[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77VDBZA2JVJF2HMJK7P0CAN":3,"skill-same:01M77VDBZA2JVJF2HMJK7P0CAN":67},{"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":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M77VDBZA2JVJF2HMJK7P0CAN","prisma-postgres-setup",null,"Set up a new Prisma Postgres database and connect it to a local project using the Management API. Use when asked to \"set up a database\", \"create a Prisma Postgres project\", \"get a connection string\", \"connect my app to Prisma Postgres\", or \"provision a database\".","Reihantt6\u002Fsns-myagent","Reihantt6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F219822095?v=4","01M77KK94PV8B7C2D9XWXNS8DJ","Mohamad Reihan tegar prasetya","01M77KK958QFMTHYXGXFV7KZ79",2,"MIT","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fprisma-postgres-setup\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Set up a new Prisma Postgres database and connect it to a local project using the Management API. Use when asked to \\\"set up a database\\\", \\\"create a Prisma Postgres project\\\", \\\"get a connection string\\\", \\\"connect my app to Prisma Postgres\\\", or \\\"provision a database\\\".\"\nlicense: \"MIT\"\nmetadata: {\"author\":\"prisma\",\"version\":\"1.1.0\"}\n---\n# Prisma Postgres Setup\n\nProcedural skill that guides you through provisioning a new Prisma Postgres database via the Management API and connecting it to a local project.\n\n## When to Apply\n\nUse this skill when:\n\n- Setting up a new Prisma Postgres database for a project\n- Creating a Prisma Postgres project and connecting it locally\n- Obtaining a connection string for Prisma Postgres\n- Provisioning a database via the Management API (not the Console UI)\n\nDo **not** use this skill when:\n\n- Setting up CI\u002FCD preview databases — use `prisma-postgres-cicd`\n- Building multi-tenant database provisioning into an app — use `prisma-postgres-integrator`\n- Working with a database that already exists and is connected (schema\u002Fmigration tasks are standard Prisma CLI)\n\n## Prerequisites\n\n- Node.js 18+\n- A Prisma Postgres workspace (create one at https:\u002F\u002Fconsole.prisma.io if needed)\n- A workspace service token (see `references\u002Fauth.md`)\n\n## UX Guidelines\n\nWhen presenting choices to the user (region selection, project deletion, etc.), **use your platform's interactive selection mechanism** (e.g., `ask` tool in Claude Code, structured prompts in other agents). Do not print static tables and ask the user to type a value — present selectable options so the user can pick with minimal effort.\n\n## Workflow\n\nFollow these steps in order. Each step includes the API call to make and how to handle the response.\n\n### Step 1: Authenticate\n\nYou need a service token. Try these methods in order:\n\n**1a. Token in the user's prompt**\n\nCheck if the user included a service token in their initial message (e.g., \"Set up Prisma Postgres with token eyJ...\"). If so, use it **exactly as provided** — do not truncate, re-encode, or round-trip it through a file. Store it in a shell variable for subsequent calls.\n\n**1b. Token in the environment**\n\nCheck for `PRISMA_SERVICE_TOKEN` in the environment or `.env` file.\n\n**1c. Ask the user to create one**\n\nIf no token is available, instruct the user:\n\n> Create a service token in Prisma Console → Workspace Settings → Service Tokens.\n> Copy the token and paste it here.\n\nRead `references\u002Fauth.md` for details on service token creation.\n\nOnce you have a token, store it in a shell variable (`PRISMA_SERVICE_TOKEN`) and use it for all subsequent API calls.\n\n### Step 2: List available regions\n\nFetch the list of available Prisma Postgres regions to let the user choose where to deploy.\n\n```bash\ncurl -s -H \"Authorization: Bearer $PRISMA_SERVICE_TOKEN\" \\\n  https:\u002F\u002Fapi.prisma.io\u002Fv1\u002Fregions\u002Fpostgres\n```\n\nThe response contains an array of regions with `id`, `name`, and `status`. Only present regions where `status` is `available`.