Author an Architecture Decision Record under docs/projects/<project>/adr/. Only when a decision has cross-feature, immutable, long-lived consequences.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-company-of-one:adr-writingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Capture a significant architectural decision as an immutable record. ADRs are
Capture a significant architectural decision as an immutable record. ADRs are distinct from spec files: specs describe what one feature delivers; ADRs describe a constraint future features will live under.
This skill is used only in /think docs-writing context, where direct writes to
DESIGN.md are the deliverable. /dev must not invoke this skill; mid-step /dev
skills read BRIEF.md only.
BRIEF.md ## Current Contract and clarified decision from clarify.docs/projects/<project>/adr/.docs/projects/<project>/adr/NNN-<past-tense-title>.md where NNN is zero-padded
and strictly one greater than the current max.BRIEF.md ## Active Specs → ADRs referenced with the new path.docs/projects/<project>/adr/ and incrementing.Proposed on first write. Flip to Accepted only after user review.## Follow-up amendment at the bottom of the existing one. ADRs are immutable.spec-writing.npx claudepluginhub the-own-lab/claude-company-of-one --plugin claude-company-of-oneProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.