Orchestrates GitHub spec-kit (spec-driven development) and Superpowers (disciplined agentic workflow) into one mode-aware flow: greenfield, per-feature, and brownfield.
Before code review, checks the branch diff against the spec's acceptance criteria and produces an advisory met/unmet/uncertain checklist for the human reviewer. Non-blocking. Use at the end of executing a superkit/spec-kit feature, just before requesting-code-review.
Iterative/brownfield change — re-spec just the affected area so the audit trail stays intact, regenerate plan/tasks, then execute with superpowers. Guards against editing code without updating the spec.
Use when iterate-to-green stalls or when stuck debugging something complex — fans out a large agent swarm to find the root cause and return a patch, using Claude Code dynamic workflows when available and degrading to superpowers:dispatching-parallel-agents otherwise.
Build one feature end-to-end with the combined spec-kit + superpowers loop — brainstorm, specify/clarify/plan/tasks, then worktree + TDD + subagent execution + review + finish.
0-to-1 product build — define the product once, write a whole batch of specs up front, then execute the batch with superpowers. Asks how to execute (continuous / sequential / parallel) at execute time.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin that fuses spec-kit and superpowers: spec-kit plans WHAT, superpowers controls HOW, superkit decides WHEN / WHICH / IN WHAT ORDER.
superkit orchestrates two tools, so install both, then the plugin itself.
uv tool install specify-cli (then run specify init . --ai claude inside each project you use superkit in)./plugin install superpowers@claude-plugins-official./plugin marketplace add joshuatrobertson/super-kit
/plugin install superkit
(Or clone the repo and point at the local path: /plugin marketplace add ./super-kit.)/superkit:setup — verify dependencies, write the bridging rule, create .superkit//superkit:greenfield, /superkit:feature, or /superkit:enhance/superkit:status — see every spec's state and what's nextSee docs/superpowers/specs/ for the full design.
| Skill | Trigger | Status | Description |
|---|---|---|---|
/superkit:setup | Invoke-only | Implemented | One-time setup: verify dependencies, write the bridging rule into spec-kit, create .superkit/ and initialise the registry. |
/superkit:greenfield | Invoke-only | Implemented | Define the product, batch-generate specs for every backlog item, then execute them all end-to-end. |
/superkit:feature | Invoke-only | Implemented | Spec, plan, and execute a single new feature end-to-end (branch + optional PR). |
/superkit:enhance | Invoke-only | Implemented | Brownfield re-spec: update or add a small spec for an existing area, regenerate plan/tasks, and execute. |
/superkit:iterate-to-green | Invoke-only | Implemented | After per-task TDD, run the full suite and loop scoped fixes until green or until the stall gate asks how to proceed. |
/superkit:escalate-to-workflows | Invoke-only | Implemented | When the loop is stuck, preflight Claude Code dynamic workflows, fan out debugging, and return a patch for the in-session loop to verify. |
/superkit:status | Invoke-only | Implemented | Display the live state of every spec in the registry so you know what's done and what's next. |
superkit-orchestration | Auto-trigger | Implemented | Route build/spec requests to the right mode and right-size the process so small work is not over-engineered. |
respecting-the-spec-contract | Auto-trigger | Implemented | During execution, enforce that tasks.md is the contract and subagents receive only their own task. |
superkit:stack-conventions | Auto-trigger | Implemented | Fetch the project stack's current best practices from the web and write a human-confirmed conventions block into the constitution; invoked by setup, re-runnable to refresh. |
superkit:conformance-check | Auto-trigger | Implemented | Before review, check the branch diff against spec.md acceptance criteria and surface an advisory met/unmet/uncertain checklist. |
/superkit:feature for a new feature, /superkit:greenfield for a new product.superkit invokes spec-kit's speckit-* skills and superpowers' skills via the Skill tool. .superkit/registry.md is the source-of-truth index tracking every spec's status; spec artefacts (spec.md, plan.md, tasks.md) stay in spec-kit's specs/<id>/ directories.
Every skill superkit invokes, across all modes, and where the execution-loop additions fire.
Nodes marked (NEW) — iterate-to-green and escalate-to-workflows — are introduced by
the iterate-to-green design.
See docs/workflow.md for the annotated, node-by-node walkthrough.
flowchart TD
U([User: build / change / spec something]) --> ROUTER{{"superkit-orchestration<br/>route + right-size"}}
ROUTER -->|"tiny: <30m, <3 files"| TINY([just do it — no tooling])
ROUTER -->|"not set up here"| SETUP
ROUTER -->|"new product"| GF_CONST
ROUTER -->|"one new feature"| BR
ROUTER -->|"change existing"| ENH_SCOPE
subgraph SET["/superkit:setup — one-time, idempotent"]
direction TB
SETUP["check-deps.sh<br/>(spec-kit + superpowers)"] --> SETUPB["bridging rule → constitution.md"] --> SETUPC["registry.sh init"]
end
SETUPC -.->|then pick a mode| ROUTER
npx claudepluginhub joshuatrobertson/super-kit --plugin superkitComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.