\n\n**Present the regions as an interactive menu** — let the user pick from options rather than typing a region ID manually.\n\nRead `references\u002Fendpoints.md` for the full response shape.\n\n### Step 3: Create a project with a database\n\n```bash\ncurl -s -X POST https:\u002F\u002Fapi.prisma.io\u002Fv1\u002Fprojects \\\n  -H \"Authorization: Bearer $PRISMA_SERVICE_TOKEN\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"name\": \"\u003Cproject-name>\",\n    \"region\": \"\u003Cregion-id>\",\n    \"createDatabase\": true\n  }'\n```\n\nUse the current directory name as the project name by default.\n\nThe response is wrapped in `{ \"data\": { ... } }`. Extract:\n\n- `data.id` — the project ID (prefixed with `proj_`)\n- `data.database.id` — the database ID (prefixed with `db_`)\n- `data.database.connections[0].endpoints.direct.connectionString` — the direct PostgreSQL connection string\n\nUse the **direct** connection string (`endpoints.direct.connectionString`). Do not use the pooled or accelerate endpoints — those are for legacy Accelerate setups and not needed for new projects.\n\nIf the response status is `provisioning`, wait a few seconds and poll `GET \u002Fv1\u002Fdatabases\u002F\u003Cdatabase-id>` until `status` is `ready`.\n\n**If creation fails due to a database limit**, list the user's existing projects and present them as an interactive menu for deletion. After the user picks one, delete it and retry.\n\nRead `references\u002Fendpoints.md` for the full request\u002Fresponse shapes.\n\n### Step 4: Create a named connection (optional)\n\nIf you need a dedicated connection (e.g., per-developer or per-environment), create one:\n\n```bash\ncurl -s -X POST https:\u002F\u002Fapi.prisma.io\u002Fv1\u002Fdatabases\u002F\u003Cdatabase-id>\u002Fconnections \\\n  -H \"Authorization: Bearer $PRISMA_SERVICE_TOKEN\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{ \"name\": \"dev\" }'\n```\n\nExtract the direct connection string from `data.endpoints.direct.connectionString`.\n\n### Step 5: Configure the local project\n\n1. Install dependencies:\n\n```bash\nnpm install prisma @prisma\u002Fclient @prisma\u002Fadapter-pg pg dotenv\n```\n\nAll five packages are required:\n- `prisma` — CLI for migrations, schema push, client generation\n- `@prisma\u002Fclient` — the generated query client\n- `@prisma\u002Fadapter-pg` — Prisma 7 driver adapter for direct PostgreSQL connections\n- `pg` — Node.js PostgreSQL driver (used by the adapter)\n- `dotenv` — loads `.env` variables for `prisma.config.ts`\n\n2. Write the direct connection string to `.env`. **Append** to the file if it already exists — do not overwrite existing entries:\n\n```\nDATABASE_URL=\"\u003Cdirect-connection-string>\"\n```\n\n3. Verify `.gitignore` includes `.env`. Create `.gitignore` if it does not exist. Warn the user if `.env` is not gitignored.\n\n4. Ensure `package.json` has `\"type\": \"module\"` set (Prisma 7 generates ESM output).\n\n5. If `prisma\u002Fschema.prisma` does not exist, run `npx prisma init` to scaffold the project. This creates both `prisma\u002Fschema.prisma` and `prisma.config.ts`.\n\n6. Ensure `schema.prisma` has the `postgresql` provider and **no** `url` or `directUrl` in the datasource block (Prisma 7 manages connection URLs in `prisma.config.ts`, not in the schema):\n\n```prisma\ndatasource db {\n  provider = \"postgresql\"\n}\n```\n\n7. Ensure `prisma.config.ts` loads the connection URL from the environment:\n\n```typescript\nimport path from 'node:path'\nimport { defineConfig } from 'prisma\u002Fconfig'\nimport 'dotenv\u002Fconfig'\n\nexport default defineConfig({\n  earlyAccess: true,\n  schema: path.join(import.meta.dirname, 'prisma', 'schema.prisma'),\n  datasource: {\n    url: process.env.DATABASE_URL!,\n  },\n})\n```\n\n**Important Prisma 7 notes:**\n- Connection URLs go in `prisma.config.ts`, never in `schema.prisma`\n- The provider in `schema.prisma` must be `\"postgresql\"` (not `\"prismaPostgres\"`)\n- `dotenv\u002Fconfig` must be imported in `prisma.config.ts` to load `.env` variables\n\n### Step 6: Define schema and push\n\nIf the schema already has models, skip to pushing. Otherwise, **present these options as an interactive menu**:\n\n1. **\"I'll define my schema manually\"** — Tell the user to edit `prisma\u002Fschema.prisma` and come back when ready. Wait for them before proceeding.