[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AXQ2MBAV7AMGKJ8Q4DFSHQ":3,"skill-same:01M7AXQ2MBAV7AMGKJ8Q4DFSHQ":73},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":13,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7AXQ2MBAV7AMGKJ8Q4DFSHQ","clerk-backend-api",null,"Clerk Backend REST API explorer and executor. Browse tags, inspect endpoint schemas, and execute authenticated requests. Use when listing users, managing organizations, or calling any Clerk API endpoint.","Krishp091205\u002Fgemini-config","Krishp091205","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F307182548?v=4","01M7AXCYY4NQ9WQ7DCT3R5Q5S4","01M7AXCYYR7QFCQQ6BFRKD93YH",0,"MIT","https:\u002F\u002Fgithub.com\u002FKrishp091205\u002Fgemini-config\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclerk-backend-api\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: clerk-backend-api\ndescription: \"Clerk Backend REST API explorer and executor. Browse tags, inspect endpoint schemas, and execute authenticated requests. Use when listing users, managing organizations, or calling any Clerk API endpoint.\"\nallowed-tools: Bash, Read, Grep, Skill, WebFetch\nlicense: MIT\ncompatibility: Requires CLERK_SECRET_KEY (sk_*) for Backend API calls.\n---\n\n## Options context\n\nUser Prompt: $ARGUMENTS\n\n## CRITICAL: Mandatory checks before EVERY write request\n\nBefore ANY POST \u002F PATCH \u002F PUT \u002F DELETE, you MUST do ALL of the following in your response:\n\n1. **Check CLERK_SECRET_KEY** — verify it is set:\n   ```bash\n   echo $CLERK_SECRET_KEY | head -c 10\n   ```\n   If empty, stop and ask the user. Do not proceed without a valid key.\n\n2. **Check CLERK_BAPI_SCOPES** — run:\n   ```bash\n   echo $CLERK_BAPI_SCOPES\n   ```\n   Inspect the output. If scopes are missing or do not include the required write permission, tell the user: *\"This is a write operation and your current scopes may not allow it. Rerun with --admin to bypass?\"* Do NOT attempt the request and fail — ask first.\n\n3. **For DELETE requests:** warn explicitly that the action is **IRREVERSIBLE** and list exactly what data will be permanently destroyed (user record, all sessions, all memberships, all associated data). Require explicit confirmation before proceeding. This warning is MANDATORY — never skip it.\n\n4. **For metadata operations:** always explain which metadata type is being used and why (see Metadata types section below).\n\n---\n\n## FAST PATH: Common operations (use directly, no spec fetching needed)\n\nFor the operations below, skip spec fetching and execute immediately using these exact templates. Substitute `$CLERK_SECRET_KEY`, `$USER_ID`, `$ORG_ID`, `$EMAIL` as needed from the user's context.\n\n### Create organization + invite member (two-step)\n\n```bash\n# Step 1 — Create organization\nORG=$(curl -s -X POST \"https:\u002F\u002Fapi.clerk.com\u002Fv1\u002Forganizations\" \\\n  -H \"Authorization: Bearer $CLERK_SECRET_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"{\\\"name\\\": \\\"Acme Corp\\\", \\\"created_by\\\": \\\"$USER_ID\\\"}\")\necho \"$ORG\" | python3 -c \"import sys,json; d=json.load(sys.stdin); print(json.dumps(d, indent=2))\"\n\n# Step 2 — Extract org ID\nORG_ID=$(echo \"$ORG\" | python3 -c \"import sys,json; print(json.load(sys.stdin)['id'])\")\n\n# Step 3 — Invite member with role\ncurl -s -X POST \"https:\u002F\u002Fapi.clerk.com\u002Fv1\u002Forganizations\u002F${ORG_ID}\u002Finvitations\" \\\n  -H \"Authorization: Bearer $CLERK_SECRET_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"{\\\"email_address\\\": \\\"user@example.com\\\", \\\"role\\\": \\\"org:admin\\\"}\" \\\n  | python3 -c \"import sys,json; print(json.dumps(json.load(sys.stdin), indent=2))\"\n```\n\n**Roles:** use `\"org:admin\"` or `\"org:member\"` (always prefix with `org:`).\n\n### SDK equivalent (for Next.js \u002F TypeScript projects with `@clerk\u002Fnextjs` or `@clerk\u002Fbackend`)\n\n```typescript\nimport { clerkClient } from '@clerk\u002Fnextjs\u002Fserver'\n\u002F\u002F OR if using @clerk\u002Fbackend directly:\n\u002F\u002F import { createClerkClient } from '@clerk\u002Fbackend'\n\u002F\u002F const clerkClient = createClerkClient({ secretKey: process.env.CLERK_SECRET_KEY })\n\n\u002F\u002F Step 1: Create organization\nconst org = await clerkClient.organizations.createOrganization({\n  name: 'Acme Corp',\n  createdBy: userId,  \u002F\u002F required — the ID of the user creating the org\n})\n\n\u002F\u002F Step 2: Invite member to the org\nconst invitation = await clerkClient.organizations.createOrganizationInvitation({\n  organizationId: org.id,\n  emailAddress: 'user@example.com',\n  role: 'org:admin',  \u002F\u002F or 'org:member'\n})\n```\n\n### Update user metadata\n\n**Always explain the three metadata types before asking which to use:**\n\n| Type | Field | Readable by | Writable by | Use for |\n|------|-------|-------------|-------------|---------|\n| Public | `public_metadata` | Client + Server | **Server only** | Plan tier, roles, feature flags the frontend reads |\n| Private | `private_metadata` | **Server only** | **Server only** | Stripe IDs, compliance flags, internal identifiers |\n| Unsafe | `unsafe_metadata` | Client + Server | Client + Server | Ephemeral UI state, onboarding steps (client-writable — avoid sensitive data) |\n\n**For `plan: 'pro'` and `onboarded: true` — use `public_metadata`** (frontend-readable, server-writable):\n\n```bash\ncurl -s -X PATCH \"https:\u002F\u002Fapi.clerk.com\u002Fv1\u002Fusers\u002F${USER_ID}\" \\\n  -H \"Authorization: Bearer $CLERK_SECRET_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"public_metadata\": {\"plan\": \"pro\", \"onboarded\": true}}' \\\n  | python3 -c \"import sys,json; d=json.load(sys.stdin); print(f'Updated user {d[\\\"id\\\"]}: public_metadata={d.get(\\\"public_metadata\\\")}')\"\n```\n\n**SDK equivalent:**\n\n```typescript\nimport { clerkClient } from '@clerk\u002Fnextjs\u002Fserver'\n\u002F\u002F OR: import { createClerkClient } from '@clerk\u002Fbackend'\n\nawait clerkClient.users.updateUser(userId, {\n  publicMetadata: { plan: 'pro', onboarded: true },   \u002F\u002F readable by client, writable server-only\n  \u002F\u002F privateMetadata: { stripeId: 'cus_xxx' },         \u002F\u002F server-only read AND write\n  \u002F\u002F unsafeMetadata: { step: 'welcome' },              \u002F\u002F client-writable, avoid sensitive data\n})\n```\n\n**Note:** REST API uses `snake_case` (`public_metadata`). SDK uses `camelCase` (`publicMetadata`).\n\n### List users (last 7 days)\n\n```bash\ncurl -s \"https:\u002F\u002Fapi.clerk.com\u002Fv1\u002Fusers?limit=100&offset=0&order_by=-created_at&created_at=gt:$(date -d '7 days ago' +%s 2>\u002Fdev\u002Fnull || date -v-7d +%s)000\" \\\n  -H \"Authorization: Bearer $CLERK_SECRET_KEY\" \\\n  | python3 -c \"\nimport sys, json\ndata = json.load(sys.stdin)\nif isinstance(data, list):\n    print(f'Found {len(data)} users:')\n    for u in data:\n        print(f'  {u[\\\"id\\\"]}: {u.get(\\\"email_addresses\\\", [{}])[0].get(\\\"email_address\\\", \\\"no email\\\")}')\nelse:\n    print(json.dumps(data, indent=2))\n\"\n```\n\n### Delete user (confirm required)\n\n```bash\n# ONLY run after explicit user confirmation\ncurl -s -X DELETE \"https:\u002F\u002Fapi.clerk.com\u002Fv1\u002Fusers\u002F${USER_ID}\" \\\n  -H \"Authorization: Bearer $CLERK_SECRET_KEY\" \\\n  | python3 -c \"import sys,json; d=json.load(sys.stdin); print(f'Deleted: {d}')\"\n```\n\n---\n\n## Clerk Backend API — Full Endpoint Reference\n\nBase URL: `https:\u002F\u002Fapi.clerk.com\u002Fv1`\nAuth: `Authorization: Bearer $CLERK_SECRET_KEY` on every request.\n\n### Users\n\n**List users**\n```\nGET \u002Fv1\u002Fusers\nQuery params: limit (max 500, default 10), offset, order_by (+\u002F-created_at, +\u002F-updated_at, +\u002F-email_address, +\u002F-web3wallet, +\u002F-first_name, +\u002F-last_name, +\u002F-phone_number, +\u002F-username, +\u002F-last_active_at, +\u002F-last_sign_in_at), email_address[], phone_number[], username[], web3wallet[], user_id[], query, created_at (ISO 8601 range: gt:TIMESTAMP or lt:TIMESTAMP in Unix ms)\nReturns: array of User objects\n```\n\n**Get user**\n```\nGET \u002Fv1\u002Fusers\u002F{user_id}\nReturns: User object\n```\n\n**Update user**\n```\nPATCH \u002Fv1\u002Fusers\u002F{user_id}\nBody (JSON, snake_case): { public_metadata, private_metadata, unsafe_metadata, first_name, last_name, username, ... }\n```\n\n**Delete user — IRREVERSIBLE**\n```\nDELETE \u002Fv1\u002Fusers\u002F{user_id}\nDestroys: user record, all sessions, all memberships, all associated data\nReturns: { id, object, deleted: true }\n```\nAlways warn the user this is permanent and confirm before proceeding.\n\n### Organizations\n\n**Create organization**\n```\nPOST \u002Fv1\u002Forganizations\nBody: { name: string, created_by: string (user_id), public_metadata?, private_metadata?, max_allowed_memberships? }\nReturns: Organization object with { id, name, slug, ... }\n```\n\n**List organizations**\n```\nGET \u002Fv1\u002Forganizations\nQuery params: limit, offset, query, order_by\n```\n\n**Invite member**\n```\nPOST \u002Fv1\u002Forganizations\u002F{organization_id}\u002Finvitations\nBody: { email_address: string, role: string (\"org:admin\" or \"org:member\"), public_metadata?, private_metadata? }\nReturns: OrganizationInvitation object\n```\n\n---\n\n## How to execute requests\n\n**ALWAYS execute requests with direct `curl` commands.** Use the spec-extraction scripts (`api-specs-context.sh`, `extract-tags.js`, `extract-endpoint-detail.sh`) to discover endpoints, but make actual API calls with `curl`. Do NOT use `scripts\u002Fexecute-request.sh` — it's a local dev helper, not for agent use.\n\nTemplate for GET requests:\n```bash\ncurl -s \"https:\u002F\u002Fapi.clerk.com\u002Fv1${PATH}${QUERY_STRING}\" \\\n  -H \"Authorization: Bearer $CLERK_SECRET_KEY\"\n```\n\nTemplate for POST\u002FPATCH requests:\n```bash\ncurl -s -X ${METHOD} \"https:\u002F\u002Fapi.clerk.com\u002Fv1${PATH}\" \\\n  -H \"Authorization: Bearer $CLERK_SECRET_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '${BODY_JSON}'\n```\n\nTemplate for DELETE requests:\n```bash\ncurl -s -X DELETE \"https:\u002F\u002Fapi.clerk.com\u002Fv1${PATH}\" \\\n  -H \"Authorization: Bearer $CLERK_SECRET_KEY\"\n```\n\n**After getting the response:** Parse and display it clearly. Use `python3 -c \"import sys,json; data=json.load(sys.stdin); print(json.dumps(data, indent=2))\"` to pretty-print JSON. Extract key fields (id, email, name, etc.) and summarize them for the user.\n\n---\n\n## API specs context\n\nBefore doing anything outside the FAST PATH, fetch the available spec versions and tags by running:\n```bash\nbash scripts\u002Fapi-specs-context.sh\n```\n\nUse the output to determine the latest version and available tags.\n\n**Caching:** If you already fetched the spec context earlier in this conversation, do NOT fetch it again. Reuse the version and tags from the previous call.