[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M76XFVA5RCR85ZMYXED0ZBAF":3,"skill-same:01M76XFVA5RCR85ZMYXED0ZBAF":102},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":6,"updatedAt":37,"install":38,"resources":51},"01M76XFVA5RCR85ZMYXED0ZBAF","rover",null,"Guide for using Apollo Rover CLI to manage GraphQL schemas and federation. Use this skill when: (1) publishing or fetching subgraph\u002Fgraph schemas, (2) composing supergraph schemas locally or via GraphOS, (3) running local supergraph development with rover dev, (4) validating schemas with check and lint commands, (5) configuring Rover authentication and environment, (6) exploring or searching a graph's schema for agent-driven discovery (rover schema describe \u002F rover schema search), (7) initializing a new graph project or MCP server with rover init, (8) working with Apollo Connectors, contracts, persisted queries, or client operations, (9) managing API keys, plugins, templates, or graph artifacts.","stanfish06\u002Fskillquarium","stanfish06","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F93099613?v=4","01M75F1CK4ZW109ZK3T26VN52F","Zhiyuan","01M75F1CM53VH6F79DZ8GXKKES",12,"MIT","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Frover\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: rover\ndescription: >\n  Guide for using Apollo Rover CLI to manage GraphQL schemas and federation. Use this skill when:\n  (1) publishing or fetching subgraph\u002Fgraph schemas,\n  (2) composing supergraph schemas locally or via GraphOS,\n  (3) running local supergraph development with rover dev,\n  (4) validating schemas with check and lint commands,\n  (5) configuring Rover authentication and environment,\n  (6) exploring or searching a graph's schema for agent-driven discovery (rover schema describe \u002F rover schema search),\n  (7) initializing a new graph project or MCP server with rover init,\n  (8) working with Apollo Connectors, contracts, persisted queries, or client operations,\n  (9) managing API keys, plugins, templates, or graph artifacts.\nlicense: MIT\ncompatibility: Node.js v18+, Linux\u002FmacOS\u002FWindows\nmetadata:\n  author: apollographql\n  version: \"1.2.0\"\nallowed-tools: Bash(rover:*) Bash(npm:*) Bash(npx:*) Read Write Edit Glob Grep\n---\n\n# Apollo Rover CLI Guide\n\nRover is the official CLI for Apollo GraphOS. It helps you manage schemas, run composition locally, publish to GraphOS, and develop supergraphs on your local machine.\n\n## Quick Start\n\n### Step 1: Install\n\n```bash\n# macOS\u002FLinux\ncurl -sSL https:\u002F\u002Frover.apollo.dev\u002Fnix\u002Flatest | sh\n\n# npm (cross-platform)\nnpm install -g @apollo\u002Frover\n\n# Windows PowerShell\niwr 'https:\u002F\u002Frover.apollo.dev\u002Fwin\u002Flatest' | iex\n```\n\n### Step 2: Authenticate\n\n```bash\n# OAuth login via browser (recommended for local dev)\nrover auth login\n\n# Or interactive API key entry\nrover config auth\n\n# Or set environment variable (recommended for CI\u002FCD)\nexport APOLLO_KEY=your-api-key\n```\n\n### Step 3: Verify Installation\n\n```bash\nrover --version\nrover auth whoami    # OAuth identity\nrover config whoami  # API key identity\n```\n\n### Step 4: Initialize a Project (optional)\n\n```bash\n# Create a new federated graph project\nrover init\n\n# Create a project with MCP server\nrover init --mcp\n```\n\n## Explore a Graph's Schema (start here for schema questions)\n\nTo answer \"what's in this graph?\", find a field, or write a query against a GraphOS graph, **fetch the API schema and pipe it into `rover schema`** — this keeps the SDL out of your context and returns only what you need:\n\n```bash\n# What can I query? (compact overview)\nrover graph fetch \u003Cgraph@variant> | rover schema describe -\n\n# Find a field by concept\u002Fkeyword (returns the path from a root operation)\nrover graph fetch \u003Cgraph@variant> | rover schema search - \"\u003Ckeyword>\"\n\n# Zoom into one type or field\nrover graph fetch \u003Cgraph@variant> | rover schema describe - --coord \u003CType.field> --depth 1\n```\n\nThree rules that keep this correct:\n\n- Use **`rover graph fetch`** (the API schema) — **not** `rover supergraph fetch` (that returns composition SDL with federation internals like `join__`\u002F`link__`).\n- **Pipe** it in — never run `rover graph fetch` alone and read the raw SDL (a large schema floods your context; that's exactly what `rover schema` avoids).\n- The `schema` commands read **piped SDL, not a graph ref** — `rover schema describe \u003Cgraph@variant>` fails; you must fetch first and pipe.