\n2. **\"Give me a starter schema\"** — Add a Blog starter schema (User, Post, Comment with relations) to `prisma\u002Fschema.prisma`. Show the user what was added and ask if they want to adjust it before pushing.\n3. **\"I'll describe what I need\"** — Ask the user to describe their data model in natural language (e.g., \"I'm building a task manager with projects, tasks, and team members\"). Generate a schema from the description, show it, and ask for confirmation before pushing.\n\nOnce the schema has models and the user is ready, create a migration and generate the client:\n\n```bash\nnpx prisma migrate dev --name init\n```\n\nThis creates migration files in `prisma\u002Fmigrations\u002F` **and** generates the client in one step. Migration history is essential for CI\u002FCD workflows (`prisma migrate deploy`) and production deployments.\n\nOnly use `npx prisma db push` if the user explicitly asks for prototyping-only mode (no migration history). In that case, follow it with `npx prisma generate`.\n\n### Step 7: Verify the connection\n\nAfter generating the client, create and run a quick verification script to confirm everything works end-to-end. This is **critical** — do not skip this step.\n\nCreate a file named `test-connection.ts`:\n\n```typescript\nimport 'dotenv\u002Fconfig'\nimport pg from 'pg'\nimport { PrismaPg } from '@prisma\u002Fadapter-pg'\nimport { PrismaClient } from '.\u002Fgenerated\u002Fprisma\u002Fclient.js'\n\nconst pool = new pg.Pool({ connectionString: process.env.DATABASE_URL })\nconst adapter = new PrismaPg(pool)\nconst prisma = new PrismaClient({ adapter })\n\nconst result = await prisma.$queryRawUnsafe('SELECT 1 as connected')\nconsole.log('Connected to Prisma Postgres:', result)\n\nawait prisma.$disconnect()\nawait pool.end()\n```\n\nRun it:\n\n```bash\nnpx tsx test-connection.ts\n```\n\n**Prisma 7 client instantiation rules:**\n- Import from `.\u002Fgenerated\u002Fprisma\u002Fclient.js` (not `.\u002Fgenerated\u002Fprisma`)\n- Create a `pg.Pool` with the `DATABASE_URL` connection string\n- Wrap it in a `PrismaPg` adapter\n- Pass `{ adapter }` to the `PrismaClient` constructor\n- Do **not** use `datasourceUrl` — that option does not exist in Prisma 7\n- Do **not** use `new PrismaClient()` with no arguments — it will throw\n\nAfter verification succeeds, delete `test-connection.ts`.\n\nThen share links for the user to explore their database:\n\n- **Prisma Studio (CLI):** `npx prisma studio` — opens a visual data browser locally\n- **Console:** `https:\u002F\u002Fconsole.prisma.io\u002F\u003CworkspaceId>\u002F\u003CprojectId>\u002F\u003CdatabaseId>\u002Fdashboard` — strip the prefixes (`wksp_`, `proj_`, `db_`) from the IDs returned in Step 3 to build this URL\n\nRead `references\u002Fprisma7-client.md` for the full client instantiation reference.