\n\n---\n\n## Rules\n\n- For common operations (list users, create org, invite, update metadata, delete user): use the FAST PATH above — do NOT fetch specs first.\n- Always disregard endpoints\u002Fschemas related to `platform`.\n- Always confirm before performing write requests (POST\u002FPUT\u002FPATCH\u002FDELETE).\n- For DELETE operations, always warn the user that the action is **irreversible** and mention what data will be lost (user record, sessions, memberships). This warning is MANDATORY — never skip it.\n- For write operations (POST\u002FPUT\u002FPATCH\u002FDELETE), check `CLERK_BAPI_SCOPES` before attempting the request. If missing or insufficient, ask the user upfront. Do NOT attempt and fail — ask before executing. This check is MANDATORY.\n- For metadata operations, always explain all three types (public, private, unsafe) and recommend the appropriate one.\n- Pagination: always use `limit` + `offset` and mention that results may be paginated for large datasets.\n- Use direct curl commands for all API calls — never use `scripts\u002Fexecute-request.sh`.\n\n---\n\n## Rate Limits & Gotchas\n\n### Rate Limits\n\n| Environment | Limit |\n|-------------|-------|\n| Production | 1,000 requests \u002F 10 seconds |\n| Development | 100 requests \u002F 10 seconds |\n| Single invitations | 100 \u002F hour |\n| Bulk invitations | 25 \u002F hour |\n| Org invitations | 250 \u002F hour |\n| Frontend API sign-in creation | 5 \u002F 10 seconds |\n| Frontend API sign-in attempts | 3 \u002F 10 seconds |\n| List users max per page | 500 |\n\n`currentUser()` makes a real API call that counts against rate limits. Use `auth()` for just the session claims — it reads from the token without an API call.\n\n### Metadata Overwrites (Not Merges)\n\n`updateUser({ publicMetadata: { role: 'admin' } })` REPLACES all public metadata, not merges. To add a field without losing existing data: read first, spread, then write.\n\nWrong:\n```typescript\nawait clerkClient.users.updateUser(userId, { publicMetadata: { newField: 'value' } })\n```\nThis DELETES all other `publicMetadata` fields.\n\nRight:\n```typescript\nconst user = await clerkClient.users.getUser(userId)\nawait clerkClient.users.updateUser(userId, {\n  publicMetadata: { ...user.publicMetadata, newField: 'value' },\n})\n```\n\n---\n\n## Modes\n\nDetermine the active mode based on the user prompt in [Options context](#options-context):\n\n| Mode | Trigger | Behavior |\n|------|---------|----------|\n| `help` | Prompt is empty, or contains only `help` \u002F `-h` \u002F `--help` | Print usage examples (step 0) |\n| `browse` | Prompt is `tags`, or a tag name (e.g. `Users`) | List all tags or endpoints for a tag |\n| `execute` | Specific endpoint (e.g. `GET \u002Fusers`) or natural language action (e.g. \"get user john_doe\") | Look up endpoint, execute request |\n| `detail` | Endpoint + `help` \u002F `-h` \u002F `--help` (e.g. `GET \u002Fusers help`) | Show endpoint schema, don't execute |\n\n---\n\n## Your Task\n\nUse the **LATEST VERSION** from [API specs context](#api-specs-context) by default. If the user specifies a different version (e.g. `--version 2024-10-01`), use that version instead.\n\nDetermine the active mode, then follow the applicable steps below.\n\n---\n\n### 0. Print usage\n\n**Modes:** `help` only — **Skip** for `browse`, `execute`, and `detail`.\n\nPrint the following examples to the user verbatim:\n\n```\nBrowse\n  \u002Fclerk-backend-api tags                         — list all tags\n  \u002Fclerk-backend-api Users                        — browse endpoints for the Users tag\n  \u002Fclerk-backend-api Users version 2025-11-10.yml — browse using a different version\n\nExecute\n  \u002Fclerk-backend-api GET \u002Fusers             — fetch all users\n  \u002Fclerk-backend-api get user john_doe      — natural language works too\n  \u002Fclerk-backend-api POST \u002Finvitations      — create an invitation\n\nInspect\n  \u002Fclerk-backend-api GET \u002Fusers help        — show endpoint schema without executing\n  \u002Fclerk-backend-api POST \u002Finvitations -h   — view request\u002Fresponse details\n\nOptions\n  --admin                            — bypass scope restrictions for write\u002Fdelete\n  --version [date], version [date]   — use a specific spec version\n  --help, -h, help                   — inspect endpoint instead of executing\n```\n\nStop here.\n\n---\n\n### 1. Fetch tags\n\n**Modes:** `browse` (when prompt is `tags` or no tag specified) — **Skip** for `help`, `execute`, and `detail`.\n\nIf using a non-latest version, fetch tags for that version:\n```bash\ncurl -s https:\u002F\u002Fraw.githubusercontent.com\u002Fclerk\u002Fopenapi-specs\u002Fmain\u002Fbapi\u002F${version_name} | node scripts\u002Fextract-tags.js\n```\nOtherwise, use the **TAGS** already in [API specs context](#api-specs-context).\n\nShare tags in a table and prompt the user to select a query.\n\n---\n\n### 2. Fetch tag endpoints\n\n**Modes:** `browse` (when a tag name is provided) — **Skip** for `help`, `execute`, and `detail`.\n\nFetch all endpoints for the identified tag:\n```bash\ncurl -s https:\u002F\u002Fraw.githubusercontent.com\u002Fclerk\u002Fopenapi-specs\u002Fmain\u002Fbapi\u002F${version_name} | bash scripts\u002Fextract-tag-endpoints.sh \"${tag_name}\"\n```\n\nShare the results (endpoints, schemas, parameters) with the user.\n\n---\n\n### 3. Fetch endpoint detail\n\n**Modes:** `execute`, `detail` — **Skip** for `help` and `browse`.