Spec-Driven Development for Claude Code: 12 atomic Socratic skills + a TDD implement engine (agent-team & dynamic-workflow modes)
Agent
Clean-context multi-perspective reviewer of an SDD feature's candidate approaches. Use during specify's ideation pass (hard depth) to pressure-test the three strategic approaches from three lenses — Engineer, Executive, UX — so the recommendation isn't blind to cost, feasibility, or the user. Read-only; returns one…
Agent
Clean-context coherence critic for SDD artifacts (a spec or a SAD). Use after a Socratic pass to detect cross-section drift, coherence damage from user edits, structural gaps, and constraint/ quality leaks the per-section walk could not see. Read-only; reads the upstream artifacts itself; emits cited findings only. It…
Agent
Clean-context adversary for SDD. Two modes, named by the dispatch prompt. (A) Ambiguity hunt over a written spec — used by clarify to find where two competent engineers would reasonably build different things (vague terms, unmeasured NFRs, under-specified ACs, conflicts). (B) Failure-mode hunt over a raw idea +…
Agent
Read-only brownfield scout for SDD. Use when a skill (design, data-model) needs the existing codebase mapped before it designs against it — module boundaries, the patterns already in use, where similar features live, the migration/test conventions — or when fix needs a reported symptom localized to its code path.…
Agent
Makes a failing SDD test pass — the GREEN + REFACTOR + GATE steps of test-driven development. Use after test-author has produced a red test for a task. Given the task and its quoted failing line, it writes the minimal production code to pass, refactors while staying green, and runs the per-task gate (unit +…
Agent
Pencil-library keeper for the design canon. Use from design-system (tool: pencil) to reconcile the repo's .pen library with the canon: verify the app's ACTIVE document is the canon's penfile, seed the document variables from the token source (light + dark where the source has both), and ensure a foundations frame with…
Agent
Clean-context competitive + adjacent-solution researcher for an SDD feature idea. Use during specify's ideation pass (medium/hard depth) to find how the market and adjacent products already solve this problem — so the spec's recommendation is grounded in what exists, not a guess. Has web access (WebSearch/WebFetch)…
Agent
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
Agent
Clean-context product decomposer. Use from the roadmap skill to break a product idea (idea-brief / PRD / vision note) into incremental, buildable steps with an explicit dependency graph and an execution path (waves of steps that can safely run in parallel). Read-only; returns one ready-to-review roadmap draft in the…
Agent
Clean-context generator of the three strategic approaches for an SDD feature idea. Use during specify's ideation pass (hard depth) to lay out genuinely different ways to solve the problem — Simplicity (shortest path), Differentiation (the moat/wow), Balanced (the trade-off) — so the spec picks an approach from real…
Agent
Writes the failing test FIRST for an SDD task — the RED step of test-driven development. Use when the implement engine needs a test that encodes a task's acceptance criteria before any production code exists. Given a task (title, acceptance-criteria text, definition of done, files hint), it writes the test(s) where…