Starlight: practice with public Academy teaching guides, source-backed challenges and feedback inside your own conversation.
Plugin starlight-academy from marketplace claude-skills-library in frankxai/claude-skills-library. Commands read from the repo's manifest — today.
connect-ai-architectConnect Starlight Academy practice to the separate AI Architect Academy human or sponsored-agent path and its canonical local AI Architect team. Use when the user wants architecture artifacts, multi-cloud implementation, validated deploy templates, or permissioned Academy resources after learning.
learn-with-starlightLearn with Starlight Academy when the user asks for its teachers, challenges, guided practice, or help giving useful feedback to AI. Choose a public mission, preserve a first attempt, coach with bounded hints, critique, revise and test transfer.
manage-quest-curriculumMaintain an evidence-based Starlight Academy quest curriculum and facilitator plan. Use when adding or revising quests, mapping prerequisites to artifact outcomes, connecting specialist studios, planning a cohort, or deciding what learning evidence may enter a portfolio.
run-learning-questRun an artifact-based Starlight Academy quest in the current AI conversation. Use when a learner wants advanced model orchestration, product or web design, private memory, an agent canvas, or a business workflow with a preserved attempt, critique, revision and transfer.
starlight-academyconnects to: https://starlightintelligence.academy/mcp
The complete library of Agent Skills — AI agents & orchestration, MCP & SDKs, Oracle & cloud, frontend & animation, engineering workflow, content & brand, and creative production. Skills auto-activate when relevant.
155 skills
Ten agent-architecture skills from claude-skills-library, each with trigger and outcome evals and a no-plugin baseline.
10 skills
GenCreator / FrankX creator OS: five practices for starting work safely, reviewing a diff, writing in a stated voice, running the checks, and a clean handoff.
5 skills · 1 command
Starlight: design one accountable AI department, practise agent evaluation and verify workflow evidence, with a local MCP practice server.
5 skills · 1 MCP server
Spend fewer tokens without lowering the ceiling: a router skill, a measurement protocol, a doctor/bench CLI and a fail-open RTK hook for shell output.
2 skills · hooks
Recommends relevant Claude Academy courses, tutorials, and use cases when users ask how to use Claude
19 skills
Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)
hooks
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Full Domino Data Lab platform support — workspaces, jobs, model deployment, experiment tracking, GenAI tracing, Spark/Ray/Dask, and app deployment for data science teams
26 skills · 4 commands · 3 agents · 1 MCP server
Claude Code native multi-agent orchestration with intelligent model routing across agents and skills. Zero learning curve. Maximum power.
85 skills · 20 commands · 19 agents · 1 MCP server · hooks
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.