\n\nFor natural language prompts in `execute` mode, first check if the operation matches a FAST PATH entry above. If it does, skip this step and proceed directly to step 4 using the FAST PATH template.\n\nFor other endpoints, identify the matching endpoint by searching the tags in context. Fetch tag endpoints if needed to resolve the exact path and method.\n\nExtract the full endpoint definition:\n```bash\ncurl -s https:\u002F\u002Fraw.githubusercontent.com\u002Fclerk\u002Fopenapi-specs\u002Fmain\u002Fbapi\u002F${version_name} | bash scripts\u002Fextract-endpoint-detail.sh \"${path}\" \"${method}\"\n```\n- `${path}` — e.g. `\u002Fusers\u002F{user_id}`\n- `${method}` — lowercase, e.g. `get`\n\n**`detail` mode:** Share the endpoint definition and schemas with the user. Stop here.\n\n**`execute` mode:** Continue to step 4.\n\n---\n\n### 4. Execute request\n\n**Modes:** `execute` only.\n\n1. Run the **mandatory checks** from the CRITICAL section above.\n2. Identify required and optional parameters from the spec (step 3) or FAST PATH.\n3. Ask the user for any required path\u002Fquery\u002Fbody parameters that weren't provided.\n4. Build and execute a **direct curl command** (see How to execute requests above). Do NOT use `scripts\u002Fexecute-request.sh`.\n5. Parse the JSON response and display it clearly. Extract and summarize key fields for the user.\n\n**Example — list users and parse response:**\n```bash\nRESPONSE=$(curl -s \"https:\u002F\u002Fapi.clerk.com\u002Fv1\u002Fusers?limit=10\" \\\n  -H \"Authorization: Bearer $CLERK_SECRET_KEY\")\necho \"$RESPONSE\" | python3 -c \"\nimport sys, json\ndata = json.load(sys.stdin)\nif isinstance(data, list):\n    print(f'Found {len(data)} users:')\n    for u in data:\n        print(f'  {u[\\\"id\\\"]}: {u.get(\\\"email_addresses\\\", [{}])[0].get(\\\"email_address\\\", \\\"no email\\\")}')\nelse:\n    print(json.dumps(data, indent=2))\n\"\n```\n\n## See Also\n\n- `clerk-setup` - Initial Clerk install\n- `clerk-orgs` - Manage organizations via API\n- `clerk-webhooks` - Real-time event sync\n","## Options context\n\nUser Prompt: $ARGUMENTS\n\n## CRITICAL: Mandatory checks before EVERY write request\n\nBefore ANY POST \u002F PATCH \u002F PUT \u002F DELETE, you MUST do ALL of the following in your response:\n\n1. **Check CLERK_SECRET_KEY** — verify it is set:\n   ```bash\n   echo $CLERK_SECRET_KEY | head -c 10\n   ```\n   If empty, stop and ask the user. Do not proceed without a valid key.\n\n2. **Check CLERK_BAPI_SCOPES** — run:\n   ```bash\n   echo $CLERK_BAPI_SCOPES\n   ```\n   Inspect the output. If scopes are missing or do not include the required write permission, tell the user: *\"This is a write operation and your current scopes may not allow it. Rerun with --admin to bypass?\"* Do NOT attempt the request and fail — ask first.\n\n3. **For DELETE requests:** warn explicitly that the action is **IRREVERSIBLE** and list exactly what data will be permanently destroyed (user record, all sessions, all memberships, all associated data). Require explicit confirmation before proceeding. This warning is MANDATORY — never skip it.\n\n4. **For metadata operations:** always explain which metadata type is being used and why (see Metadata types section below).\n\n---\n\n## FAST PATH: Common operations (use directly, no spec fetching needed)\n\nFor the operations below, skip spec fetching and execute immediately using these exact templates. Substitute `$CLERK_SECRET_KEY`, `$USER_ID`, `$ORG_ID`, `$EMAIL` as needed from the user's context.\n\n### Create organization + invite member (two-step)\n\n```bash\n# Step 1 — Create organization\nORG=$(curl -s -X POST \"https:\u002F\u002Fapi.clerk.com\u002Fv1\u002Forganizations\" \\\n  -H \"Authorization: Bearer $CLERK_SECRET_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"{\\\"name\\\": \\\"Acme Corp\\\", \\\"created_by\\\": \\\"$USER_ID\\\"}\")\necho \"$ORG\" | python3 -c \"import sys,json; d=json.load(sys.stdin); print(json.dumps(d, indent=2))\"\n\n# Step 2 — Extract org ID\nORG_ID=$(echo \"$ORG\" | python3 -c \"import sys,json; print(json.load(sys.stdin)['id'])\")\n\n# Step 3 — Invite member with role\ncurl -s -X POST \"https:\u002F\u002Fapi.clerk.com\u002Fv1\u002Forganizations\u002F${ORG_ID}\u002Finvitations\" \\\n  -H \"Authorization: Bearer $CLERK_SECRET_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"{\\\"email_address\\\": \\\"user@example.com\\\", \\\"role\\\": \\\"org:admin\\\"}\" \\\n  | python3 -c \"import sys,json; print(json.dumps(json.load(sys.stdin), indent=2))\"\n```\n\n**Roles:** use `\"org:admin\"` or `\"org:member\"` (always prefix with `org:`).