modernize-ui5-app
SkillEnd-to-end workflow for modernizing a UI5 application. Use this skill when: - User wants to modernize their UI5 app - User mentions "UI5 modernization", "modernize UI5 app", "upgrade UI5", "make app modern UI5 compatible" - User asks to "fix all linter errors", "run full modernization", "modernize m
Install
git clone https://github.com/UI5/plugins-coding-agents.git ~/.claude/skills/modernize-ui5-appWhat is modernize-ui5-app?
End-to-end workflow for modernizing a UI5 application. Use this skill when: - User wants to modernize their UI5 app - User mentions "UI5 modernization", "modernize UI5 app", "upgrade UI5", "make app modern UI5 compatible" - User asks to "fix all linter errors", "run full modernization", "modernize my UI5 project" This skill runs the modernization in five phases with a verification gate after each phase. The user picks the verification mode once at the start (full autonomous / half autonomous / manual). The agent applies that mode at every gate without re-asking.
What this can do
Capabilities declared in this component's own frontmatter — not inferred.
Inherit all session tools
Declares no tool restrictions — inherits every session tool
~142 tokens of context used while enabled, before you invoke anything
Documentation
README · ~25 min readUI5 Modernization Workflow
This skill modernizes a UI5 application in five phases, each followed by a verification gate. The user picks the gate behavior once at the start — full autonomous, half autonomous, or manual — and the orchestrator applies that choice at every phase boundary.
The five phases
- Mechanical baseline — autofix + test starter restructure. These touch many files but are low-risk and unlock test runs in later gates.
- Foundation —
manifest.jsonandComponent.js. Everything downstream reads the manifest. - Module system & globals — get the dependency graph right (sap.ui.define arrays, lazy requires, no implicit globals). Cyclic-dep and blind-spot fixes belong here because they're symptoms of the same module-system work, not separate phases.
- Deprecated APIs — pure name-for-name replacement. Independent of module structure, so safe to run in parallel after phase 3 stabilizes the graph.
- CSP compliance — last, because it depends on every prior phase being CSP-clean (no inline scripts, no globals leaking through).
A documentation pass writes MODERNIZATION-REPORT.md and MODERNIZATION-ISSUES.md after phase 5.
Rule ID to Skill Mapping
Reviews
Log in to leave a review.
No reviews yet — be the first.
Explore related
Other things in this space — across every part of the ecosystem, not just skills.
Skillssimilar to this one
All skills →awesome-claude-skills
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
71.2K stars
claude-automation-recommender
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wa
32.8K stars
agents-best-practices
Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.
2.2K stars