From synapsys
Configure Synapsys memory storage. Use when the user says "install synapsys", "set up memory", "set up synapsys", "configure memory", "create memory store", "initialize memory", or asks to start using the memory system. Picks local (./.claude/synapsys), worktree (../.claude/synapsys), global (~/.claude/synapsys/<project>), or shared (~/.claude/synapsys-shared, reused across all projects).
How this skill is triggered — by the user, by Claude, or both
Slash command
/synapsys:installThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
1. If the user passed `local`, `worktree`, `global`, or `shared` as an argument, skip to step 3 with that kind.
local, worktree, global, or shared as an argument, skip to step 3 with that kind.AskUserQuestion to pick the kind. Recommend worktree when git worktree list shows >1 entry (multi-worktree setup); recommend local otherwise. Mention global (per-project, survives worktree deletion) and shared (one store reused across ALL projects) as options.node "${CLAUDE_PLUGIN_ROOT}/scripts/synapsys-init.js" --kind=<kind>
The init script is idempotent (re-running on an existing store just refreshes the marker). It writes .synapsys.json + a starter INDEX.md. It never deletes memories.
Multiple kinds can coexist — re-run this skill with a different kind to add another store.
Guides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Implements work from a spec or tickets using TDD at agreed seams, with regular typechecking and test runs, followed by code review.
npx claudepluginhub thomfilg/ai-plugin-work --plugin synapsys