\n\n## Error Handling\n\nRead `references\u002Fapi-basics.md` for the full error reference. Key self-correction patterns:\n\n| HTTP Status | Error Code | Action |\n|---|---|---|\n| 401 | `authentication-failed` | Service token is invalid or expired. Ask the user to create a new one in Console → Workspace Settings → Service Tokens. |\n| 404 | `resource-not-found` | Check that the resource ID includes the correct prefix (`proj_`, `db_`, `con_`). |\n| 422 | `validation-error` | Check request body against the endpoint schema. Common: missing `name`, invalid `region`. |\n| 429 | `rate-limit-exceeded` | Back off and retry after a few seconds. |\n\n## Reference Files\n\nDetailed API and usage information is in:\n\n```\nreferences\u002Fauth.md             — Service token creation and usage\nreferences\u002Fapi-basics.md       — Base URL, envelope, IDs, errors, pagination\nreferences\u002Fendpoints.md        — Endpoint details for projects, databases, connections, regions\nreferences\u002Fprisma7-client.md   — Prisma 7 client instantiation and usage patterns\n```\n","# Prisma Postgres Setup\n\nProcedural skill that guides you through provisioning a new Prisma Postgres database via the Management API and connecting it to a local project.\n\n## When to Apply\n\nUse this skill when:\n\n- Setting up a new Prisma Postgres database for a project\n- Creating a Prisma Postgres project and connecting it locally\n- Obtaining a connection string for Prisma Postgres\n- Provisioning a database via the Management API (not the Console UI)\n\nDo **not** use this skill when:\n\n- Setting up CI\u002FCD preview databases — use `prisma-postgres-cicd`\n- Building multi-tenant database provisioning into an app — use `prisma-postgres-integrator`\n- Working with a database that already exists and is connected (schema\u002Fmigration tasks are standard Prisma CLI)\n\n## Prerequisites\n\n- Node.js 18+\n- A Prisma Postgres workspace (create one at https:\u002F\u002Fconsole.prisma.io if needed)\n- A workspace service token (see `references\u002Fauth.md`)\n\n## UX Guidelines\n\nWhen presenting choices to the user (region selection, project deletion, etc.), **use your platform's interactive selection mechanism** (e.g., `ask` tool in Claude Code, structured prompts in other agents). Do not print static tables and ask the user to type a value — present selectable options so the user can pick with minimal effort.\n\n## Workflow\n\nFollow these steps in order. Each step includes the API call to make and how to handle the response.\n\n### Step 1: Authenticate\n\nYou need a service token. Try these methods in order:\n\n**1a. Token in the user's prompt**\n\nCheck if the user included a service token in their initial message (e.g., \"Set up Prisma Postgres with token eyJ...\"). If so, use it **exactly as provided** — do not truncate, re-encode, or round-trip it through a file. Store it in a shell variable for subsequent calls.\n\n**1b. Token in the environment**\n\nCheck for `PRISMA_SERVICE_TOKEN` in the environment or `.env` file.\n\n**1c. Ask the user to create one**\n\nIf no token is available, instruct the user:\n\n> Create a service token in Prisma Console → Workspace Settings → Service Tokens.\n> Copy the token and paste it here.\n\nRead `references\u002Fauth.md` for details on service token creation.\n\nOnce you have a token, store it in a shell variable (`PRISMA_SERVICE_TOKEN`) and use it for all subsequent API calls.\n\n### Step 2: List available regions\n\nFetch the list of available Prisma Postgres regions to let the user choose where to deploy.\n\n```bash\ncurl -s -H \"Authorization: Bearer $PRISMA_SERVICE_TOKEN\" \\\n  https:\u002F\u002Fapi.prisma.io\u002Fv1\u002Fregions\u002Fpostgres\n```\n\nThe response contains an array of regions with `id`, `name`, and `status`. Only present regions where `status` is `available`.\n\n**Present the regions as an interactive menu** — let the user pick from options rather than typing a region ID manually.\n\nRead `references\u002Fendpoints.md` for the full response shape.\n\n### Step 3: Create a project with a database\n\n```bash\ncurl -s -X POST https:\u002F\u002Fapi.prisma.io\u002Fv1\u002Fprojects \\\n  -H \"Authorization: Bearer $PRISMA_SERVICE_TOKEN\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"name\": \"\u003Cproject-name>\",\n    \"region\": \"\u003Cregion-id>\",\n    \"createDatabase\": true\n  }'\n```\n\nUse the current directory name as the project name by default.