npx claudepluginhub anicol/engineering-agents --plugin agentemThis skill uses the workspace's default tool permissions.
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Orchestrates end-to-end MLOps pipelines from data preparation and feature engineering through model training, validation, and production deployment using DAG patterns.
Before performing your primary task, load and validate the project's context files.
Find context directory. Look for a context/ directory in the project root.
If no context directory exists:
/agentem:init to scaffold the context directory.If context directory exists, read all .md files found in context/:
context/product/strategy.mdcontext/architecture/system-map.mdcontext/team/topology.mdcontext/team/capacity.mdcontext/standards/review-playbook.mdcontext/standards/spec-standards.mdcontext/learnings/what-doesnt.mdcontext/learnings/what-works.md.md files presentCheck for placeholder content. Scan each file for [placeholder] patterns (text in square brackets with uppercase first letter, e.g. [Your Product Name], [Team Name]). If a file has many unfilled placeholders, note which files need filling.
Load agent state from context/agent-state.json if it exists:
last_run, run_count, last_summaryactive signals — do not re-alert on signals already reporteddismissed signals — skip these entirelyfeedback history — note any patterns (e.g., signal types consistently rated "No")actions_taken — know what actions were already executedLoad autonomy config from context/autonomy.yaml if it exists:
autonomous, which requires_approval, which disabledrequires_approvalSummarize available context before proceeding with the agent's primary task: