ethical-stewardship
Ethical stewardship
Establish and maintain software ethics not as a series of rigid compliance checklists, but as a dynamic stewardship practice and moral bridge for human-agent collaboration.
This skill guides agents and humans to work side-by-side to elicit, translate, and refine context-appropriate ethical constraints for any project.
When to use
- Bootstrapping a repository's ethical core, project credo, or team values.
- Helping a team identify implicit ethical choices and code styling preferences in an existing repository.
- Translating abstract moral principles (like user trust or simplicity) into quantifiable technical constraints.
- Resolving design trade-offs (e.g., balancing speed vs. quality) through a clear ethical decision framework.
- Auditing a proposed design, dependency, or feature against product quality boundaries.
1. The Human-Agent Stewardship Workflow
AI agents and humans should collaboratively guide the repository's ethical lifecycle using the following four-phase loop:
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.
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.
1