/decision-record

Capture an architectural decision so the next session (or engineer) knows WHY. Use after any non-obvious technical choice.

BOOST

archive228@archive228

GitHub

From plugin

loopkit

75553 skills1 agent4 commands2 MCP

Install

$ npx -y skills add Archive228/loopkit --skill decision-record --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/decision-record

Context preview

The summary Claude sees to decide when to auto-load this skill.

Capture an architectural decision so the next session (or engineer) knows WHY. Use after any non-obvious technical choice.

SKILL.md

decision-record.SKILL.md

name: decision-record
description: Capture an architectural decision so the next session (or engineer) knows WHY. Use after any non-obvious technical choice.
when_to_use: picked a library/pattern/schema, a tradeoff was made, a hard-to-reverse choice

Decision Record (ADR)

Write a short file `docs/decisions/NNN-<slug>.md`:

**Context** — what forced a decision. The constraints.
**Options** — the 2-3 real candidates, one line each.
**Decision** — what you picked, dated.
**Why** — the tradeoff. What you gave up. "We picked Postgres over Mongo because we need real joins; we accept heavier ops."
**Consequences** — what this now makes easy and hard.

Hard-to-reverse choices (schema, auth, data store) MUST get one. Future-you will ask "why on earth did we do this" — answer it now.

Read it on GitHub ↗

Ships withloopkit

33 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI).

Get the whole plugin

Stats

Node Bash SQL Git GitHub

+4 tags

Markdown Anthropic Gemini MCP

755

Stars

124