Architecture Decision Record

VerifiedSafe

Scaffold an architecture decision record in the repository using governed ID conventions. Ideal for documenting decisions when prompted by user or /adr command.

Sby Skills Guide Bot
DocumentationIntermediate
7/24/2026
Claude CodeCursorCodex
#adr#architecture-decisions#documentation#governance#repo-conventions

Recommended for

Automated summary

Scaffolds an architecture decision record in architecture/decisions/ using the repository's governed ID conventions and updates the index table.

Strengths

  • Clearly separates the local ADR-KOA-DEV-NNN range from the governed ADR-KOA-NNN range owned by the Koʻa baseline amendment process
  • Produces a consistent template with status, date, deciders, Context, Decision and Consequences sections
  • Always appends the new row to the index table in architecture/decisions/README.md
  • Reminds the author about the cultural-review caveat for naming decisions and the ADR-KOA-DEV-001 reference when promoting the placeholder workflow

Limitations

  • Assumes architecture/decisions/README.md already exists and holds the conventions to read
  • Does not handle superseding or amending existing ADRs, and status is limited to proposed or accepted
  • Does not validate the substance of the decision: content and numbering remain the author's responsibility
When to use it

Use it whenever a repository-local architecture decision about tooling, CI, layout or the harness needs to be formally recorded.

When not to use it

Avoid it for amending the governed Koʻa baseline, which must not be minted through the ADR-KOA-DEV range.

Security analysis

Safe
Quality score82/100

The skill only instructs reading repository documentation and creating markdown files for architecture decision records. It does not execute shell commands, access networks, handle secrets, or perform destructive actions. No obfuscation or exfiltration risk is present.

No concerns found

How this analysis is made

Examples

Record a tooling decision
We decided to standardize on pnpm workspaces for all packages. Write an ADR for it in architecture/decisions/ and add it to the index.
Slash command
/adr — we need to record why the test harness lives in its own package.
Placeholder workflow decision
Document the decision to keep the placeholder workflow as-is for now, and explicitly reference ADR-KOA-DEV-001 in the record.

name: adr description: Scaffold an architecture decision record in architecture/decisions/ using the repo's governed ID conventions. Use when a decision needs recording or the user says /adr.

/adr — record an architecture decision

  1. Read architecture/decisions/README.md for conventions.
  2. ID selection (critical): use ADR-KOA-DEV-NNN (next sequential number) for decisions local to this repository — harness, CI, tooling, repo layout. The governed ADR-KOA-NNN range belongs to the Koʻa baseline amendment process and must NOT be minted here.
  3. Create architecture/decisions/ADR-KOA-DEV-NNN-<slug>.md:
# ADR-KOA-DEV-NNN — <Title>

**Status:** proposed | accepted
**Date:** <YYYY-MM-DD>
**Deciders:** <who>

## Context
Why this decision is needed; constraints from the governance baseline
(architecture/governance/) that bear on it.

## Decision
The decision, stated actively. Numbered points if there are several.

## Consequences
What becomes easier/harder; follow-ups; what would trigger revisiting.
  1. Add a row to the index table in architecture/decisions/README.md.
  2. If the decision touches naming, include the cultural-review caveat; if it promotes the placeholder workflow toward a real capability, say so explicitly and reference ADR-KOA-DEV-001.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/architecture-decision-record-mryiqil1/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/architecture-decision-record-mryiqil1' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/architecture-decision-record-mryiqil1/download' --output '.skill-downloads/architecture-decision-record-mryiqil1/SKILL.md.part' && mv '.skill-downloads/architecture-decision-record-mryiqil1/SKILL.md.part' '.skill-downloads/architecture-decision-record-mryiqil1/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/architecture-decision-record-mryiqil1/SKILL.md' && test -s '.skill-downloads/architecture-decision-record-mryiqil1/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/adr' && cp -R '.skill-downloads/architecture-decision-record-mryiqil1' '.claude/skills/adr'

Cursor
test -f '.skill-downloads/architecture-decision-record-mryiqil1/SKILL.md' && test -s '.skill-downloads/architecture-decision-record-mryiqil1/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/adr' && cp -R '.skill-downloads/architecture-decision-record-mryiqil1' '.cursor/skills/adr'

Codex
test -f '.skill-downloads/architecture-decision-record-mryiqil1/SKILL.md' && test -s '.skill-downloads/architecture-decision-record-mryiqil1/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/adr' && cp -R '.skill-downloads/architecture-decision-record-mryiqil1' '.agents/skills/adr'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/architecture-decision-record-mryiqil1'

openskills read 'architecture-decision-record-mryiqil1'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/architecture-decision-record-mryiqil1/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills