Catches bugs before they ship, and blocked features before they're built: per-task model/effort routing, stack-aware TDD (Java, Angular, React/Next.js, Python), and a two-pass adversarial reviewer (Dylan Dog).
A fork of obra/superpowers.
Skills 13 in the Claude listing
Configuring sixth sense One-time interactive setup — configures model preferences and effort levels for Sixth Sense subagents. Crossroad stack Use before applying test-driven-development, diagnosing-bugs, or requesting-code-review to detect whether the task targets Java/Spring Boot backend, Angular, React, Next.js, Python, or other stacks, a Diagnosing bugs Use when encountering bugs, test failures, or unexpected behavior — replaces random fixes with a disciplined, hypothesis-driven diagnosis loop. Dispatching parallel agents Use when facing multiple independent tasks that can be worked on without shared state or sequential dependencies — dispatches specialized subagents with Effort Routing, batching, and agent cap. Domain modeling Build and sharpen a project's domain model — pin down terminology, record architectural decisions, maintain CONTEXT.md and ADRs. Dylan dog The nightmare investigator — hunts edge cases and runs premortems on failure modes. Managing development branches Covers the full lifecycle of a development branch — creating an isolated git worktree with systematic safety checks, resolving an in-progress merge/rebase conflict by intent, and closing out a finishe Requesting code review Use when completing tasks, implementing features, or before merging — dispatches Dylan Dog (edge-case hunting) and processes feedback with technical rigor, not performative agreement. roundtable Put the user's plan or design through a relentless round of questioning until a shared understanding is reached. Specifying and implementing Turn the current conversation into a structured spec document, then implement it — orchestrates TDD, typechecking, code review, and commit. Test driven development Use when implementing a feature or fixing a bug. Using sixth sense Use when starting any conversation — establishes how to find and use skills, and platform adaptation. Verification before completion Use when about to claim work is complete, fixed, or passing, before committing or creating PRs — requires running verification commands and confirming output before making any success claims; evidence