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
  • Authors
  • 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.

ProTermsPrivacyRefunds
Back to skills

Adr

ASecurity

Create/list Architecture Decision Records. `--axial` elicits the Axis of Decomposition ADR.

9 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentsexpressgit

Security Analysis

A100/100

Scanned 9/23/2026

Install to Claude Code

$npx -y skills add Roxabi/roxabi-plugins --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/roxabi-adr/badge)](https://www.skillsdirectory.com/skills/roxabi-adr)

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

Download with Pro
Files
SKILL.md
---
name: R-adr
argument-hint: '["Title of decision" | --list | --axial]'
description: Create/list Architecture Decision Records. `--axial` elicits the Axis of Decomposition ADR.
version: 0.5.0
allowed-tools: Write, Read, Glob, Grep, ToolSearch
---

# ADR (Architecture Decision Record)

Let:
  D := `docs/architecture/adr/`
  NNN := zero-padded 3-digit sequence number
  AQ := ask user
  ADR_GLOB := `{NNN}-*.md` + legacy `{NNN}-*.mdx` (read only)

Create and manage ADRs — document **why** technical choices were made.

**Write format:** always Markdown (`.md`). Legacy `.mdx` ADRs are still readable for list/scan; never write new `.mdx`.

```
/R-adr "Title"   → Create mode
/R-adr --list    → List mode
/R-adr --axial   → Axial mode (Axis of Decomposition interview + ADR)
```

`--axial` present → **Axial Mode** (below). Do not also run Create Mode.

## Axial Mode

Follow [references/axial-interview.md](${CLAUDE_SKILL_DIR}/references/axial-interview.md) end-to-end. That file is the procedure (interview, singleton, write, supersede). Exit `created` | `kept` | `superseded` | `cancelled`.

Called from `/R-dev-init` Phase 3a when no unique `axial: true` ADR exists (or singleton is broken). Standalone to re-elicit / supersede. ¬spawn a dedicated agent — this skill **is** the writer.

## Create Mode

**1. Next NNN:** Scan D for `{NNN}-*.md` and legacy `{NNN}-*.mdx` → highest + 1. ¬D ∨ ¬files → create D, start at `001`.

**2. Resolve title:** ∃ title in `$ARGUMENTS` → use. ¬title → AQ.

**3. Interview:** AQ (1–2 calls, ≤3 questions). Skip if clear from title:

| Topic | Ask |
|-------|-----|
| Context | What problem prompted this decision? |
| Options | What alternatives were considered? (≥2, key pros/cons each) |
| Decision | Which was chosen and why? |
| Consequences | Positive, negative, neutral trade-offs? |

**4. Write ADR:** `D/{NNN}-{slug}.md` (slug = kebab-case title).

```md
---
title: "ADR-{NNN}: {Title}"
description: {one-line summary}
---

## Status

{Proposed | Accepted | Deprecated | Superseded by ADR-XXX}

## Context

{What is the issue? Why does this decision need to be made?}

## Options Considered

### Option A: {Name}
- **Pros:** {advantages}
- **Cons:** {disadvantages}

### Option B: {Name}
- **Pros:** {advantages}
- **Cons:** {disadvantages}

## Decision

{What was decided and why.}

## Consequences

### Positive
- {benefit}

### Negative
- {trade-off}

### Neutral
- {side effect}
```

Default status: **Accepted** unless stated otherwise. Min 2 options.

**5. Confirm:** Inform: file path, NNN + title, status.

## List Mode

Scan D for `.md` and legacy `.mdx` files. ¬∃ → inform + suggest `/R-adr "Title"`.

∃ → ∀ file: read frontmatter for title, status, date. Sort by NNN ascending.

```
Architecture Decision Records
══════════════════════════════

  #    │ Title                    │ Status    │ Date
  001  │ Fastify over Express     │ Accepted  │ 2025-03-15
  002  │ Bun as runtime           │ Accepted  │ 2025-04-01
  003  │ REST over GraphQL        │ Deprecated│ 2025-04-10
```

## Edge Cases

| Scenario | Behavior |
|----------|----------|
| First ADR ever | Create D from scratch |
| ¬title provided | AQ before proceeding |
| Superseding an ADR | Update old status to `Superseded by ADR-{NNN}`; reference old in new context |
| Legacy `.mdx` present | Include in NNN scan + list; new ADRs still write `.md` |
| Same NNN as both `.md` and `.mdx` | Prefer `.md` for display; do not write over either |
| `--axial` | Axial Mode only — see `references/axial-interview.md` |

$ARGUMENTS

Attribution

RoxabiRoxabi
View sourceMore from Roxabi →
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

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →