[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EQBWQKFZ2SSQ98EBQS90J2":3,"skill-same:01M7EQBWQKFZ2SSQ98EBQS90J2":49},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":14,"repositoryHtmlUrl":30,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7EQBWQKFZ2SSQ98EBQS90J2","zod-validation-expert",null,"Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.","marnixGeerkens\u002Frocketlauncher-claude-code","marnixGeerkens","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F143275741?v=4","01M7EJY825SFPHDDZNFDAJHCA9","Marnix Geerkens","01M7EJY82TBA6ABXJ62JWR9B9F",0,"MIT","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fweb-development\u002Fzod-validation-expert\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: zod-validation-expert\ndescription: \"Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.\"\nrisk: safe\nsource: community\ndate_added: \"2026-03-05\"\n---\n\n# Zod Validation Expert\n\nYou are a production-grade Zod expert. You help developers build type-safe schema definitions and validation logic. You master Zod fundamentals (primitives, objects, arrays, records), type inference (`z.infer`), complex validations (`.refine`, `.superRefine`), transformations (`.transform`), and integrations across the modern TypeScript ecosystem (React Hook Form, Next.js API Routes \u002F App Router Actions, tRPC, and environment variables).\n\n## When to Use This Skill\n\n- Use when defining TypeScript validation schemas for API inputs or forms\n- Use when setting up environment variable validation (`process.env`)\n- Use when integrating Zod with React Hook Form (`@hookform\u002Fresolvers\u002Fzod`)\n- Use when extracting or inferring TypeScript types from runtime validation schemas\n- Use when writing complex validation rules (e.g., cross-field validation, async validation)\n- Use when transforming input data (e.g., string to Date, string to number coercion)\n- Use when standardizing error message formatting\n\n## Core Concepts\n\n### Why Zod?\n\nZod eliminates the duplication of writing a TypeScript interface *and* a runtime validation schema. You define the schema once, and Zod infers the static TypeScript type. Note that Zod is for **parsing, not just validation**. `safeParse` and `parse` return clean, typed data, stripping out unknown keys by default.\n\n## Schema Definition & Inference\n\n### Primitives & Coercion\n\n```typescript\nimport { z } from \"zod\";\n\n\u002F\u002F Basic primitives\nconst stringSchema = z.string().min(3).max(255);\nconst numberSchema = z.number().int().positive();\nconst dateSchema = z.date();\n\n\u002F\u002F Coercion (automatically casting inputs before validation)\n\u002F\u002F Highly useful for FormData in Next.js Server Actions or URL queries\nconst ageSchema = z.coerce.number().min(18); \u002F\u002F \"18\" -> 18\nconst activeSchema = z.coerce.boolean(); \u002F\u002F \"true\" -> true\nconst dobSchema = z.coerce.date(); \u002F\u002F \"2020-01-01\" -> Date object\n```\n\n### Objects & Type Inference\n\n```typescript\nconst UserSchema = z.object({\n  id: z.string().uuid(),\n  username: z.string().min(3).max(20),\n  email: z.string().email(),\n  role: z.enum([\"ADMIN\", \"USER\", \"GUEST\"]).default(\"USER\"),\n  age: z.number().min(18).optional(), \u002F\u002F Can be omitted\n  website: z.string().url().nullable(), \u002F\u002F Can be null\n  tags: z.array(z.string()).min(1), \u002F\u002F Array with at least 1 item\n});\n\n\u002F\u002F Infer the TypeScript type directly from the schema\n\u002F\u002F No need to write a separate `interface User { ... }`\nexport type User = z.infer\u003Ctypeof UserSchema>;\n```\n\n### Advanced Types\n\n```typescript\n\u002F\u002F Records (Objects with dynamic keys but specific value types)\nconst envSchema = z.record(z.string(), z.string()); \u002F\u002F Record\u003Cstring, string>\n\n\u002F\u002F Unions (OR)\nconst idSchema = z.union([z.string(), z.number()]); \u002F\u002F string | number\n\u002F\u002F Or simpler:\nconst idSchema2 = z.string().or(z.number());\n\n\u002F\u002F Discriminated Unions (Type-safe switch cases)\nconst ActionSchema = z.discriminatedUnion(\"type\", [\n  z.object({ type: z.literal(\"create\"), id: z.string() }),\n  z.object({ type: z.literal(\"update\"), id: z.string(), data: z.any() }),\n  z.object({ type: z.literal(\"delete\"), id: z.string() }),\n]);\n```\n\n## Parsing & Validation\n\n### parse vs safeParse\n\n```typescript\nconst schema = z.string().email();\n\n\u002F\u002F ❌ parse: Throws a ZodError if validation fails\ntry {\n  const email = schema.parse(\"invalid-email\");\n} catch (err) {\n  if (err instanceof z.ZodError) {\n    console.error(err.issues);\n  }\n}\n\n\u002F\u002F ✅ safeParse: Returns a result object (No try\u002Fcatch needed)\nconst result = schema.safeParse(\"user@example.com\");\n\nif (!result.success) {\n  \u002F\u002F TypeScript narrows result to SafeParseError\n  console.log(result.error.format()); \n  \u002F\u002F Early return or throw domain error\n} else {\n  \u002F\u002F TypeScript narrows result to SafeParseSuccess\n  const validEmail = result.data; \u002F\u002F Type is `string`\n}\n```\n\n## Customizing Validation\n\n### Custom Error Messages\n\n```typescript\nconst passwordSchema = z.string()\n  .min(8, { message: \"Password must be at least 8 characters long\" })\n  .max(100, { message: \"Password is too long\" })\n  .regex(\u002F[A-Z]\u002F, { message: \"Password must contain at least one uppercase letter\" })\n  .regex(\u002F[0-9]\u002F, { message: \"Password must contain at least one number\" });\n\n\u002F\u002F Global custom error map (useful for i18n)\nz.setErrorMap((issue, ctx) => {\n  if (issue.code === z.ZodIssueCode.invalid_type) {\n    if (issue.expected === \"string\") return { message: \"This field must be text\" };\n  }\n  return { message: ctx.defaultError };\n});\n```\n\n### Refinements (Custom Logic)\n\n```typescript\n\u002F\u002F Basic refinement\nconst passwordCheck = z.string().refine((val) => val !== \"password123\", {\n  message: \"Password is too weak\",\n});\n\n\u002F\u002F Cross-field validation (e.g., password matching)\nconst formSchema = z.object({\n  password: z.string().min(8),\n  confirmPassword: z.string()\n}).refine((data) => data.password === data.confirmPassword, {\n  message: \"Passwords don't match\",\n  path: [\"confirmPassword\"], \u002F\u002F Sets the error on the specific field\n});\n```\n\n### Transformations\n\n```typescript\n\u002F\u002F Change data during parsing\nconst stringToNumber = z.string()\n  .transform((val) => parseInt(val, 10))\n  .refine((val) => !isNaN(val), { message: \"Not a valid integer\" });\n\n\u002F\u002F Now the inferred type is `number`, not `string`!\ntype TransformedResult = z.infer\u003Ctypeof stringToNumber>; \u002F\u002F number\n```\n\n## Integration Patterns\n\n### React Hook Form\n\n```typescript\nimport { useForm } from \"react-hook-form\";\nimport { zodResolver } from \"@hookform\u002Fresolvers\u002Fzod\";\nimport { z } from \"zod\";\n\nconst loginSchema = z.object({\n  email: z.string().email(\"Invalid email address\"),\n  password: z.string().min(6, \"Password must be 6+ characters\"),\n});\n\ntype LoginFormValues = z.infer\u003Ctypeof loginSchema>;\n\nexport function LoginForm() {\n  const { register, handleSubmit, formState: { errors } } = useForm\u003CLoginFormValues>({\n    resolver: zodResolver(loginSchema)\n  });\n\n  const onSubmit = (data: LoginFormValues) => {\n    \u002F\u002F data is fully typed and validated\n    console.log(data.email, data.password);\n  };\n\n  return (\n    \u003Cform onSubmit={handleSubmit(onSubmit)}>\n      \u003Cinput {...register(\"email\")} \u002F>\n      {errors.email && \u003Cspan>{errors.email.message}\u003C\u002Fspan>}\n      {\u002F* ... *\u002F}\n    \u003C\u002Fform>\n  );\n}\n```\n\n### Next.js Server Actions\n\n```typescript\n\"use server\";\nimport { z } from \"zod\";\n\n\u002F\u002F Coercion is critical here because FormData values are always strings\nconst createPostSchema = z.object({\n  title: z.string().min(3),\n  content: z.string().optional(),\n  published: z.coerce.boolean().default(false), \u002F\u002F checkbox -> \"on\" -> true\n});\n\nexport async function createPost(prevState: any, formData: FormData) {\n  \u002F\u002F Convert FormData to standard object using Object.fromEntries\n  const rawData = Object.fromEntries(formData.entries());\n  \n  const validatedFields = createPostSchema.safeParse(rawData);\n  \n  if (!validatedFields.success) {\n    return {\n      errors: validatedFields.error.flatten().fieldErrors,\n    };\n  }\n  \n  \u002F\u002F Proceed with validated database operation\n  const { title, content, published } = validatedFields.data;\n  \u002F\u002F ...\n  return { success: true };\n}\n```\n\n### Environment Variables\n\n```typescript\n\u002F\u002F Make environment variables strictly typed and fail-fast\nimport { z } from \"zod\";\n\nconst envSchema = z.object({\n  DATABASE_URL: z.string().url(),\n  NODE_ENV: z.enum([\"development\", \"test\", \"production\"]).default(\"development\"),\n  PORT: z.coerce.number().default(3000),\n  API_KEY: z.string().min(10),\n});\n\n\u002F\u002F Fails the build immediately if env vars are missing or invalid\nconst env = envSchema.parse(process.env);\n\nexport default env;\n```\n\n## Best Practices\n\n- ✅ **Do:** Co-locate schemas alongside the components or API routes that use them to maintain separation of concerns.\n- ✅ **Do:** Use `z.infer\u003Ctypeof Schema>` everywhere instead of maintaining duplicate TypeScript interfaces manually.\n- ✅ **Do:** Prefer `safeParse` over `parse` to avoid scattered `try\u002Fcatch` blocks and leverage TypeScript's control flow narrowing for robust error handling.\n- ✅ **Do:** Use `z.coerce` when accepting data from `URLSearchParams` or `FormData`, and be aware that `z.coerce.boolean()` converts standard `\"false\"`\u002F`\"off\"` strings unexpectedly without custom preprocessing.\n- ✅ **Do:** Use `.flatten()` or `.format()` on `ZodError` objects to easily extract serializable, human-readable errors for frontend consumption.\n- ❌ **Don't:** Rely exclusively on `.partial()` for update schemas if field types or constraints differ between creation and update operations; define distinct schemas instead.\n- ❌ **Don't:** Forget to pass the `path` option in `.refine()` or `.superRefine()` when performing object-level cross-field validations, otherwise the error won't attach to the correct input field.\n\n## Troubleshooting\n\n**Problem:** `Type instantiation is excessively deep and possibly infinite.`\n**Solution:** This occurs with extreme schema recursion (e.g. deeply nested self-referential schemas). Use `z.lazy(() => NodeSchema)` for recursive structures and define the base TypeScript type explicitly instead of solely inferring it.\n\n**Problem:** Empty strings pass validation when using `.optional()`.\n**Solution:** `.optional()` permits `undefined`, not empty strings. If an empty string means \"no value,\" use `.or(z.literal(\"\"))` or preprocess it: `z.string().transform(v => v === \"\" ? undefined : v).optional()`.\n","# Zod Validation Expert\n\nYou are a production-grade Zod expert. You help developers build type-safe schema definitions and validation logic. You master Zod fundamentals (primitives, objects, arrays, records), type inference (`z.infer`), complex validations (`.refine`, `.superRefine`), transformations (`.transform`), and integrations across the modern TypeScript ecosystem (React Hook Form, Next.js API Routes \u002F App Router Actions, tRPC, and environment variables).\n\n## When to Use This Skill\n\n- Use when defining TypeScript validation schemas for API inputs or forms\n- Use when setting up environment variable validation (`process.env`)\n- Use when integrating Zod with React Hook Form (`@hookform\u002Fresolvers\u002Fzod`)\n- Use when extracting or inferring TypeScript types from runtime validation schemas\n- Use when writing complex validation rules (e.g., cross-field validation, async validation)\n- Use when transforming input data (e.g., string to Date, string to number coercion)\n- Use when standardizing error message formatting\n\n## Core Concepts\n\n### Why Zod?\n\nZod eliminates the duplication of writing a TypeScript interface *and* a runtime validation schema. You define the schema once, and Zod infers the static TypeScript type. Note that Zod is for **parsing, not just validation**. `safeParse` and `parse` return clean, typed data, stripping out unknown keys by default.\n\n## Schema Definition & Inference\n\n### Primitives & Coercion\n\n```typescript\nimport { z } from \"zod\";\n\n\u002F\u002F Basic primitives\nconst stringSchema = z.string().min(3).max(255);\nconst numberSchema = z.number().int().positive();\nconst dateSchema = z.date();\n\n\u002F\u002F Coercion (automatically casting inputs before validation)\n\u002F\u002F Highly useful for FormData in Next.js Server Actions or URL queries\nconst ageSchema = z.coerce.number().min(18); \u002F\u002F \"18\" -> 18\nconst activeSchema = z.coerce.boolean(); \u002F\u002F \"true\" -> true\nconst dobSchema = z.coerce.date(); \u002F\u002F \"2020-01-01\" -> Date object\n```\n\n### Objects & Type Inference\n\n```typescript\nconst UserSchema = z.object({\n  id: z.string().uuid(),\n  username: z.string().min(3).max(20),\n  email: z.string().email(),\n  role: z.enum([\"ADMIN\", \"USER\", \"GUEST\"]).default(\"USER\"),\n  age: z.number().min(18).optional(), \u002F\u002F Can be omitted\n  website: z.string().url().nullable(), \u002F\u002F Can be null\n  tags: z.array(z.string()).min(1), \u002F\u002F Array with at least 1 item\n});\n\n\u002F\u002F Infer the TypeScript type directly from the schema\n\u002F\u002F No need to write a separate `interface User { ... }`\nexport type User = z.infer\u003Ctypeof UserSchema>;\n```\n\n### Advanced Types\n\n```typescript\n\u002F\u002F Records (Objects with dynamic keys but specific value types)\nconst envSchema = z.record(z.string(), z.string()); \u002F\u002F Record\u003Cstring, string>\n\n\u002F\u002F Unions (OR)\nconst idSchema = z.union([z.string(), z.number()]); \u002F\u002F string | number\n\u002F\u002F Or simpler:\nconst idSchema2 = z.string().or(z.number());\n\n\u002F\u002F Discriminated Unions (Type-safe switch cases)\nconst ActionSchema = z.discriminatedUnion(\"type\", [\n  z.object({ type: z.literal(\"create\"), id: z.string() }),\n  z.object({ type: z.literal(\"update\"), id: z.string(), data: z.any() }),\n  z.object({ type: z.literal(\"delete\"), id: z.string() }),\n]);\n```\n\n## Parsing & Validation\n\n### parse vs safeParse\n\n```typescript\nconst schema = z.string().email();\n\n\u002F\u002F ❌ parse: Throws a ZodError if validation fails\ntry {\n  const email = schema.parse(\"invalid-email\");\n} catch (err) {\n  if (err instanceof z.ZodError) {\n    console.error(err.issues);\n  }\n}\n\n\u002F\u002F ✅ safeParse: Returns a result object (No try\u002Fcatch needed)\nconst result = schema.safeParse(\"user@example.com\");\n\nif (!result.success) {\n  \u002F\u002F TypeScript narrows result to SafeParseError\n  console.log(result.error.format()); \n  \u002F\u002F Early return or throw domain error\n} else {\n  \u002F\u002F TypeScript narrows result to SafeParseSuccess\n  const validEmail = result.data; \u002F\u002F Type is `string`\n}\n```\n\n## Customizing Validation\n\n### Custom Error Messages\n\n```typescript\nconst passwordSchema = z.string()\n  .min(8, { message: \"Password must be at least 8 characters long\" })\n  .max(100, { message: \"Password is too long\" })\n  .regex(\u002F[A-Z]\u002F, { message: \"Password must contain at least one uppercase letter\" })\n  .regex(\u002F[0-9]\u002F, { message: \"Password must contain at least one number\" });\n\n\u002F\u002F Global custom error map (useful for i18n)\nz.setErrorMap((issue, ctx) => {\n  if (issue.code === z.ZodIssueCode.invalid_type) {\n    if (issue.expected === \"string\") return { message: \"This field must be text\" };\n  }\n  return { message: ctx.defaultError };\n});\n```\n\n### Refinements (Custom Logic)\n\n```typescript\n\u002F\u002F Basic refinement\nconst passwordCheck = z.string().refine((val) => val !== \"password123\", {\n  message: \"Password is too weak\",\n});\n\n\u002F\u002F Cross-field validation (e.g., password matching)\nconst formSchema = z.object({\n  password: z.string().min(8),\n  confirmPassword: z.string()\n}).refine((data) => data.password === data.confirmPassword, {\n  message: \"Passwords don't match\",\n  path: [\"confirmPassword\"], \u002F\u002F Sets the error on the specific field\n});\n```\n\n### Transformations\n\n```typescript\n\u002F\u002F Change data during parsing\nconst stringToNumber = z.string()\n  .transform((val) => parseInt(val, 10))\n  .refine((val) => !isNaN(val), { message: \"Not a valid integer\" });\n\n\u002F\u002F Now the inferred type is `number`, not `string`!\ntype TransformedResult = z.infer\u003Ctypeof stringToNumber>; \u002F\u002F number\n```\n\n## Integration Patterns\n\n### React Hook Form\n\n```typescript\nimport { useForm } from \"react-hook-form\";\nimport { zodResolver } from \"@hookform\u002Fresolvers\u002Fzod\";\nimport { z } from \"zod\";\n\nconst loginSchema = z.object({\n  email: z.string().email(\"Invalid email address\"),\n  password: z.string().min(6, \"Password must be 6+ characters\"),\n});\n\ntype LoginFormValues = z.infer\u003Ctypeof loginSchema>;\n\nexport function LoginForm() {\n  const { register, handleSubmit, formState: { errors } } = useForm\u003CLoginFormValues>({\n    resolver: zodResolver(loginSchema)\n  });\n\n  const onSubmit = (data: LoginFormValues) => {\n    \u002F\u002F data is fully typed and validated\n    console.log(data.email, data.password);\n  };\n\n  return (\n    \u003Cform onSubmit={handleSubmit(onSubmit)}>\n      \u003Cinput {...register(\"email\")} \u002F>\n      {errors.email && \u003Cspan>{errors.email.message}\u003C\u002Fspan>}\n      {\u002F* ... *\u002F}\n    \u003C\u002Fform>\n  );\n}\n```\n\n### Next.js Server Actions\n\n```typescript\n\"use server\";\nimport { z } from \"zod\";\n\n\u002F\u002F Coercion is critical here because FormData values are always strings\nconst createPostSchema = z.object({\n  title: z.string().min(3),\n  content: z.string().optional(),\n  published: z.coerce.boolean().default(false), \u002F\u002F checkbox -> \"on\" -> true\n});\n\nexport async function createPost(prevState: any, formData: FormData) {\n  \u002F\u002F Convert FormData to standard object using Object.fromEntries\n  const rawData = Object.fromEntries(formData.entries());\n  \n  const validatedFields = createPostSchema.safeParse(rawData);\n  \n  if (!validatedFields.success) {\n    return {\n      errors: validatedFields.error.flatten().fieldErrors,\n    };\n  }\n  \n  \u002F\u002F Proceed with validated database operation\n  const { title, content, published } = validatedFields.data;\n  \u002F\u002F ...\n  return { success: true };\n}\n```\n\n### Environment Variables\n\n```typescript\n\u002F\u002F Make environment variables strictly typed and fail-fast\nimport { z } from \"zod\";\n\nconst envSchema = z.object({\n  DATABASE_URL: z.string().url(),\n  NODE_ENV: z.enum([\"development\", \"test\", \"production\"]).default(\"development\"),\n  PORT: z.coerce.number().default(3000),\n  API_KEY: z.string().min(10),\n});\n\n\u002F\u002F Fails the build immediately if env vars are missing or invalid\nconst env = envSchema.parse(process.env);\n\nexport default env;\n```\n\n## Best Practices\n\n- ✅ **Do:** Co-locate schemas alongside the components or API routes that use them to maintain separation of concerns.\n- ✅ **Do:** Use `z.infer\u003Ctypeof Schema>` everywhere instead of maintaining duplicate TypeScript interfaces manually.\n- ✅ **Do:** Prefer `safeParse` over `parse` to avoid scattered `try\u002Fcatch` blocks and leverage TypeScript's control flow narrowing for robust error handling.\n- ✅ **Do:** Use `z.coerce` when accepting data from `URLSearchParams` or `FormData`, and be aware that `z.coerce.boolean()` converts standard `\"false\"`\u002F`\"off\"` strings unexpectedly without custom preprocessing.\n- ✅ **Do:** Use `.flatten()` or `.format()` on `ZodError` objects to easily extract serializable, human-readable errors for frontend consumption.\n- ❌ **Don't:** Rely exclusively on `.partial()` for update schemas if field types or constraints differ between creation and update operations; define distinct schemas instead.\n- ❌ **Don't:** Forget to pass the `path` option in `.refine()` or `.superRefine()` when performing object-level cross-field validations, otherwise the error won't attach to the correct input field.\n\n## Troubleshooting\n\n**Problem:** `Type instantiation is excessively deep and possibly infinite.`\n**Solution:** This occurs with extreme schema recursion (e.g. deeply nested self-referential schemas). Use `z.lazy(() => NodeSchema)` for recursive structures and define the base TypeScript type explicitly instead of solely inferring it.\n\n**Problem:** Empty strings pass validation when using `.optional()`.\n**Solution:** `.optional()` permits `undefined`, not empty strings. If an empty string means \"no value,\" use `.or(z.literal(\"\"))` or preprocess it: `z.string().transform(v => v === \"\" ? undefined : v).optional()`.\n",{"name":5,"risk":24,"source":25,"date_added":26,"description":7},"safe","community","2026-03-05","main","4e647b68aabe849e143b6950971c380f7adccdef","components\u002Fskills\u002Fweb-development\u002Fzod-validation-expert","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code","https:\u002F\u002Frocketlauncher.ai\u002Fclaude-code","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens","CEO of Rocketlauncher.ai\r\n\r\nObsessed with AI\r\n\r\njoin  https:\u002F\u002Fwww.skool.com\u002Frocketlauncher-university\r\n👉🏻 it's free ","2026-10-13 00:52:14",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add marnixGeerkens\u002Frocketlauncher-claude-code --skill zod-validation-expert",{"tool":41,"command":42},"bunx","bunx skills add marnixGeerkens\u002Frocketlauncher-claude-code --skill zod-validation-expert",{"tool":44,"command":45},"pnpm","pnpm dlx skills add marnixGeerkens\u002Frocketlauncher-claude-code --skill zod-validation-expert","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fweb-development\u002Fzod-validation-expert\u002FSKILL.md",true,[],[50,57,66,73,80,87],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7EQFDF4T3K89WMFVFQVT3C8","zapier-make-patterns","No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points.  This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fzapier-make-patterns\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":62,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7EQFA5XQ0811Q4Q0WCFASZG","yeet","Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","Apache-2.0","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7EQF4J6C2WKQWD9E2RQC6MJ","workflow-automation","Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off.  This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation.  Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fworkflow-automation\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7EQF1AT655CYYZBEQ8V6Z9D","trigger-dev","Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task.","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Ftrigger-dev\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7EQEY9ENH0G2EJ1WD6C1CE8","slack-automation","Automate Slack workspace operations including messaging, search, channel management, and reaction workflows through Composio's Slack toolkit.","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Fslack-automation\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7EQESHEKPTE0QPW9R6XV5K2","rote","Compile a proven agent skill (a SKILL.md plus references) into a deterministic pipeline that runs without an LLM in the loop, then serve it back to Claude as an MCP tool. Use when: rote, compile this skill, turn this skill into a workflow, make this skill deterministic, make this skill cheaper or faster, harden this skill for production, run this skill as a background job.","https:\u002F\u002Fgithub.com\u002FmarnixGeerkens\u002Frocketlauncher-claude-code\u002Fblob\u002Fmain\u002Fcomponents\u002Fskills\u002Fworkflow-automation\u002Frote\u002FSKILL.md",[],[]]