\n\nFull reference, ranking rules, and the save-once pattern: [Schema Exploration](#schema-exploration-for-agents) and [references\u002Fschema.md](references\u002Fschema.md).\n\n## Core Commands Overview\n\n| Command | Description | Use Case |\n|---------|-------------|----------|\n| `rover init` | Initialize a new federated graph project | New project setup, MCP server setup |\n| `rover subgraph publish` | Publish subgraph schema to GraphOS | CI\u002FCD, schema updates |\n| `rover subgraph check` | Validate schema changes | PR checks, pre-deploy |\n| `rover subgraph fetch` | Download subgraph schema | Local development |\n| `rover supergraph compose` | Compose supergraph locally | Local testing |\n| `rover dev` | Local supergraph development | Development workflow |\n| `rover graph publish` | Publish monograph schema | Non-federated graphs |\n| `rover schema describe` | Explore a schema by coordinate; **takes SDL via stdin\u002Ffile, not a graph ref** — pipe from `rover graph fetch` | Agent schema discovery |\n| `rover schema search` | Search a schema by keyword; **takes SDL via stdin\u002Ffile, not a graph ref** — pipe from `rover graph fetch` | Agent schema discovery |\n| `rover connector` | Work with Apollo Connectors (run, test, list) | Connector development |\n| `rover contract` | Manage contract variants (describe, preview, publish) | API surface filtering |\n| `rover persisted-queries` | Generate and publish persisted query manifests (alias: `pq`) | Security, performance |\n| `rover client check` | Validate client operations against a graph schema | Client-side CI |\n| `rover auth login` | Authenticate via OAuth browser flow | Local dev auth |\n| `rover api-key` | Create, list, delete, rename, rotate API keys | Key management |\n| `rover readme` | Fetch or publish graph variant READMEs | Graph documentation |\n| `rover template` | List and use project templates | Scaffolding |\n\n## Graph Reference Format\n\nMost commands require a graph reference in the format:\n\n```\n\u003CGRAPH_ID>@\u003CVARIANT>\n```\n\nExamples:\n- `my-graph@production`\n- `my-graph@staging`\n- `my-graph@current` (default variant)\n\nSet as environment variable:\n```bash\nexport APOLLO_GRAPH_REF=my-graph@production\n```\n\n## Subgraph Workflow\n\n### Publishing a Subgraph\n\n```bash\n# From schema file\nrover subgraph publish my-graph@production \\\n  --name products \\\n  --schema .\u002Fschema.graphql \\\n  --routing-url https:\u002F\u002Fproducts.example.com\u002Fgraphql\n\n# From running server (introspection)\nrover subgraph publish my-graph@production \\\n  --name products \\\n  --schema \u003C(rover subgraph introspect http:\u002F\u002Flocalhost:4001\u002Fgraphql) \\\n  --routing-url https:\u002F\u002Fproducts.example.com\u002Fgraphql\n```\n\n### Checking Schema Changes\n\n```bash\n# Check against production traffic\nrover subgraph check my-graph@production \\\n  --name products \\\n  --schema .\u002Fschema.graphql\n```\n\n### Fetching Schema\n\n```bash\n# Fetch from GraphOS\nrover subgraph fetch my-graph@production --name products\n\n# Introspect running server\nrover subgraph introspect http:\u002F\u002Flocalhost:4001\u002Fgraphql\n```\n\n## Supergraph Composition\n\n### Local Composition\n\nCreate `supergraph.yaml`:\n\n```yaml\nfederation_version: =2.9.0\nsubgraphs:\n  products:\n    routing_url: http:\u002F\u002Flocalhost:4001\u002Fgraphql\n    schema:\n      file: .\u002Fproducts\u002Fschema.graphql\n  reviews:\n    routing_url: http:\u002F\u002Flocalhost:4002\u002Fgraphql\n    schema:\n      subgraph_url: http:\u002F\u002Flocalhost:4002\u002Fgraphql\n```\n\n`federation_version` here is the **composition version** — it only needs to be ≥\neach subgraph's `@link` floor, so subgraphs pinned to a lower version compose\nfine. If a subgraph server throws `UNKNOWN_FEDERATION_LINK_VERSION` at startup,\nthat's a client-library lag, not a composition problem. See the apollo-federation\nskill's [Federation versions](..\u002Fapollo-federation\u002Freferences\u002Fcomposition.md#federation-versions-floor-vs-composition).\n\nCompose:\n```bash\nrover supergraph compose --config supergraph.yaml > supergraph.graphql\n```\n\n### Fetch Composed Supergraph\n\n```bash\nrover supergraph fetch my-graph@production\n```\n\n> This returns the **supergraph SDL** (federation directives + `join__`\u002F`link__` internals) — use it for composition\u002Frouter work. To **explore what you can query** or write an operation, use `rover graph fetch` (the API schema) instead — see [Explore a Graph's Schema](#explore-a-graphs-schema-start-here-for-schema-questions).