This one helps you write architecture decision records without leaving your baseline documentation stale. It walks you through a three-question gate (hard to reverse, surprising without context, real trade-off) before you commit to writing anything, then forces you to sync the current-state baseline if the decision actually changed what the system is. The compact output contract is nice if you want structured decision hygiene. It's opinionated about distinguishing executed decisions from unexecuted ideas, and it won't let you treat an ADR as proof the work is done. Useful if your team has burned itself by recording why without updating what, or by writing decision docs for things that didn't need them.
npx -y skills add ganyuanran/aegis --skill recording-architecture-decisions --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
metabase/metabase
github/awesome-copilot
UKGovernmentBEIS/inspect_evals
addyosmani/agent-skills