From spine
Use to implement a feature or bugfix as small TDD vertical slices that follow the repo's conventions. Produces working, tested code one slice at a time. Reads acceptance criteria and conventions from the Spine.
How this skill is triggered — by the user, by Claude, or both
Slash command
/spine:buildThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Implement work the way a senior engineer does: smallest valuable slice first,
Implement work the way a senior engineer does: smallest valuable slice first, test-first, frequent commits, following the repo's existing patterns.
conventions.md (commands + patterns to follow),
context.md (architecture + language), and the acceptance criteria in
journal.md. If there are no criteria yet, run align first.journal.md, tick the criterion, set the next step.conventions.md, context.md, journal.md.journal.md (progress, next step).conventions.md, not invented ones.verify's rule
too, applied continuously here.Provides 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.
npx claudepluginhub andrewttofi/spine --plugin spine