\n\n## Local Development with `rover dev`\n\nStart a local Router with automatic schema composition:\n\n```bash\n# Start with supergraph config\nrover dev --supergraph-config supergraph.yaml\n\n# Start with GraphOS variant as base\nrover dev --graph-ref my-graph@staging --supergraph-config local.yaml\n```\n\n### With MCP Integration\n\n```bash\n# Start with MCP server enabled\nrover dev --supergraph-config supergraph.yaml --mcp\n```\n\n## Schema Exploration (for Agents)\n\n`rover schema describe` and `rover schema search` let an agent explore a schema **without loading the full SDL into context** — that is the entire point of these commands.\n\n> ⚠️ **Never read the raw SDL into context.** Running `rover graph fetch \u003Cref>` (or `rover graph introspect \u003Curl>`) on its own prints the entire schema — hundreds to tens of thousands of lines — straight into your context, which defeats the purpose of these commands. **Always pipe fetch output into `rover schema describe`\u002F`search`**: the SDL flows through stdin and only the compact overview\u002Fresults reach you. (Fetching to a file is fine when the user actually wants the SDL.)\n>\n> These commands also take SDL on **stdin or a file, NOT a graph ref** — you can't pass `graph@variant` to them. Fetch first, then pipe:\n>\n> ```bash\n> ❌ rover schema describe my-graph@current             # error: looks for a file named that\n> ❌ rover graph fetch my-graph@current                 # dumps the full SDL into your context\n> ✅ rover graph fetch my-graph@current | rover schema describe -\n> ```\n\nTo explore a graph in GraphOS, fetch its schema and pipe it in. **Use `rover graph fetch` (the API schema) for \"what can I query?\" exploration** — it omits federation internals. Reach for `rover supergraph fetch` only when you need composition details (`join__`\u002F`link__` types, subgraph structure):\n\n```bash\n# Overview of a GraphOS graph\nrover graph fetch my-graph@current | rover schema describe -\n\n# Find fields by keyword (results include paths from root operations)\nrover graph fetch my-graph@current | rover schema search - \"playback\"\n\n# Zoom into a coordinate, expanding referenced types one level\nrover graph fetch my-graph@current | rover schema describe - --coord \u003CType.field> --depth 1\n```\n\n**Coordinate forms:** `--coord` accepts a type (`User`), a field (`User.posts`), a field argument (`Type.field(arg:)`), or a directive (`@deprecated`) — omit it for the overview.\n\n**`search` vs `describe`:** reach for `rover schema search` first when matching a concept or keyword and you don't yet know the field name — it finds **nested** fields and shows the path from a root operation. The `describe` overview lists only root fields, so `search` is how you locate fields buried deeper. Use `describe` for the overview or once you know the type\u002Ffield coordinate.\n\nThis enables a closed-loop workflow — search → describe → write a query — with no MCP server setup. See [Schema Exploration](references\u002Fschema.md) for the full command reference, ranking rules, and the save-once pattern for large schemas.\n\n**Running the generated operation:** Rover does **not** execute queries — it only manages and inspects schemas. To actually run a generated query you need the graph's endpoint:\n\n- **Single-subgraph graph:** `rover subgraph list \u003Cgraph@variant>` prints the **Routing Url** — send the query there with `curl`.\n- **Multi-subgraph \u002F federated:** the client endpoint is the **router** URL (find it in GraphOS Studio), not the per-subgraph routing URLs.\n- Don't try to discover the endpoint via the GraphOS Platform API — Rover keeps the API key in its profile\u002Fkeychain, not `$APOLLO_KEY`, so ad-hoc API calls will come back unauthenticated.\n\n## Reference Files\n\nDetailed documentation for specific topics:\n\n- [Init](references\u002Finit.md) - `rover init` project initialization and MCP server setup\n- [Subgraphs](references\u002Fsubgraphs.md) - fetch, publish, check, lint, introspect, delete\n- [Graphs](references\u002Fgraphs.md) - monograph commands (non-federated)\n- [Supergraphs](references\u002Fsupergraphs.md) - compose, fetch, config format\n- [Dev](references\u002Fdev.md) - rover dev for local development\n- [Schema Exploration](references\u002Fschema.md) - describe, search, agent schema discovery workflows\n- [Connectors](references\u002Fconnectors.md) - `rover connector` run, test, list, analyze, generate\n- [Contracts](references\u002Fcontracts.md) - contract variant describe, preview, publish\n- [Persisted Queries](references\u002Fpersisted-queries.md) - generate and publish persisted query manifests\n- [Client Operations](references\u002Fclient.md) - validate client operations, extract GraphQL documents\n- [Configuration](references\u002Fconfiguration.md) - install, auth, env vars, profiles, OAuth login\n- [Additional Commands](references\u002Fadditional-commands.md) - template, readme, api-key, plugin, license, graph-artifact, completion, explain, docs\n\n## Common Patterns\n\n### CI\u002FCD Pipeline\n\n```bash\n# 1. Check schema changes\nrover subgraph check $APOLLO_GRAPH_REF \\\n  --name $SUBGRAPH_NAME \\\n  --schema .\u002Fschema.graphql\n\n# 2. If check passes, publish\nrover subgraph publish $APOLLO_GRAPH_REF \\\n  --name $SUBGRAPH_NAME \\\n  --schema .\u002Fschema.graphql \\\n  --routing-url $ROUTING_URL\n```\n\n### Schema Linting\n\n```bash\n# Lint against GraphOS rules\nrover subgraph lint --name products .\u002Fschema.graphql\n\n# Lint monograph\nrover graph lint my-graph@production .\u002Fschema.graphql\n```\n\n### Output Formats\n\n```bash\n# JSON output for scripting\nrover subgraph fetch my-graph@production --name products --format json\n\n# Plain output (default)\nrover subgraph fetch my-graph@production --name products --format plain\n```\n\n## Ground Rules\n\n- ALWAYS authenticate before using GraphOS commands (`rover auth login`, `rover config auth`, or `APOLLO_KEY`)\n- ALWAYS use the correct graph reference format: `graph@variant`\n- PREFER `rover subgraph check` before `rover subgraph publish` in CI\u002FCD\n- USE `rover dev` for local supergraph development instead of running Router manually\n- USE `rover init` to scaffold new graph projects instead of manual setup\n- NEVER commit `APOLLO_KEY` or `APOLLO_CLIENT_SECRET` to version control; use environment variables\n- USE `--format json` when parsing output programmatically\n- SPECIFY `federation_version` explicitly in supergraph.yaml for reproducibility\n- USE `rover subgraph introspect` to extract schemas from running services\n- USE `rover schema search` \u002F `rover schema describe` (piped from a `fetch`) to explore large schemas instead of loading the full SDL into context\n- NEVER fetch a full schema into context just to explore it — pipe `rover graph fetch`\u002F`introspect` into `rover schema describe`\u002F`search` (a bare `fetch` is only for when the user wants the SDL file itself)\n- USE `rover client check` to validate client operations before deploying client changes\n- USE `rover persisted-queries publish` to register operations for persisted query enforcement\n","# Apollo Rover CLI Guide\n\nRover is the official CLI for Apollo GraphOS. It helps you manage schemas, run composition locally, publish to GraphOS, and develop supergraphs on your local machine.\n\n## Quick Start\n\n### Step 1: Install\n\n```bash\n# macOS\u002FLinux\ncurl -sSL https:\u002F\u002Frover.apollo.dev\u002Fnix\u002Flatest | sh\n\n# npm (cross-platform)\nnpm install -g @apollo\u002Frover\n\n# Windows PowerShell\niwr 'https:\u002F\u002Frover.apollo.dev\u002Fwin\u002Flatest' | iex\n```\n\n### Step 2: Authenticate\n\n```bash\n# OAuth login via browser (recommended for local dev)\nrover auth login\n\n# Or interactive API key entry\nrover config auth\n\n# Or set environment variable (recommended for CI\u002FCD)\nexport APOLLO_KEY=your-api-key\n```\n\n### Step 3: Verify Installation\n\n```bash\nrover --version\nrover auth whoami    # OAuth identity\nrover config whoami  # API key identity\n```\n\n### Step 4: Initialize a Project (optional)\n\n```bash\n# Create a new federated graph project\nrover init\n\n# Create a project with MCP server\nrover init --mcp\n```\n\n## Explore a Graph's Schema (start here for schema questions)\n\nTo answer \"what's in this graph?\", find a field, or write a query against a GraphOS graph, **fetch the API schema and pipe it into `rover schema`** — this keeps the SDL out of your context and returns only what you need:\n\n```bash\n# What can I query? (compact overview)\nrover graph fetch \u003Cgraph@variant> | rover schema describe -\n\n# Find a field by concept\u002Fkeyword (returns the path from a root operation)\nrover graph fetch \u003Cgraph@variant> | rover schema search - \"\u003Ckeyword>\"\n\n# Zoom into one type or field\nrover graph fetch \u003Cgraph@variant> | rover schema describe - --coord \u003CType.field> --depth 1\n```\n\nThree rules that keep this correct:\n\n- Use **`rover graph fetch`** (the API schema) — **not** `rover supergraph fetch` (that returns composition SDL with federation internals like `join__`\u002F`link__`).\n- **Pipe** it in — never run `rover graph fetch` alone and read the raw SDL (a large schema floods your context; that's exactly what `rover schema` avoids).\n- The `schema` commands read **piped SDL, not a graph ref** — `rover schema describe \u003Cgraph@variant>` fails; you must fetch first and pipe.