\n\n### SDK equivalent (for Next.js \u002F TypeScript projects with `@clerk\u002Fnextjs` or `@clerk\u002Fbackend`)\n\n```typescript\nimport { clerkClient } from '@clerk\u002Fnextjs\u002Fserver'\n\u002F\u002F OR if using @clerk\u002Fbackend directly:\n\u002F\u002F import { createClerkClient } from '@clerk\u002Fbackend'\n\u002F\u002F const clerkClient = createClerkClient({ secretKey: process.env.CLERK_SECRET_KEY })\n\n\u002F\u002F Step 1: Create organization\nconst org = await clerkClient.organizations.createOrganization({\n  name: 'Acme Corp',\n  createdBy: userId,  \u002F\u002F required — the ID of the user creating the org\n})\n\n\u002F\u002F Step 2: Invite member to the org\nconst invitation = await clerkClient.organizations.createOrganizationInvitation({\n  organizationId: org.id,\n  emailAddress: 'user@example.com',\n  role: 'org:admin',  \u002F\u002F or 'org:member'\n})\n```\n\n### Update user metadata\n\n**Always explain the three metadata types before asking which to use:**\n\n| Type | Field | Readable by | Writable by | Use for |\n|------|-------|-------------|-------------|---------|\n| Public | `public_metadata` | Client + Server | **Server only** | Plan tier, roles, feature flags the frontend reads |\n| Private | `private_metadata` | **Server only** | **Server only** | Stripe IDs, compliance flags, internal identifiers |\n| Unsafe | `unsafe_metadata` | Client + Server | Client + Server | Ephemeral UI state, onboarding steps (client-writable — avoid sensitive data) |\n\n**For `plan: 'pro'` and `onboarded: true` — use `public_metadata`** (frontend-readable, server-writable):\n\n```bash\ncurl -s -X PATCH \"https:\u002F\u002Fapi.clerk.com\u002Fv1\u002Fusers\u002F${USER_ID}\" \\\n  -H \"Authorization: Bearer $CLERK_SECRET_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"public_metadata\": {\"plan\": \"pro\", \"onboarded\": true}}' \\\n  | python3 -c \"import sys,json; d=json.load(sys.stdin); print(f'Updated user {d[\\\"id\\\"]}: public_metadata={d.get(\\\"public_metadata\\\")}')\"\n```\n\n**SDK equivalent:**\n\n```typescript\nimport { clerkClient } from '@clerk\u002Fnextjs\u002Fserver'\n\u002F\u002F OR: import { createClerkClient } from '@clerk\u002Fbackend'\n\nawait clerkClient.users.updateUser(userId, {\n  publicMetadata: { plan: 'pro', onboarded: true },   \u002F\u002F readable by client, writable server-only\n  \u002F\u002F privateMetadata: { stripeId: 'cus_xxx' },         \u002F\u002F server-only read AND write\n  \u002F\u002F unsafeMetadata: { step: 'welcome' },              \u002F\u002F client-writable, avoid sensitive data\n})\n```\n\n**Note:** REST API uses `snake_case` (`public_metadata`). SDK uses `camelCase` (`publicMetadata`).\n\n### List users (last 7 days)\n\n```bash\ncurl -s \"https:\u002F\u002Fapi.clerk.com\u002Fv1\u002Fusers?limit=100&offset=0&order_by=-created_at&created_at=gt:$(date -d '7 days ago' +%s 2>\u002Fdev\u002Fnull || date -v-7d +%s)000\" \\\n  -H \"Authorization: Bearer $CLERK_SECRET_KEY\" \\\n  | python3 -c \"\nimport sys, json\ndata = json.load(sys.stdin)\nif isinstance(data, list):\n    print(f'Found {len(data)} users:')\n    for u in data:\n        print(f'  {u[\\\"id\\\"]}: {u.get(\\\"email_addresses\\\", [{}])[0].get(\\\"email_address\\\", \\\"no email\\\")}')\nelse:\n    print(json.dumps(data, indent=2))\n\"\n```\n\n### Delete user (confirm required)\n\n```bash\n# ONLY run after explicit user confirmation\ncurl -s -X DELETE \"https:\u002F\u002Fapi.clerk.com\u002Fv1\u002Fusers\u002F${USER_ID}\" \\\n  -H \"Authorization: Bearer $CLERK_SECRET_KEY\" \\\n  | python3 -c \"import sys,json; d=json.load(sys.stdin); print(f'Deleted: {d}')\"\n```\n\n---\n\n## Clerk Backend API — Full Endpoint Reference\n\nBase URL: `https:\u002F\u002Fapi.clerk.com\u002Fv1`\nAuth: `Authorization: Bearer $CLERK_SECRET_KEY` on every request.\n\n### Users\n\n**List users**\n```\nGET \u002Fv1\u002Fusers\nQuery params: limit (max 500, default 10), offset, order_by (+\u002F-created_at, +\u002F-updated_at, +\u002F-email_address, +\u002F-web3wallet, +\u002F-first_name, +\u002F-last_name, +\u002F-phone_number, +\u002F-username, +\u002F-last_active_at, +\u002F-last_sign_in_at), email_address[], phone_number[], username[], web3wallet[], user_id[], query, created_at (ISO 8601 range: gt:TIMESTAMP or lt:TIMESTAMP in Unix ms)\nReturns: array of User objects\n```\n\n**Get user**\n```\nGET \u002Fv1\u002Fusers\u002F{user_id}\nReturns: User object\n```\n\n**Update user**\n```\nPATCH \u002Fv1\u002Fusers\u002F{user_id}\nBody (JSON, snake_case): { public_metadata, private_metadata, unsafe_metadata, first_name, last_name, username, ... }\n```\n\n**Delete user — IRREVERSIBLE**\n```\nDELETE \u002Fv1\u002Fusers\u002F{user_id}\nDestroys: user record, all sessions, all memberships, all associated data\nReturns: { id, object, deleted: true }\n```\nAlways warn the user this is permanent and confirm before proceeding.\n\n### Organizations\n\n**Create organization**\n```\nPOST \u002Fv1\u002Forganizations\nBody: { name: string, created_by: string (user_id), public_metadata?, private_metadata?, max_allowed_memberships? }\nReturns: Organization object with { id, name, slug, ... }\n```\n\n**List organizations**\n```\nGET \u002Fv1\u002Forganizations\nQuery params: limit, offset, query, order_by\n```\n\n**Invite member**\n```\nPOST \u002Fv1\u002Forganizations\u002F{organization_id}\u002Finvitations\nBody: { email_address: string, role: string (\"org:admin\" or \"org:member\"), public_metadata?, private_metadata? }\nReturns: OrganizationInvitation object\n```\n\n---\n\n## How to execute requests\n\n**ALWAYS execute requests with direct `curl` commands.** Use the spec-extraction scripts (`api-specs-context.sh`, `extract-tags.js`, `extract-endpoint-detail.sh`) to discover endpoints, but make actual API calls with `curl`. Do NOT use `scripts\u002Fexecute-request.sh` — it's a local dev helper, not for agent use.