concept-doc-store
Concept doc store (vectorless)
Maintain documentation as a git-native, linkable lattice—not an embedding index. Agents and humans navigate by role and question, then jump to code, examples, and tests for behavior.
Reference layout: structured repository documentation directories (docs/start_here/docs_map.mdx, docs/decisions/, docs/superpowers/). Complements faq-driven-docs (package-level DESIGN_FAQ / DX_FAQ).
Core rule — three sources of truth
| Need | Authoritative source | Docs must… |
|---|---|---|
| How code behaves | Code, examples, tests | Link (Authoritative source: path/) — never paraphrase implementation |
| Why we chose X | ADRs, DESIGN_FAQ | Compress decision + trade-off only |
| How to use the product | DX_FAQ, guides, skills | Patterns and commands; defer API detail to examples |
If a doc paragraph could be replaced by reading a file or running an example, delete the paragraph and add a link.
Doc lattice (layers)
Build only layers the repo needs. See references/layer-catalog.md.
More from arenukvern/skill_steward
adr-records
Writes and maintains ADRs (MADR, Nygard, Y-Statement) and runs decision checkpoints before/during work—trigger matrix, option briefs, proposed ADRs. Use when creating or updating ADRs, facing a design fork, trade-off, boundary change, or when the user asks for key design decisions before implementing.
1faq-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.
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