\n\nFull reference, ranking rules, and the save-once pattern: [Schema Exploration](#schema-exploration-for-agents) and [references\u002Fschema.md](references\u002Fschema.md).\n\n## Core Commands Overview\n\n| Command | Description | Use Case |\n|---------|-------------|----------|\n| `rover init` | Initialize a new federated graph project | New project setup, MCP server setup |\n| `rover subgraph publish` | Publish subgraph schema to GraphOS | CI\u002FCD, schema updates |\n| `rover subgraph check` | Validate schema changes | PR checks, pre-deploy |\n| `rover subgraph fetch` | Download subgraph schema | Local development |\n| `rover supergraph compose` | Compose supergraph locally | Local testing |\n| `rover dev` | Local supergraph development | Development workflow |\n| `rover graph publish` | Publish monograph schema | Non-federated graphs |\n| `rover schema describe` | Explore a schema by coordinate; **takes SDL via stdin\u002Ffile, not a graph ref** — pipe from `rover graph fetch` | Agent schema discovery |\n| `rover schema search` | Search a schema by keyword; **takes SDL via stdin\u002Ffile, not a graph ref** — pipe from `rover graph fetch` | Agent schema discovery |\n| `rover connector` | Work with Apollo Connectors (run, test, list) | Connector development |\n| `rover contract` | Manage contract variants (describe, preview, publish) | API surface filtering |\n| `rover persisted-queries` | Generate and publish persisted query manifests (alias: `pq`) | Security, performance |\n| `rover client check` | Validate client operations against a graph schema | Client-side CI |\n| `rover auth login` | Authenticate via OAuth browser flow | Local dev auth |\n| `rover api-key` | Create, list, delete, rename, rotate API keys | Key management |\n| `rover readme` | Fetch or publish graph variant READMEs | Graph documentation |\n| `rover template` | List and use project templates | Scaffolding |\n\n## Graph Reference Format\n\nMost commands require a graph reference in the format:\n\n```\n\u003CGRAPH_ID>@\u003CVARIANT>\n```\n\nExamples:\n- `my-graph@production`\n- `my-graph@staging`\n- `my-graph@current` (default variant)\n\nSet as environment variable:\n```bash\nexport APOLLO_GRAPH_REF=my-graph@production\n```\n\n## Subgraph Workflow\n\n### Publishing a Subgraph\n\n```bash\n# From schema file\nrover subgraph publish my-graph@production \\\n  --name products \\\n  --schema .\u002Fschema.graphql \\\n  --routing-url https:\u002F\u002Fproducts.example.com\u002Fgraphql\n\n# From running server (introspection)\nrover subgraph publish my-graph@production \\\n  --name products \\\n  --schema \u003C(rover subgraph introspect http:\u002F\u002Flocalhost:4001\u002Fgraphql) \\\n  --routing-url https:\u002F\u002Fproducts.example.com\u002Fgraphql\n```\n\n### Checking Schema Changes\n\n```bash\n# Check against production traffic\nrover subgraph check my-graph@production \\\n  --name products \\\n  --schema .\u002Fschema.graphql\n```\n\n### Fetching Schema\n\n```bash\n# Fetch from GraphOS\nrover subgraph fetch my-graph@production --name products\n\n# Introspect running server\nrover subgraph introspect http:\u002F\u002Flocalhost:4001\u002Fgraphql\n```\n\n## Supergraph Composition\n\n### Local Composition\n\nCreate `supergraph.yaml`:\n\n```yaml\nfederation_version: =2.9.0\nsubgraphs:\n  products:\n    routing_url: http:\u002F\u002Flocalhost:4001\u002Fgraphql\n    schema:\n      file: .\u002Fproducts\u002Fschema.graphql\n  reviews:\n    routing_url: http:\u002F\u002Flocalhost:4002\u002Fgraphql\n    schema:\n      subgraph_url: http:\u002F\u002Flocalhost:4002\u002Fgraphql\n```\n\n`federation_version` here is the **composition version** — it only needs to be ≥\neach subgraph's `@link` floor, so subgraphs pinned to a lower version compose\nfine. If a subgraph server throws `UNKNOWN_FEDERATION_LINK_VERSION` at startup,\nthat's a client-library lag, not a composition problem. See the apollo-federation\nskill's [Federation versions](..\u002Fapollo-federation\u002Freferences\u002Fcomposition.md#federation-versions-floor-vs-composition).\n\nCompose:\n```bash\nrover supergraph compose --config supergraph.yaml > supergraph.graphql\n```\n\n### Fetch Composed Supergraph\n\n```bash\nrover supergraph fetch my-graph@production\n```\n\n> This returns the **supergraph SDL** (federation directives + `join__`\u002F`link__` internals) — use it for composition\u002Frouter work. To **explore what you can query** or write an operation, use `rover graph fetch` (the API schema) instead — see [Explore a Graph's Schema](#explore-a-graphs-schema-start-here-for-schema-questions).