR - New technology/tool or significant change to existing technology
Architecture_ADR - New guardrail, pattern, or standard
Local_ADR - Following existing guardrails
Store the selected type in adrType frontmatter field.
Based on the ADR type and subject area, identify required approvers using [[Page - YourOrg ADR Approvers and SME (Official)]].
Core Assessors (Always Required):
Ask the user: "What subject areas does this ADR cover?"
Common Subject Areas (select all that apply):
Build the complete approvers list from Core + Subject-Specific SMEs.
Ask the user for key information using the official YourOrg ADR template structure:
Generate filename: ADR - {{title}}.md
Create the ADR in vault root using the structure from +Templates/ADR.md:
Frontmatter:
---
type: Adr
title: {{title}}
description: {{one-line summary}}
status: draft
adrType: {{Technology_ADR | Architecture_ADR | Local_ADR}}
tags: [ADR, architecture, {{additional relevant tags}}]
created: {{DATE}}
modified: {{DATE}}
deciders: [Engineering Architecture Team, {{project team if applicable}}]
approvers:
# Core Assessors (Required)
- Head of Architecture or Engineering
- Principal Solution Architect
- Cyber Assurance (Security Lead or delegate)
# Subject-Specific SMEs (from user selections)
{{list of SME approvers based on subject areas}}
# Stakeholders
{{project stakeholders if applicable}}
project: {{project_link or null}}
jiraTicket: null # To be added when JIRA ticket created
# Source/Provenance
source: local # local | confluence
sourcePageId: null # Confluence page ID (once published)
sourceSpace: null # Confluence space key
sourceUrl: null # Link to authoritative version
sourceVersion: null # Version number
# Publication
isPublished: false # Updated when published to Confluence
publishedDate: null # YYYY-MM-DD
publishedUrl: null # Confluence URL
# Authority Level
authority: draft # draft → local → team → organizational
# Relationships
relatedTo: []
supersedes: []
dependsOn: {{selected_dependencies_from_discovery_step}}
# Quality Indicators
confidence: medium
freshness: current
verified: false
reviewed: {{DATE}}
# Context
summary: {{one-line summary}}
assumptions: []
stakeholders: {{list from approvers}}
---
Content: Use official YourOrg ADR template structure with all sections filled in from user responses.
Include at the top:
> **Based on Official YourOrg ADR Template**: [[Page - YourOrg ADR Template (Official)]]
>
> **ADR Process**: [[Page - YourOrg ADR Process (Official)]]
>
> **Required Approvers**: [[Page - YourOrg ADR Approvers and SME (Official)]]
After creating the ADR, display:
✅ ADR created: ADR - {{title}}.md
📋 Next Steps (Official YourOrg ADR Process):
1. ⏳ REVIEW ADR CONTENT
- Review all sections for completeness
- Ensure alternatives are well-documented
- Verify approvers list is correct
2. ⏳ CREATE JIRA TICKET (CRITICAL - ADR not complete without this)
- Project: {{user's project or ARCH}}
- Issue Type: ADR
- Label: "{{adrType}}"
- Summary: "ADR - {{title}}"
- Link this ADR document to JIRA ticket
3. ⏳ ADD APPROVERS IN JIRA
Use '@' function in Jira to add:
{{list all approvers from frontmatter}}
4. ⏳ CREATE/LINK CONFLUENCE PAGE
- Create Confluence page with ADR content
- Link Confluence page to JIRA ticket
5. ⏳ UPDATE ADR STATUS
- After JIRA ticket created, update status: draft → proposed
- Add JIRA ticket reference to frontmatter
6. ⏳ STAKEHOLDER REVIEW
- Approvers review in Jira
- Discussion via Jira comments
- All approvers must agree
7. ⏳ ADR ACCEPTANCE
- All approvals confirmed in Jira
- Update status: proposed → accepted
8. ⏳ POST-APPROVAL
- Close JIRA ticket
- Tidy Confluence page
- Add appropriate labels
9. ⏳ PUBLISH TO CONFLUENCE (Final Step)
- Create Confluence page with ADR content
- Update vault ADR frontmatter:
- isPublished: true
- publishedDate: {{today}}
- publishedUrl: {{confluence URL}}
- authority: team (or organizational if it becomes a guardrail)
- status: accepted
🔄 Authority Progression:
- draft → ADR being created (local work)
- local → Personal decision, not yet shared
- team → Approved by team, in Confluence
- organizational → Company-wide standard/guardrail
📚 References:
- [[Page - YourOrg ADR Process (Official)]] - Full process documentation
- [[Page - YourOrg ADR Approvers and SME (Official)]] - Approvers reference
- [[Page - YourOrg ADR Template (Official)]] - Template structure
⚠️ REMEMBER: ADRs are not complete until JIRA ticket is raised!
Ask the user: "Would you like me to create a task to track this ADR through the approval process?"
If yes, create a task: Task - Create ADR - {{title}}.md with:
All guidance based on:
tools
--- context: fork --- # /youtube Save a YouTube video as both a Weblink (quick reference) and a detailed Page (full analysis). ## Usage ``` /youtube <url> /youtube <url> <optional title override> ``` ## Examples ``` /youtube https://www.youtube.com/watch?v=0TpON5T-Sw4 /youtube https://youtu.be/abc123 AWS re:Invent Keynote ``` ## Prerequisites This skill uses the MCP Docker YouTube tools: - `mcp__MCP_DOCKER__get_video_info` - Video metadata - `mcp__MCP_DOCKER__get_transcript` - Full trans
data-ai
Create and manage git worktrees for parallel agent sessions
testing
--- context: fork --- # /wipe Generate a context handoff summary, clear the session, and resume in a fresh conversation. Detects environment and provides automated (tmux) or manual workflow. ## Usage ``` /wipe /wipe quick # Minimal handoff, just essentials /wipe detailed # Comprehensive handoff with full context ``` ## Instructions When the user invokes `/wipe`: ### Phase 1: Detect Environment First, check the terminal environment: ```bash echo "Environment Detection:"
data-ai
--- context: fork --- # /weekly-summary Generate comprehensive weekly summary from daily notes, meetings, tasks, and project updates using parallel sub-agents. ## Usage ``` /weekly-summary /weekly-summary --last-week /weekly-summary --from 2026-01-01 --to 2026-01-07 /weekly-summary --output page # Create Page note instead of just outputting ``` ## Instructions This skill uses **5 parallel sub-agents** to gather data concurrently from different vault areas, then synthesizes a comprehensi