AndrewTtofi
UserA full-lifecycle Claude Code skill system unified by a .spine/ project-memory store — your agent works like a senior engineer and never loses context.
Categories
Indexed Skills (6)
design
Use after align and before build to turn acceptance criteria into a concrete architecture — module boundaries, interfaces, data flow — recorded as ADRs and an architecture map in the Spine. Greenfield-first; also designs features within an existing codebase. Use when starting a new project, making upfront architectural decisions, or designing a non-trivial feature.
align
Use before building any feature or change to interrogate intent until acceptance criteria are crisp. Prevents the agent from building the wrong thing. Writes the agreed intent and criteria to .spine/journal.md.
build
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.
init
Use to bootstrap the .spine/ project-memory store in a repo before using the other skills. Detects the stack and seeds context.md, conventions.md, and journal.md. Run once per repo.
remember
Use at the end of a work session to distill what happened back into the .spine/ store so the next session starts informed instead of cold. Updates context and conventions, records decisions as ADRs, and compacts the journal.
verify
Use when work is supposedly complete, before claiming it is done or merging. Checks the change against the acceptance criteria by running tests, typecheck, and review — and reports evidence, never bare assertions. Reads criteria from the Spine.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.