\n\n## Local Development with `rover dev`\n\nStart a local Router with automatic schema composition:\n\n```bash\n# Start with supergraph config\nrover dev --supergraph-config supergraph.yaml\n\n# Start with GraphOS variant as base\nrover dev --graph-ref my-graph@staging --supergraph-config local.yaml\n```\n\n### With MCP Integration\n\n```bash\n# Start with MCP server enabled\nrover dev --supergraph-config supergraph.yaml --mcp\n```\n\n## Schema Exploration (for Agents)\n\n`rover schema describe` and `rover schema search` let an agent explore a schema **without loading the full SDL into context** — that is the entire point of these commands.\n\n> ⚠️ **Never read the raw SDL into context.** Running `rover graph fetch \u003Cref>` (or `rover graph introspect \u003Curl>`) on its own prints the entire schema — hundreds to tens of thousands of lines — straight into your context, which defeats the purpose of these commands. **Always pipe fetch output into `rover schema describe`\u002F`search`**: the SDL flows through stdin and only the compact overview\u002Fresults reach you. (Fetching to a file is fine when the user actually wants the SDL.)\n>\n> These commands also take SDL on **stdin or a file, NOT a graph ref** — you can't pass `graph@variant` to them. Fetch first, then pipe:\n>\n> ```bash\n> ❌ rover schema describe my-graph@current             # error: looks for a file named that\n> ❌ rover graph fetch my-graph@current                 # dumps the full SDL into your context\n> ✅ rover graph fetch my-graph@current | rover schema describe -\n> ```\n\nTo explore a graph in GraphOS, fetch its schema and pipe it in. **Use `rover graph fetch` (the API schema) for \"what can I query?\" exploration** — it omits federation internals. Reach for `rover supergraph fetch` only when you need composition details (`join__`\u002F`link__` types, subgraph structure):\n\n```bash\n# Overview of a GraphOS graph\nrover graph fetch my-graph@current | rover schema describe -\n\n# Find fields by keyword (results include paths from root operations)\nrover graph fetch my-graph@current | rover schema search - \"playback\"\n\n# Zoom into a coordinate, expanding referenced types one level\nrover graph fetch my-graph@current | rover schema describe - --coord \u003CType.field> --depth 1\n```\n\n**Coordinate forms:** `--coord` accepts a type (`User`), a field (`User.posts`), a field argument (`Type.field(arg:)`), or a directive (`@deprecated`) — omit it for the overview.\n\n**`search` vs `describe`:** reach for `rover schema search` first when matching a concept or keyword and you don't yet know the field name — it finds **nested** fields and shows the path from a root operation. The `describe` overview lists only root fields, so `search` is how you locate fields buried deeper. Use `describe` for the overview or once you know the type\u002Ffield coordinate.\n\nThis enables a closed-loop workflow — search → describe → write a query — with no MCP server setup. See [Schema Exploration](references\u002Fschema.md) for the full command reference, ranking rules, and the save-once pattern for large schemas.\n\n**Running the generated operation:** Rover does **not** execute queries — it only manages and inspects schemas. To actually run a generated query you need the graph's endpoint:\n\n- **Single-subgraph graph:** `rover subgraph list \u003Cgraph@variant>` prints the **Routing Url** — send the query there with `curl`.\n- **Multi-subgraph \u002F federated:** the client endpoint is the **router** URL (find it in GraphOS Studio), not the per-subgraph routing URLs.\n- Don't try to discover the endpoint via the GraphOS Platform API — Rover keeps the API key in its profile\u002Fkeychain, not `$APOLLO_KEY`, so ad-hoc API calls will come back unauthenticated.\n\n## Reference Files\n\nDetailed documentation for specific topics:\n\n- [Init](references\u002Finit.md) - `rover init` project initialization and MCP server setup\n- [Subgraphs](references\u002Fsubgraphs.md) - fetch, publish, check, lint, introspect, delete\n- [Graphs](references\u002Fgraphs.md) - monograph commands (non-federated)\n- [Supergraphs](references\u002Fsupergraphs.md) - compose, fetch, config format\n- [Dev](references\u002Fdev.md) - rover dev for local development\n- [Schema Exploration](references\u002Fschema.md) - describe, search, agent schema discovery workflows\n- [Connectors](references\u002Fconnectors.md) - `rover connector` run, test, list, analyze, generate\n- [Contracts](references\u002Fcontracts.md) - contract variant describe, preview, publish\n- [Persisted Queries](references\u002Fpersisted-queries.md) - generate and publish persisted query manifests\n- [Client Operations](references\u002Fclient.md) - validate client operations, extract GraphQL documents\n- [Configuration](references\u002Fconfiguration.md) - install, auth, env vars, profiles, OAuth login\n- [Additional Commands](references\u002Fadditional-commands.md) - template, readme, api-key, plugin, license, graph-artifact, completion, explain, docs\n\n## Common Patterns\n\n### CI\u002FCD Pipeline\n\n```bash\n# 1. Check schema changes\nrover subgraph check $APOLLO_GRAPH_REF \\\n  --name $SUBGRAPH_NAME \\\n  --schema .