AI SummaryGenerates per-category catalog JSON files from the npm package's public API. Each catalog lists all UseCase and EventHandler abstractions in a category with their resolved source file paths. LLMs read source files on demand for exact, up-to-date types — no enrichment phase needed. 1. Discovers all
Install
Copy this and paste it into Claude Code, Cursor, or any AI assistant:
I want to install the "webiny-skill-generator" skill in my project. Please run this command in my terminal: # Install skill into your project (2 files) mkdir -p .claude/skills/skills-generator && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/skills-generator/SKILL.md "https://raw.githubusercontent.com/webiny/webiny-js/next/.claude/skills/skills-generator/SKILL.md" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/skills-generator/architecture.md "https://raw.githubusercontent.com/webiny/webiny-js/next/.claude/skills/skills-generator/architecture.md" Then restart Claude Code (or reload the window in Cursor) so the skill is picked up.
Description
Generate, update, and maintain abstraction catalogs from the Webiny platform's public API. Use this skill whenever you need to: scan the `webiny` package to discover exported EventHandlers and UseCases, regenerate catalog JSON files after a platform release, check which abstractions are available, or add support for a new abstraction type.
How It Works
`bash yarn generate-skills ` The script: • Discovers all EventHandler and UseCase exports from packages/webiny • Resolves the actual source file path for each export via ts-morph • Writes one catalog JSON per category to skills/catalogs/ That's it. No skeletons, no enrichment, no templates.
Webiny Skill Generator
Generates per-category catalog JSON files from the webiny npm package's public API. Each catalog lists all UseCase and EventHandler abstractions in a category with their resolved source file paths. LLMs read source files on demand for exact, up-to-date types — no enrichment phase needed.
Output
` skills/ ├── catalogs/ │ ├── api-cms.json # 82 entries │ ├── api-security.json # 37 entries │ ├── api-website-builder.json │ ├── api-tenancy.json │ ├── api-file-manager.json │ ├── api-aco.json │ ├── api-scheduler.json │ └── api-system.json └── patterns/ ├── use-case.md # Generic UseCase pattern doc └── event-handler.md # Generic EventHandler pattern doc ` Each catalog entry looks like: `json { "className": "CreateTenantUseCase", "importPath": "webiny/api/tenancy", "type": "use-case", "typeLabel": "UseCase", "humanName": "Create Tenant", "entity": "Tenant", "operation": "create", "sourceFilePath": "packages/api-core/src/features/tenancy/CreateTenant/index.ts", "description": "Programmatically create tenant." } `
How LLMs Use Catalogs
• Find the right abstraction: Read the catalog JSON for the relevant category • Read the pattern doc: skills/patterns/use-case.md or skills/patterns/event-handler.md • Resolve types on demand: Read the sourceFilePath from the catalog entry to get exact interfaces, payloads, and error types • Generate code: Use the pattern + resolved types to write the extension This ensures types are always current — no stale snapshots.
Discussion
Health Signals
My Fox Den
Community Rating
Sign in to rate this booster