adr-records
Architecture Decision Records (adr.github.io)
Maintain a decision log of architecturally significant choices using formats from adr.github.io.
When to use
- User asks for an ADR, architecture decision record, or decision log
- Before or during implementation — design fork, trade-off, or “which approach?” (decision checkpoints)
- User asks for key design decisions when doing work (checkpoint brief, not silent defaults)
- Recording a significant design choice (stack, integration, security, data model, deployment)
- Updating ADR status (
accepted,deprecated,superseded) - Aligning an existing repo with MADR / Nygard conventions
Decision checkpoints (layer 0)
Layer 0 = checkpoint (brief or proposed ADR). Layer 1 = accepted ADR after agreement.
When triggers fire, stop and ask—do not implement the most convenient option.
More from arenukvern/skill_steward
faq-driven-docs
Creates and maintains DESIGN_FAQ (why) and DX_FAQ (how) documentation in FAQ-driven development style. Use when writing docs, rules, prompts, updating FAQs after code changes, or bootstrapping faq_usage rules and Cursor commands.
1create-skill
Scaffold a new Agent Skill in this marketplace repo with valid SKILL.md, directory layout, and registry entries. Use when adding a skill, creating SKILL.md, or contributing to skill_steward.
1skill-source-citations
Requires durable citations when authoring or researching Agent Skills—maintain references/sources.md per skill, link external research, and record provenance in PRs. Use when creating skills, updating SKILL.md, doing web research for skills, or auditing missing sources.
1skill-spec-review
Audit SKILL.md and skill directories for Agent Skills spec, Cursor extensions, and npx skills compatibility. Use when reviewing a skill, validating frontmatter, or checking marketplace readiness.
1concept-doc-store
Bootstraps and maintains a vectorless, layered documentation store for concepts, architecture, and decisions—without duplicating how code works. Use when organizing repo docs, writing ADRs, north-star charters, agent playbooks, or product-style doc lattices.
1multi-agent-handoff
Plan and document handoffs between specialized AI agents (foreman, workers, reviewers). Use for multi-agent workflows, subagent delegation, baton passes, or guild-style agent coordination.
1