From spec-driven
Writes an architecture decision record under docs/adr with context, options, decision, and consequences, four-digit numbering, and the immutability plus supersede rules for accepted ADRs.
How this skill is triggered — by the user, by Claude, or both
Slash command
/spec-driven:writing-adrThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
An ADR records *why* a decision was made: its context, the options considered,
An ADR records why a decision was made: its context, the options considered,
the choice, and the consequences. Once status: accepted its body is immutable.
authoring-living-spec.max(existing) + 1, zero-padded to four digits.NNNN-<kebab-title>.md.${CLAUDE_PLUGIN_ROOT}/references/spec-and-adr-frontmatter.md; set affects_specs to the <domain>/<name> specs this shapes.STOP: do not edit an already-accepted ADR's body — write a new one and supersede.
supersedes: <old>.status: superseded + superseded_by: <new> — this is the only permitted edit to an accepted ADR.${CLAUDE_PLUGIN_ROOT}/references/spec-and-adr-frontmatter.md${CLAUDE_PLUGIN_ROOT}/references/change-lifecycle.mddocs/specs/meta/spec-governance.mdGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub baranovxyz/agent-context-kit --plugin spec-driven