Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Adr

ASecurity

Create a numbered ADR in docs/adr/ for a significant architectural choice

8 stars
0 votes
0 copies
0 views
Added 9/20/2026
documentationdocumentation

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add tstapler/dotfiles --skill adr --agent claude-code

Installs 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.

Security grade badge for Adr
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tstapler-adr/badge)](https://www.skillsdirectory.com/skills/tstapler-adr)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
description: Create a numbered ADR in docs/adr/ for a significant architectural choice
---

# Create ADR: Architecture Decision Record

Creates `docs/adr/ADR-NNN-<title>.md`. Scope: repo-wide, cross-cutting decisions about the dotfiles repo itself (tooling, infra, conventions) that outlive any single project_plans/ entry. For a decision internal to one SDD project's own implementation, use `/sdd:adr` instead, which writes to that project's `project_plans/<project>/decisions/`.

Use when making a significant architectural choice during Phase 3 (Planning) or whenever a decision warrants documentation:
- Choosing between two non-trivial approaches
- Adopting or rejecting a technology/library
- Establishing a pattern that other work will follow
- Deciding something that would be hard to reverse

**Not every decision needs an ADR.** Small, obvious, or easily reversible choices don't.

## Step 1: Determine project and ADR number

If `{{args}}` is provided, parse `project` and `title` from it.
Otherwise, infer project from context (open files, current task, recent messages) or ask.

Scan `docs/adr/` to find existing ADRs and determine the next sequential number (e.g., if ADR-001 and ADR-002 exist, next is ADR-003). If no docs/adr/ directory exists, start at 001.

## Step 2: Ask clarifying questions (if not already clear)

Use `AskUserQuestion` to get what's needed:

- "What decision was made?" (the choice itself — one clear sentence)
- "What were the alternatives considered?" (at least one alternative, even if obvious)
- "What are the key consequences or trade-offs?"

If the context makes these clear, skip the questions and draft from context.

## Step 3: Write the ADR file

Create `docs/adr/ADR-NNN-<kebab-title>.md`:

```markdown
# ADR-NNN: <Title>

**Status**: Proposed
**Date**: <YYYY-MM-DD>
**Project**: <project>

## Context

<What forces, constraints, or circumstances led to this decision? What problem needed solving? What was the trigger?>

## Decision

<What was decided? Be specific and unambiguous. One clear statement.>

## Alternatives Considered

- **<Alternative A>**: <Why it was rejected or not chosen>
- **<Alternative B>**: <Why it was rejected or not chosen>

## Rationale

<Why this option over the alternatives? What made it the right call given the constraints?>

## Consequences

**Positive:**
- <Trade-off or benefit 1>

**Negative / Risks:**
- <Trade-off or risk 1>

**Follow-up work:**
- <Any work this decision creates or requires>

## Related

- Requirements: `project_plans/<project>/requirements.md`
- Supersedes: (none)
- Related ADRs: (none)
```

## Step 4: Confirm output

Tell the user:
- File created: `docs/adr/ADR-NNN-<title>.md`
- Status is `Proposed` — change to `Accepted` when the team/stakeholders agree
- Reference this ADR from `plan.md` under the architectural decisions section

## ADR Status Lifecycle

| Status | Meaning |
|--------|---------|
| `Proposed` | Decision drafted, not yet reviewed |
| `Accepted` | Decision approved and in effect |
| `Deprecated` | Decision was valid but no longer applies |
| `Superseded` | Replaced by a newer ADR (link to it) |

## Rules

- Number sequentially per project — ADR-001, ADR-002, etc.
- One decision per ADR — if you're documenting two decisions, create two ADRs
- Write in past tense ("We decided to...") once Accepted
- Never delete ADRs — deprecate or supersede them instead

Attribution

tstaplertstapler
View sourceMore from tstapler →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Context Fundamentals

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.

179001 votes

release-notes

Draft release notes and changelog entries from git history or merged PRs between two refs (tags/SHAs/branches), including breaking changes, migrations, and upgrade steps. Use when the user asks for release notes, changelog updates, or a GitHub Release draft.

1301 votes

docs-style-guide

Documentation style guide enforcer by @planetabhi. Applies and reviews the writing style guide when authoring or editing product documentation and tutorials. Use to check prose for voice, tense, word choice, inclusive language, formatting, code block, UI, Markdown, and number/date conventions.

11 votes

Caveman Help

Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".

1023330 votes

How It Works

Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".

929660 votes
View all in documentation →