This is a Socratic questioning session that stress-tests your plan against your codebase's existing terminology and documented decisions. It asks one question at a time, waiting for your answer before moving on, and updates your CONTEXT.md glossary and ADRs as you clarify things. The skill actively challenges fuzzy language, invents concrete scenarios to expose edge cases, and cross-references what you're saying against the actual code. It's intentionally picky about ADRs, only suggesting them when a decision is truly hard to reverse and would confuse future readers. Use this when you have a plan that needs to survive contact with your domain model's reality.
npx -y skills add vinvcn/mattpocock-skills-zh-cn --skill grill-with-docs --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
supercent-io/skills-template
supercent-io/skills-template
huangjia2019/claude-code-engineering
reactjs/react.dev
reactjs/react.dev