\n\nThe response is wrapped in `{ \"data\": { ... } }`. Extract:\n\n- `data.id` — the project ID (prefixed with `proj_`)\n- `data.database.id` — the database ID (prefixed with `db_`)\n- `data.database.connections[0].endpoints.direct.connectionString` — the direct PostgreSQL connection string\n\nUse the **direct** connection string (`endpoints.direct.connectionString`). Do not use the pooled or accelerate endpoints — those are for legacy Accelerate setups and not needed for new projects.\n\nIf the response status is `provisioning`, wait a few seconds and poll `GET \u002Fv1\u002Fdatabases\u002F\u003Cdatabase-id>` until `status` is `ready`.\n\n**If creation fails due to a database limit**, list the user's existing projects and present them as an interactive menu for deletion. After the user picks one, delete it and retry.\n\nRead `references\u002Fendpoints.md` for the full request\u002Fresponse shapes.\n\n### Step 4: Create a named connection (optional)\n\nIf you need a dedicated connection (e.g., per-developer or per-environment), create one:\n\n```bash\ncurl -s -X POST https:\u002F\u002Fapi.prisma.io\u002Fv1\u002Fdatabases\u002F\u003Cdatabase-id>\u002Fconnections \\\n  -H \"Authorization: Bearer $PRISMA_SERVICE_TOKEN\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{ \"name\": \"dev\" }'\n```\n\nExtract the direct connection string from `data.endpoints.direct.connectionString`.\n\n### Step 5: Configure the local project\n\n1. Install dependencies:\n\n```bash\nnpm install prisma @prisma\u002Fclient @prisma\u002Fadapter-pg pg dotenv\n```\n\nAll five packages are required:\n- `prisma` — CLI for migrations, schema push, client generation\n- `@prisma\u002Fclient` — the generated query client\n- `@prisma\u002Fadapter-pg` — Prisma 7 driver adapter for direct PostgreSQL connections\n- `pg` — Node.js PostgreSQL driver (used by the adapter)\n- `dotenv` — loads `.env` variables for `prisma.config.ts`\n\n2. Write the direct connection string to `.env`. **Append** to the file if it already exists — do not overwrite existing entries:\n\n```\nDATABASE_URL=\"\u003Cdirect-connection-string>\"\n```\n\n3. Verify `.gitignore` includes `.env`. Create `.gitignore` if it does not exist. Warn the user if `.env` is not gitignored.\n\n4. Ensure `package.json` has `\"type\": \"module\"` set (Prisma 7 generates ESM output).\n\n5. If `prisma\u002Fschema.prisma` does not exist, run `npx prisma init` to scaffold the project. This creates both `prisma\u002Fschema.prisma` and `prisma.config.ts`.\n\n6. Ensure `schema.prisma` has the `postgresql` provider and **no** `url` or `directUrl` in the datasource block (Prisma 7 manages connection URLs in `prisma.config.ts`, not in the schema):\n\n```prisma\ndatasource db {\n  provider = \"postgresql\"\n}\n```\n\n7. Ensure `prisma.config.ts` loads the connection URL from the environment:\n\n```typescript\nimport path from 'node:path'\nimport { defineConfig } from 'prisma\u002Fconfig'\nimport 'dotenv\u002Fconfig'\n\nexport default defineConfig({\n  earlyAccess: true,\n  schema: path.join(import.meta.dirname, 'prisma', 'schema.prisma'),\n  datasource: {\n    url: process.env.DATABASE_URL!,\n  },\n})\n```\n\n**Important Prisma 7 notes:**\n- Connection URLs go in `prisma.config.ts`, never in `schema.prisma`\n- The provider in `schema.prisma` must be `\"postgresql\"` (not `\"prismaPostgres\"`)\n- `dotenv\u002Fconfig` must be imported in `prisma.config.ts` to load `.env` variables\n\n### Step 6: Define schema and push\n\nIf the schema already has models, skip to pushing. Otherwise, **present these options as an interactive menu**:\n\n1. **\"I'll define my schema manually\"** — Tell the user to edit `prisma\u002Fschema.prisma` and come back when ready. Wait for them before proceeding.\n2. **\"Give me a starter schema\"** — Add a Blog starter schema (User, Post, Comment with relations) to `prisma\u002Fschema.prisma`. Show the user what was added and ask if they want to adjust it before pushing.