Self-improving Compose Multiplatform UI harness. Inspection tests render every screen across a stress matrix; a deterministic Tier-1 asserter plus a vision evaluator grade them in a separate lane; recurring findings ratchet into permanent gates via a compounding feedback ledger. Ships Konsist architecture rails and a setup skill that scaffolds it all into a project.
Plugin shipwithai-mobile-ui-harness from marketplace shipwithai in ShipWithAI/shipwithai-plugins. Commands read from the repo's manifest — 1 month ago.
konsist-architecture-testsUse when adding or extending automated module-boundary / architecture enforcement in a Kotlin or Kotlin Multiplatform Gradle project — rules like "core must not depend on feature", "api must not leak impl", layer/package dependency directions that should fail the build the moment a bad import is wri
mobile-designEvaluation criteria for grading rendered mobile UI screens. Use when reviewing, critiquing, or self-checking a mobile UI screenshot — especially after any UI edit in an agentic loop — to decide pass/fail and produce concrete fixes. Targets Compose Multiplatform (Android + iOS), Material 3. The mobil
setupWire the self-improving UI harness into this Compose Multiplatform project — scaffold the harness/ ledger + Python tools, install Tier1Assertions + the Roborazzi screenshot-testing convention plugin + an inspection-test template (package-parameterized), and print the build wiring. Short interview fi
/shipwithai-mobile-ui-harness:ui-distillDistill the feedback ledger into promotion proposals and — on human approval — harden recurring findings into permanent gates, then delete the now-redundant soft guidance. The self-improvement ratchet's act-half.
/shipwithai-mobile-ui-harness:ui-iterateIterate on a Compose screen until it passes the structural gate + visual evaluator — renders the stress matrix, grades it in a separate lane, logs findings to the ledger. Caps at 4 iterations then escalates.
/shipwithai-mobile-ui-harness:ui-metricsRender the harness's self-improvement metrics from the ledger — iterations-to-pass, first-pass yield, and recurrence-after-deposit — to show whether the harness is actually compounding.
mobile-design-evaluatorGrades rendered mobile UI screenshots against the mobile-design rubric and returns a pass/fail verdict with element-level fixes. Dispatch it AFTER an inspection harness has rendered a screen's PNGs (e.g. SongsScreenInspection → build/outputs/roborazzi/_inspect_*.png), especially after any @Composabl
Set up a standardized Claude Code harness for any project. One guided interview configures CLAUDE.md, permissions, hooks, MCP servers, agents, and SSOT docs. Three tiers: Essential (5 min), Standard (15 min), Full (30 min).
13 skills · 4 commands · 2 agents
Guardrail-first Spring Boot + JPA toolkit. Just-in-time hooks catch missing @Version, broken @Transactional proxies, entity-in-controller leaks, N+1, and query injection as you write them; scaffold skills generate correct-by-default entities, endpoints, and migrations; a tuned reviewer agent shares one ruleset with the hooks.
11 skills · 1 agent
Set up production-ready auth in minutes. Supports Better Auth and Firebase Auth with OAuth social login, UI components, database schemas. Auto-detects existing themes.
2 skills · 2 commands · hooks
Generate a production-ready Claude Code harness for your project. Auto-detects stack (Next.js, Laravel, Spring Boot). Generates CLAUDE.md, settings.json, and safety hooks in one command.
2 skills · 2 commands · hooks
Governance harness for the ShipWithAI design system: spec-first workflow skills, read-only auditor agents (incl. design-harness-doctor), and warn-only guardrail hooks. Install one plugin and a dev/agent inherits the whole workflow.
Governance harness for the ShipWithAI knowledge corpus: a thin orchestration layer that runs the existing citation/outcome validators, links the member handbook, and prepares governance dossiers for a human to sign.
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.