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 Template

ASecurity

Architecture Decision Record format, naming conventions, and when to create ADRs. Load when making or documenting architectural decisions.

16 stars
0 votes
0 copies
0 views
Added 9/20/2026
documentationgogitapidocumentation

Works with

api

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add woditschka/agentic-coding-reference --skill adr-template --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Adr Template?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Adr Template
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/woditschka-adr-template-9bf4a359/badge)](https://www.skillsdirectory.com/skills/woditschka-adr-template-9bf4a359)

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

Download Zip
Files
SKILL.md
---
name: adr-template
description: >-
  Architecture Decision Record format, naming conventions, and
  when to create ADRs. Load when making or documenting architectural decisions.
compatibility:
  - claude-code
  - github-copilot
  - opencode
reads:
  - docs/adr/
metadata:
  version: "1.0"
  author: team
---

## When to Create an ADR

Create an ADR when a decision constrains future slices or reverses a recorded one:

- A pattern, library, or approach chosen over a reasonable alternative that later work must not silently re-open.
- A rejected alternative a later reader would otherwise re-litigate.
- A reversal or narrowing of a recorded decision (supersede or amend the old ADR).

Do not create an ADR for a choice with no trade-off, or for one a single slice contains. That rationale is one clause on the current-state line in `docs/system-design.md`. ADRs are the project's decision log for people; agents execute from the current-state docs and read an ADR by back-link.

## What an ADR Owns

An ADR owns:

- Context for each architectural decision
- Options considered with trade-offs
- Decision outcome and rationale
- Consequences (positive and negative)
- Implementation mapping (which requirements, which files)

It does not own:

- Detailed implementation (lives in `docs/system-design.md`)
- Requirement specifications (live in `docs/prd.md`)

## Template, Guidelines, and Index

See `docs/adr/README.md` for the ADR template, naming convention (`YYYY-MM-DD-title-in-kebab-case.md`), guidelines, and index table. The filename pattern and the README's presence are harness-project API requirements; the `doctor` skill enforces them deterministically. The decision log itself is project-owned: harness upgrades never write here.

ADR prose follows the writing standards in the [`document-writing`](../document-writing/documentation-standards.md) skill — the same discipline as every other project document.

## Non-Goal ADRs

A non-goal ADR captures a *product* decision not to build something — distinct from an architectural ADR that records a *how* decision. Two conventions apply:

1. **Filename:** `YYYY-MM-DD-non-goal-<slug>.md` (the `non-goal-` infix is load-bearing — it scopes write access).
2. **Implementation section:** use `**Non-goal:** NG-X` instead of `**Requirements:** REQ-XX-NNN`.

**Ownership.** Non-goal ADRs may be authored by `product-requirements-expert` (the agent's write scope explicitly includes `docs/adr/*-non-goal-*.md`). All other ADRs are owned by `system-design-expert`.

Attribution

woditschkawoditschka
View sourceMore from woditschka →
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?".

942310 votes
View all in documentation →