\n3. **\"I'll describe what I need\"** — Ask the user to describe their data model in natural language (e.g., \"I'm building a task manager with projects, tasks, and team members\"). Generate a schema from the description, show it, and ask for confirmation before pushing.\n\nOnce the schema has models and the user is ready, create a migration and generate the client:\n\n```bash\nnpx prisma migrate dev --name init\n```\n\nThis creates migration files in `prisma\u002Fmigrations\u002F` **and** generates the client in one step. Migration history is essential for CI\u002FCD workflows (`prisma migrate deploy`) and production deployments.\n\nOnly use `npx prisma db push` if the user explicitly asks for prototyping-only mode (no migration history). In that case, follow it with `npx prisma generate`.\n\n### Step 7: Verify the connection\n\nAfter generating the client, create and run a quick verification script to confirm everything works end-to-end. This is **critical** — do not skip this step.\n\nCreate a file named `test-connection.ts`:\n\n```typescript\nimport 'dotenv\u002Fconfig'\nimport pg from 'pg'\nimport { PrismaPg } from '@prisma\u002Fadapter-pg'\nimport { PrismaClient } from '.\u002Fgenerated\u002Fprisma\u002Fclient.js'\n\nconst pool = new pg.Pool({ connectionString: process.env.DATABASE_URL })\nconst adapter = new PrismaPg(pool)\nconst prisma = new PrismaClient({ adapter })\n\nconst result = await prisma.$queryRawUnsafe('SELECT 1 as connected')\nconsole.log('Connected to Prisma Postgres:', result)\n\nawait prisma.$disconnect()\nawait pool.end()\n```\n\nRun it:\n\n```bash\nnpx tsx test-connection.ts\n```\n\n**Prisma 7 client instantiation rules:**\n- Import from `.\u002Fgenerated\u002Fprisma\u002Fclient.js` (not `.\u002Fgenerated\u002Fprisma`)\n- Create a `pg.Pool` with the `DATABASE_URL` connection string\n- Wrap it in a `PrismaPg` adapter\n- Pass `{ adapter }` to the `PrismaClient` constructor\n- Do **not** use `datasourceUrl` — that option does not exist in Prisma 7\n- Do **not** use `new PrismaClient()` with no arguments — it will throw\n\nAfter verification succeeds, delete `test-connection.ts`.\n\nThen share links for the user to explore their database:\n\n- **Prisma Studio (CLI):** `npx prisma studio` — opens a visual data browser locally\n- **Console:** `https:\u002F\u002Fconsole.prisma.io\u002F\u003CworkspaceId>\u002F\u003CprojectId>\u002F\u003CdatabaseId>\u002Fdashboard` — strip the prefixes (`wksp_`, `proj_`, `db_`) from the IDs returned in Step 3 to build this URL\n\nRead `references\u002Fprisma7-client.md` for the full client instantiation reference.\n\n## Error Handling\n\nRead `references\u002Fapi-basics.md` for the full error reference. Key self-correction patterns:\n\n| HTTP Status | Error Code | Action |\n|---|---|---|\n| 401 | `authentication-failed` | Service token is invalid or expired. Ask the user to create a new one in Console → Workspace Settings → Service Tokens. |\n| 404 | `resource-not-found` | Check that the resource ID includes the correct prefix (`proj_`, `db_`, `con_`). |\n| 422 | `validation-error` | Check request body against the endpoint schema. Common: missing `name`, invalid `region`. |\n| 429 | `rate-limit-exceeded` | Back off and retry after a few seconds. |\n\n## Reference Files\n\nDetailed API and usage information is in:\n\n```\nreferences\u002Fauth.md             — Service token creation and usage\nreferences\u002Fapi-basics.md       — Base URL, envelope, IDs, errors, pagination\nreferences\u002Fendpoints.md        — Endpoint details for projects, databases, connections, regions\nreferences\u002Fprisma7-client.md   — Prisma 7 client instantiation and usage patterns\n```\n",{"license":15,"metadata":24,"description":7},{"author":25,"version":26},"prisma","1.1.0","main","58843b159d7a4050d6b785a98b908cce505c0b92","agent\u002Fskills\u002Fprisma-postgres-setup",0,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent","https:\u002F\u002Fgithub.com\u002FReihantt6","reihsns.web.id","2026-08-19 