Create an Architecture Decision Record in docs/decisions/ and optionally sync to Confluence for business projects. Use when making significant technical decisions. Triggers on: architecture decision, ADR, technical decision.
Scanned 9/12/2026
Install to Claude Code
npx -y skills add igorilic/agentic-orchestration --skill adr --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Adr?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/igorilic-adr)More formats (shields.io, HTML) on the badges page.
---
name: adr
description: >
Create an Architecture Decision Record in docs/decisions/ and optionally
sync to Confluence for business projects. Use when making significant
technical decisions. Triggers on: architecture decision, ADR, technical decision.
---
## Architecture Decision Record
### Step 1: Determine Next ADR Number
```bash
ls docs/decisions/ADR-*.md 2>/dev/null | sort -t- -k2 -n | tail -1
```
Increment by 1. Start at 001 if none exist.
### Step 2: Create ADR
Create `docs/decisions/ADR-<NNN>-<kebab-case-title>.md` with sections:
- **Status**: Proposed / Accepted / Deprecated / Superseded
- **Date**: YYYY-MM-DD
- **Context**: The challenge or decision point
- **Decision**: What was decided and why
- **Consequences**: Positive, Negative, Risks
- **Alternatives Considered**: Each with reason for rejection
### Step 3: Update Architecture Docs
Add reference in `docs/context/ARCHITECTURE.md`.
### Step 4: Sync to Confluence (Business Only)
If Confluence MCP is available, create a child page under "Architecture Decisions".
Note: canonical version is always the repo file.
### Step 5: Commit
`docs(adr): ADR-<NNN> <title>`
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.