Cloverleaf reference implementation — Claude Code skills for task scaffolding and the Delivery pipeline (implementer, documenter, reviewer, UI reviewer with multi-viewport visual diff, QA, merge).
Invoke the Plan agent (operation=breakdown) to decompose an approved RFC + completed spikes into a Plan with task_dag + inline tasks. Transitions Plan drafting → gate-pending (task_batch_gate). Usage — /cloverleaf-breakdown <RFC-ID>.
End-to-end Discovery orchestrator. Drives RFC → (Spikes) → Plan → gates → task materialisation. Blocks on human gate decisions (rfc_strategy_gate, task_batch_gate). On Plan approval, materialises tasks and asks whether to kick off /cloverleaf-run on the first DAG root. Usage — /cloverleaf-discover <brief-file>.
Run the Documenter agent on a task in the `implementing` state (full pipeline only). Dispatches a subagent to add doc-only commits to the feature branch, then advances implementing → documenting → review. Usage — /cloverleaf-document <TASK-ID>.
Invoke the Researcher agent (operation=draftRfc) to populate an RFC body from its brief. Emits zero or more Spike work items from the RFC's unknowns[]. Transitions the RFC drafting → spike-in-flight (if unknowns exist) or drafting → planning (if no unknowns). Usage — /cloverleaf-draft-rfc <RFC-ID>.
Human gate action on an RFC (rfc_strategy_gate) or Plan (task_batch_gate) in status gate-pending. Usage — /cloverleaf-gate <item-id> <approve|reject|revise> [reason]. `revise` is valid only at rfc_strategy_gate (RFC only).
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.
An AI-first software development methodology and its machine-readable interoperability standard.
Cloverleaf is a two-track methodology (Discovery + Delivery) for teams where AI agents are the primary code authors and humans orchestrate, gate, and architect. The Interoperability Standard makes Cloverleaf vendor-neutral: any tool can read, write, and verify Cloverleaf artifacts.
standard/ — the machine-readable specification: JSON Schemas, OpenAPI agent contracts, state machines, reference validators, and a conformance test pack. Published as @cloverleaf/standard on npm.reference-impl/ — reference implementation of the methodology as Claude Code skills. Published as @cloverleaf/reference-impl on npm.site/ — the methodology documentation site (Astro + MDX). Local-only during pre-publication.cd standard
npm install
npm test # unit-level schema + validator tests
npm run validate:examples # full conformance runner
npm run validate:examples -- --level=1 # L1 (Producer) suite
npm run validate:examples -- --level=2 # L2 (Exchange) suite
npm run validate:examples -- --level=3 # L3 (Host) suite
MIT — see LICENSE.
npx claudepluginhub cloverleaf-org/cloverleaf --plugin cloverleafComprehensive 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.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
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.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Create new skills, improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, or benchmark skill performance with variance analysis.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development