\n\nTemplate for GET requests:\n```bash\ncurl -s \"https:\u002F\u002Fapi.clerk.com\u002Fv1${PATH}${QUERY_STRING}\" \\\n  -H \"Authorization: Bearer $CLERK_SECRET_KEY\"\n```\n\nTemplate for POST\u002FPATCH requests:\n```bash\ncurl -s -X ${METHOD} \"https:\u002F\u002Fapi.clerk.com\u002Fv1${PATH}\" \\\n  -H \"Authorization: Bearer $CLERK_SECRET_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '${BODY_JSON}'\n```\n\nTemplate for DELETE requests:\n```bash\ncurl -s -X DELETE \"https:\u002F\u002Fapi.clerk.com\u002Fv1${PATH}\" \\\n  -H \"Authorization: Bearer $CLERK_SECRET_KEY\"\n```\n\n**After getting the response:** Parse and display it clearly. Use `python3 -c \"import sys,json; data=json.load(sys.stdin); print(json.dumps(data, indent=2))\"` to pretty-print JSON. Extract key fields (id, email, name, etc.) and summarize them for the user.\n\n---\n\n## API specs context\n\nBefore doing anything outside the FAST PATH, fetch the available spec versions and tags by running:\n```bash\nbash scripts\u002Fapi-specs-context.sh\n```\n\nUse the output to determine the latest version and available tags.\n\n**Caching:** If you already fetched the spec context earlier in this conversation, do NOT fetch it again. Reuse the version and tags from the previous call.\n\n---\n\n## Rules\n\n- For common operations (list users, create org, invite, update metadata, delete user): use the FAST PATH above — do NOT fetch specs first.\n- Always disregard endpoints\u002Fschemas related to `platform`.\n- Always confirm before performing write requests (POST\u002FPUT\u002FPATCH\u002FDELETE).\n- For DELETE operations, always warn the user that the action is **irreversible** and mention what data will be lost (user record, sessions, memberships). This warning is MANDATORY — never skip it.\n- For write operations (POST\u002FPUT\u002FPATCH\u002FDELETE), check `CLERK_BAPI_SCOPES` before attempting the request. If missing or insufficient, ask the user upfront. Do NOT attempt and fail — ask before executing. This check is MANDATORY.\n- For metadata operations, always explain all three types (public, private, unsafe) and recommend the appropriate one.\n- Pagination: always use `limit` + `offset` and mention that results may be paginated for large datasets.\n- Use direct curl commands for all API calls — never use `scripts\u002Fexecute-request.sh`.\n\n---\n\n## Rate Limits & Gotchas\n\n### Rate Limits\n\n| Environment | Limit |\n|-------------|-------|\n| Production | 1,000 requests \u002F 10 seconds |\n| Development | 100 requests \u002F 10 seconds |\n| Single invitations | 100 \u002F hour |\n| Bulk invitations | 25 \u002F hour |\n| Org invitations | 250 \u002F hour |\n| Frontend API sign-in creation | 5 \u002F 10 seconds |\n| Frontend API sign-in attempts | 3 \u002F 10 seconds |\n| List users max per page | 500 |\n\n`currentUser()` makes a real API call that counts against rate limits. Use `auth()` for just the session claims — it reads from the token without an API call.\n\n### Metadata Overwrites (Not Merges)\n\n`updateUser({ publicMetadata: { role: 'admin' } })` REPLACES all public metadata, not merges. To add a field without losing existing data: read first, spread, then write.\n\nWrong:\n```typescript\nawait clerkClient.users.updateUser(userId, { publicMetadata: { newField: 'value' } })\n```\nThis DELETES all other `publicMetadata` fields.\n\nRight:\n```typescript\nconst user = await clerkClient.users.getUser(userId)\nawait clerkClient.users.updateUser(userId, {\n  publicMetadata: { ...user.publicMetadata, newField: 'value' },\n})\n```\n\n---\n\n## Modes\n\nDetermine the active mode based on the user prompt in [Options context](#options-context):\n\n| Mode | Trigger | Behavior |\n|------|---------|----------|\n| `help` | Prompt is empty, or contains only `help` \u002F `-h` \u002F `--help` | Print usage examples (step 0) |\n| `browse` | Prompt is `tags`, or a tag name (e.g. `Users`) | List all tags or endpoints for a tag |\n| `execute` | Specific endpoint (e.g. `GET \u002Fusers`) or natural language action (e.g. \"get user john_doe\") | Look up endpoint, execute request |\n| `detail` | Endpoint + `help` \u002F `-h` \u002F `--help` (e.g. `GET \u002Fusers help`) | Show endpoint schema, don't execute |\n\n---\n\n## Your Task\n\nUse the **LATEST VERSION** from [API specs context](#api-specs-context) by default. If the user specifies a different version (e.g. `--version 2024-10-01`), use that version instead.\n\nDetermine the active mode, then follow the applicable steps below.\n\n---\n\n### 0. Print usage\n\n**Modes:** `help` only — **Skip** for `browse`, `execute`, and `detail`.\n\nPrint the following examples to the user verbatim:\n\n```\nBrowse\n  \u002Fclerk-backend-api tags                         — list all tags\n  \u002Fclerk-backend-api Users                        — browse endpoints for the Users tag\n  \u002Fclerk-backend-api Users version 2025-11-10.yml — browse using a different version\n\nExecute\n  \u002Fclerk-backend-api GET \u002Fusers             — fetch all users\n  \u002Fclerk-backend-api get user john_doe      — natural language works too\n  \u002Fclerk-backend-api POST \u002Finvitations      — create an invitation\n\nInspect\n  \u002Fclerk-backend-api GET \u002Fusers help        — show endpoint schema without executing\n  \u002Fclerk-backend-api POST \u002Finvitations -h   — view request\u002Fresponse details\n\nOptions\n  --admin                            — bypass scope restrictions for write\u002Fdelete\n  --version [date], version [date]   — use a specific spec version\n  --help, -h, help                   — inspect endpoint instead of executing\n```\n\nStop here.\n\n---\n\n### 1. Fetch tags\n\n**Modes:** `browse` (when prompt is `tags` or no tag specified) — **Skip** for `help`, `execute`, and `detail`.