\u002Fschema.graphql\n\n# 2. If check passes, publish\nrover subgraph publish $APOLLO_GRAPH_REF \\\n  --name $SUBGRAPH_NAME \\\n  --schema .\u002Fschema.graphql \\\n  --routing-url $ROUTING_URL\n```\n\n### Schema Linting\n\n```bash\n# Lint against GraphOS rules\nrover subgraph lint --name products .\u002Fschema.graphql\n\n# Lint monograph\nrover graph lint my-graph@production .\u002Fschema.graphql\n```\n\n### Output Formats\n\n```bash\n# JSON output for scripting\nrover subgraph fetch my-graph@production --name products --format json\n\n# Plain output (default)\nrover subgraph fetch my-graph@production --name products --format plain\n```\n\n## Ground Rules\n\n- ALWAYS authenticate before using GraphOS commands (`rover auth login`, `rover config auth`, or `APOLLO_KEY`)\n- ALWAYS use the correct graph reference format: `graph@variant`\n- PREFER `rover subgraph check` before `rover subgraph publish` in CI\u002FCD\n- USE `rover dev` for local supergraph development instead of running Router manually\n- USE `rover init` to scaffold new graph projects instead of manual setup\n- NEVER commit `APOLLO_KEY` or `APOLLO_CLIENT_SECRET` to version control; use environment variables\n- USE `--format json` when parsing output programmatically\n- SPECIFY `federation_version` explicitly in supergraph.yaml for reproducibility\n- USE `rover subgraph introspect` to extract schemas from running services\n- USE `rover schema search` \u002F `rover schema describe` (piped from a `fetch`) to explore large schemas instead of loading the full SDL into context\n- NEVER fetch a full schema into context just to explore it — pipe `rover graph fetch`\u002F`introspect` into `rover schema describe`\u002F`search` (a bare `fetch` is only for when the user wants the SDL file itself)\n- USE `rover client check` to validate client operations before deploying client changes\n- USE `rover persisted-queries publish` to register operations for persisted query enforcement\n",{"name":5,"license":15,"metadata":24,"description":27,"allowed-tools":28,"compatibility":29},{"author":25,"version":26},"apollographql","1.2.0","Guide for using Apollo Rover CLI to manage GraphQL schemas and federation. Use this skill when: (1) publishing or fetching subgraph\u002Fgraph schemas, (2) composing supergraph schemas locally or via GraphOS, (3) running local supergraph development with rover dev, (4) validating schemas with check and lint commands, (5) configuring Rover authentication and environment, (6) exploring or searching a graph's schema for agent-driven discovery (rover schema describe \u002F rover schema search), (7) initializing a new graph project or MCP server with rover init, (8) working with Apollo Connectors, contracts, persisted queries, or client operations, (9) managing API keys, plugins, templates, or graph artifacts.\n","Bash(rover:*) Bash(npm:*) Bash(npx:*) Read Write Edit Glob Grep","Node.js v18+, Linux\u002FmacOS\u002FWindows","master","49e49abf2f670d429e0b7e2c0349739c3fdd5cbe","skills\u002Frover",5,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium","https:\u002F\u002Fgithub.com\u002Fstanfish06","https:\u002F\u002Fwww.stanfish.dev\u002F","2026-11-14 21:31:37",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add stanfish06\u002Fskillquarium --skill rover",{"tool":44,"command":45},"bunx","bunx skills add stanfish06\u002Fskillquarium --skill rover",{"tool":47,"command":48},"pnpm","pnpm dlx skills add stanfish06\u002Fskillquarium --skill