20:08:18",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add Reihantt6\u002Fsns-myagent --skill prisma-postgres-setup",{"tool":41,"command":42},"bunx","bunx skills add Reihantt6\u002Fsns-myagent --skill prisma-postgres-setup",{"tool":44,"command":45},"pnpm","pnpm dlx skills add Reihantt6\u002Fsns-myagent --skill prisma-postgres-setup","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fprisma-postgres-setup\u002FSKILL.md",true,[49,55,59,63],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fapi-basics.md","REFERENCE","参考文档",2582,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fprisma-postgres-setup\u002Freferences\u002Fapi-basics.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fauth.md",1521,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fprisma-postgres-setup\u002Freferences\u002Fauth.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fendpoints.md",4927,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fprisma-postgres-setup\u002Freferences\u002Fendpoints.md",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fprisma7-client.md",2690,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fprisma-postgres-setup\u002Freferences\u002Fprisma7-client.md",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M77XDCYZ407XYMF2T4P6F7VT","youtube-transcript","Extract transcripts from YouTube videos. Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com\u002Fwatch?v=, youtu.be\u002F, or similar). Supports output with or without timestamps.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-transcript\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M77XD7PBC98J6MXGJJ2TJ8DX","youtube-thumbnail-design","YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A\u002FB testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-thumbnail-design\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M77XD2541C8HXJ6RHYZP4NGJ","youtube-short-maker","Make YouTube Shorts that hold attention with Pexo — vertical 9:16, fast-paced, hook in the first 3 seconds. Describe your topic and Pexo writes the script, generates the shots, picks the models, and assembles a finished Short with music and captions. Use for YouTube Shorts: \"youtube short\", \"make a youtube short\", \"shorts video\", \"short-form video\". NOT for long-form or landscape video.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-short-maker\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M77XCXKVSYK7KTZ3PQBVVGFD","xcode-project-setup","Safely modifies Xcode projects (.pbxproj) to add Swift Packages and link files. Use this skill whenever an iOS project needs dependencies installed (e.g. Firebase, Alamofire).","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fxcode-project-setup\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M77XCR1DV8ZQK2NHWKVY4EWX","x402","Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — \"just use it\" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing touches your codebase) or \"build it in\" (install the SDK and write the key + code into your project). Walks through wallet setup, funding, .env, and a ~$1 test run. Use when the user asks about x402, pay-per-use, USDC payments, or wants Browser Use Cloud without an API key. For the free-tier signup (reverse-CAPTCHA → API key), use `browser-use cloud signup` or the `cloud` skill instead.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fx402\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M77XCMD3R3ZBZQQSW6E0793B","x-twitter-scraper","Build GitHub Copilot workflows with Xquik X API SDKs, REST endpoints, hosted Apify Actor runs, MCP tools, TweetClaw OpenClaw plugin installs, signed webhooks, tweet search, user lookup, follower exports, media actions, and agent automation.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fx-twitter-scraper\u002FSKILL.md",[],[]]