\n\nIf using a non-latest version, fetch tags for that version:\n```bash\ncurl -s https:\u002F\u002Fraw.githubusercontent.com\u002Fclerk\u002Fopenapi-specs\u002Fmain\u002Fbapi\u002F${version_name} | node scripts\u002Fextract-tags.js\n```\nOtherwise, use the **TAGS** already in [API specs context](#api-specs-context).\n\nShare tags in a table and prompt the user to select a query.\n\n---\n\n### 2. Fetch tag endpoints\n\n**Modes:** `browse` (when a tag name is provided) — **Skip** for `help`, `execute`, and `detail`.\n\nFetch all endpoints for the identified tag:\n```bash\ncurl -s https:\u002F\u002Fraw.githubusercontent.com\u002Fclerk\u002Fopenapi-specs\u002Fmain\u002Fbapi\u002F${version_name} | bash scripts\u002Fextract-tag-endpoints.sh \"${tag_name}\"\n```\n\nShare the results (endpoints, schemas, parameters) with the user.\n\n---\n\n### 3. Fetch endpoint detail\n\n**Modes:** `execute`, `detail` — **Skip** for `help` and `browse`.\n\nFor natural language prompts in `execute` mode, first check if the operation matches a FAST PATH entry above. If it does, skip this step and proceed directly to step 4 using the FAST PATH template.\n\nFor other endpoints, identify the matching endpoint by searching the tags in context. Fetch tag endpoints if needed to resolve the exact path and method.\n\nExtract the full endpoint definition:\n```bash\ncurl -s https:\u002F\u002Fraw.githubusercontent.com\u002Fclerk\u002Fopenapi-specs\u002Fmain\u002Fbapi\u002F${version_name} | bash scripts\u002Fextract-endpoint-detail.sh \"${path}\" \"${method}\"\n```\n- `${path}` — e.g. `\u002Fusers\u002F{user_id}`\n- `${method}` — lowercase, e.g. `get`\n\n**`detail` mode:** Share the endpoint definition and schemas with the user. Stop here.\n\n**`execute` mode:** Continue to step 4.\n\n---\n\n### 4. Execute request\n\n**Modes:** `execute` only.\n\n1. Run the **mandatory checks** from the CRITICAL section above.\n2. Identify required and optional parameters from the spec (step 3) or FAST PATH.\n3. Ask the user for any required path\u002Fquery\u002Fbody parameters that weren't provided.\n4. Build and execute a **direct curl command** (see How to execute requests above). Do NOT use `scripts\u002Fexecute-request.sh`.\n5. Parse the JSON response and display it clearly. Extract and summarize key fields for the user.\n\n**Example — list users and parse response:**\n```bash\nRESPONSE=$(curl -s \"https:\u002F\u002Fapi.clerk.com\u002Fv1\u002Fusers?limit=10\" \\\n  -H \"Authorization: Bearer $CLERK_SECRET_KEY\")\necho \"$RESPONSE\" | python3 -c \"\nimport sys, json\ndata = json.load(sys.stdin)\nif isinstance(data, list):\n    print(f'Found {len(data)} users:')\n    for u in data:\n        print(f'  {u[\\\"id\\\"]}: {u.get(\\\"email_addresses\\\", [{}])[0].get(\\\"email_address\\\", \\\"no email\\\")}')\nelse:\n    print(json.dumps(data, indent=2))\n\"\n```\n\n## See Also\n\n- `clerk-setup` - Initial Clerk install\n- `clerk-orgs` - Manage organizations via API\n- `clerk-webhooks` - Real-time event sync\n",{"name":5,"license":14,"description":7,"allowed-tools":23,"compatibility":24},"Bash, Read, Grep, Skill, WebFetch","Requires CLERK_SECRET_KEY (sk_*) for Backend API calls.","main","1f317365436456f9c1039c414a2f6426caabc74c",".agents\u002Fskills\u002Fclerk-backend-api","https:\u002F\u002Fgithub.com\u002FKrishp091205\u002Fgemini-config","https:\u002F\u002Fgithub.com\u002FKrishp091205","2026-08-23 02:02:24",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add Krishp091205\u002Fgemini-config --skill clerk-backend-api",{"tool":37,"command":38},"bunx","bunx skills add Krishp091205\u002Fgemini-config --skill clerk-backend-api",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Krishp091205\u002Fgemini-config --skill clerk-backend-api","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKrishp091205\u002Fgemini-config\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclerk-backend-api\u002FSKILL.md",true,[45,51,57,61,65,69],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"evals\u002Fevals.json","REFERENCE","参考文档",4742,"https:\u002F\u002Fgithub.com\u002FKrishp091205\u002Fgemini-config\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclerk-backend-api\u002Fevals\u002Fevals.json",{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"scripts\u002Fapi-specs-context.sh","SCRIPT","脚本",887,"https:\u002F\u002Fgithub.com\u002FKrishp091205\u002Fgemini-config\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclerk-backend-api\u002Fscripts\u002Fapi-specs-context.sh",{"path":58,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":59,"sourceHtmlUrl":60},"scripts\u002Fexecute-request.sh",2376,"https:\u002F\u002Fgithub.com\u002FKrishp091205\u002Fgemini-config\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclerk-backend-api\u002Fscripts\u002Fexecute-request.sh",{"path":62,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":63,"sourceHtmlUrl":64},"scripts\u002Fextract-endpoint-detail.sh",5244,"https:\u002F\u002Fgithub.com\u002FKrishp091205\u002Fgemini-config\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclerk-backend-api\u002Fscripts\u002Fextract-endpoint-detail.sh",{"path":66,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":67,"sourceHtmlUrl":68},"scripts\u002Fextract-tag-endpoints.sh",5952,"https:\u002F\u002Fgithub.com\u002FKrishp091205\u002Fgemini-config\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclerk-backend-api\u002Fscripts\u002Fextract-tag-endpoints.sh",{"path":70,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":71,"sourceHtmlUrl":72},"scripts\u002Fextract-tags.js",429,"https:\u002F\u002Fgithub.com\u002FKrishp091205\u002Fgemini-config\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclerk-backend-api\u002Fscripts\u002Fextract-tags.js",[74,82,89,96,103,110],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M7B0GYVAXB2M99PR4Z3N1WW0","skill-repair","Use this to fix and re-install agent skills that have failed installation.\nThis skill provides the necessary context and permissions to surgically update\nthe `manifest.json` after a fix has been applied.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FKrishp091205\u002Fgemini-config\u002Fblob\u002Fmain\u002Fskills\u002Fskill-repair\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M7B0GQ2CKFX5P1DTV802XMAB","notebook-guidance","This skill guides the use of Jupyter notebooks for data analysis, exploration, and visualization, particularly with BigQuery. It outlines best practices for notebook execution and validation (supporting both cell-by-cell execution and full notebook generation depending on tool availability), library installation, and structuring notebooks for clarity. It also covers specific rules for data cleaning, plotting, and integrating with BigQuery SQL and machine learning workflows.\nRelevant when any of the following conditions are true:\n  1. The user request involves a data analysis, data exploration, data visualization, or data insights task that requires multiple steps, queries, or visualizations to answer.\n  2. The user explicitly requests a notebook (.ipynb).\n  3. You are creating, editing, or executing cells in a Jupyter notebook.\n  4. You need to query BigQuery from within a notebook. DO NOT use the Python BigQuery client library; instead, you MUST use the `%%bqsql` magics explained in this skill.","https:\u002F\u002Fgithub.com\u002FKrishp091205\u002Fgemini-config\u002Fblob\u002Fmain\u002Fskills\u002Fnotebook-guidance\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M7B0GJ1K1JE2K593JZT4CAY9","ml-best-practices","CRITICAL RULE: You MUST use this skill whenever the task involves any machine learning tasks or data analysis.\nUse this skill if the user's prompt or requirements mention any of the following:\n  * Clustering\n  * Classification\n  * Regression\n  * Time series forecasting\n  * Statistical testing\n  * Model comparison\n  * ML\n  * Data analysis\n\nSQL\u002FBigQuery ML HANDOFF: If the user requires a SQL solution, use this skill to dictate the ANALYSIS STEPS (e.g., markdown analysis cells, visualization logic), but defer to `bigquery` for all SQL syntax.","https:\u002F\u002Fgithub.com\u002FKrishp091205\u002Fgemini-config\u002Fblob\u002Fmain\u002Fskills\u002Fml-best-practices\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M7B0GD7FSN72WCSZ16WEDH42","managing-python-dependencies","Ensures proper Python dependency management, avoiding global `pip install` and\nadhering to project-specific tooling.\n\nUse this skill if any of the following are true:\n  1. Attempting to run `pip install {package_name}`.\n  2. Python packages or dependencies need to be added or modified.\n  3. Initiating a new Python project.\n  4. Creating a new notebook, even if just using BigQuery cells.\n  5. Generating Python code that includes `import` statements for third-party libraries.\n  6. Before executing Python scripts via the terminal to ensure the correct virtual environment is active.","https:\u002F\u002Fgithub.com\u002FKrishp091205\u002Fgemini-config\u002Fblob\u002Fmain\u002Fskills\u002Fmanaging-python-dependencies\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":18},"01M7B0G6CC6JP6QTQGPSTBMJTX","google-cloud-storage-basics","Stores, retrieves, and manages data as objects in Cloud Storage (Google Cloud Storage, or GCS) buckets. Use when you need to interact with Cloud Storage — create or configure buckets, upload, download, stream, or transfer data, organize objects with folders, generate signed URLs, control access (IAM, ACLs, public access prevention), set storage classes and tiering (Standard, Nearline, Coldline, Archive), manage cost and lifecycle, protect data (versioning, encryption\u002FCMEK, retention and Bucket Lock, object holds, soft delete), host static websites, trigger Pub\u002FSub notifications on object changes, mount buckets as a file system (gcsfuse), or optimize storage performance at any scale. Covers the gcloud storage \u002F gsutil CLI, JSON and XML APIs, client libraries, Terraform, and Cloud Storage MCP servers. Don't use for block storage (Persistent Disk), data warehousing\u002Fanalytics (BigQuery), or databases (Cloud SQL, Spanner, Bigtable, Firestore).","https:\u002F\u002Fgithub.com\u002FKrishp091205\u002Fgemini-config\u002Fblob\u002Fmain\u002Fskills\u002Fgoogle-cloud-storage-basics\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":18},"01M7B0G2DF32KW9A77S99QBZ4Q","gcs-security-assessment","Assesses security posture, evaluates risks, and checks SAIF compliance for Google Cloud Storage buckets or projects. Use when the user requests security scans, vulnerability checks, or SAIF assessments. Don't use when: The user is asking about non-GCS resources (Compute Engine, GKE, etc.), investigating a live production outage, or asking general security questions not tied to a specific project or bucket.","https:\u002F\u002Fgithub.com\u002FKrishp091205\u002Fgemini-config\u002Fblob\u002Fmain\u002Fskills\u002Fgcs-security-assessment\u002FSKILL.md",[],[]]