rover","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Frover\u002FSKILL.md",true,[52,58,62,66,70,74,78,82,86,90,94,98],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fadditional-commands.md","REFERENCE","参考文档",5450,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Frover\u002Freferences\u002Fadditional-commands.md",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fclient.md",3449,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Frover\u002Freferences\u002Fclient.md",{"path":63,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fconfiguration.md",6391,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Frover\u002Freferences\u002Fconfiguration.md",{"path":67,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fconnectors.md",6945,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Frover\u002Freferences\u002Fconnectors.md",{"path":71,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fcontracts.md",6242,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Frover\u002Freferences\u002Fcontracts.md",{"path":75,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fdev.md",5760,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Frover\u002Freferences\u002Fdev.md",{"path":79,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fgraphs.md",4620,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Frover\u002Freferences\u002Fgraphs.md",{"path":83,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Finit.md",6284,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Frover\u002Freferences\u002Finit.md",{"path":87,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fpersisted-queries.md",5617,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Frover\u002Freferences\u002Fpersisted-queries.md",{"path":91,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fschema.md",9220,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Frover\u002Freferences\u002Fschema.md",{"path":95,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fsubgraphs.md",6069,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Frover\u002Freferences\u002Fsubgraphs.md",{"path":99,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fsupergraphs.md",5717,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Frover\u002Freferences\u002Fsupergraphs.md",[103,110,119,126,133,140],{"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},"01M76ZJTRVA456GD7K8Y3EP82H","zarr-python","Stores and queries chunked N-D scientific arrays with Zarr-Python 3, including codecs, sharding, S3\u002FGCS storage, and NumPy\u002FDask\u002FXarray integration. Use for array layout, bounded I\u002FO, format migration, or scientific metadata preservation.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":114,"licenseFileUrl":115,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":19},"01M76ZJQZ15Q1HKC5V85NHE325","yeet","Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":114,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":19},"01M76ZJ8ASZ4QYQ70Y6SBA4Z4S","xarray","N-dimensional labeled arrays and datasets in Python. Built on top of NumPy and Dask. It introduces labels in the form of dimensions, coordinates, and attributes on top of raw NumPy-like arrays, making data analysis in physical sciences more intuitive and less error-prone. Use for working with multi-dimensional scientific data, NetCDF\u002FGRIB\u002FZarr files, climate\u002Fweather\u002Foceanographic datasets, remote sensing, geospatial imaging, large out-of-memory datasets with Dask, and labeled array operations.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fxarray\u002FSKILL.md",[],[],{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":19},"01M76ZHFBXD6VXPQ02VCEG202B","writing-mstest-tests","Use when asked to fix, rewrite, update, improve, modernize, show corrected code for, or explain existing MSTest tests or MSTest-specific configuration. Use for \"review\" when corrected code or edits are wanted, even for one pasted assertion or passing tests with bad failure output. Covers expected\u002Factual labels; generic Boolean, collection, string, numeric, null, identity, exception, hard-cast, and object[] checks; TestContext\u002Flifecycle; timeout\u002Fcancellation; OS\u002FCI conditions, retry, cleanup, parallelization, MSTest.Sdk project setup, and MSTESTxxxx. Honor the installed MSTest version. DO NOT USE to design new test cases (code-testing), perform report-only audits, create project files rather than explain MSTest setup, run tests, migrate frameworks, or handle non-MSTest\u002Fnon-.NET code.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwriting-mstest-tests\u002FSKILL.md",[],[],{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":19},"01M76ZDFDF4N88RH6HSYGS7GP2","wgs-prs","End-to-end WGS to polygenic risk score pipeline. Takes paired-end FASTQ files (or a pre-existing VCF) through nf-core\u002Fsarek for variant calling, applies VCF QC (normalisation, hard filtering, Ti\u002FTv and Het\u002FHom checks), then computes polygenic risk scores via the PGS Catalog. Fills the FASTQ to VCF gap upstream of the gwas-prs skill.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwgs-prs\u002FSKILL.md",[],[],{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":114,"licenseFileUrl":144,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":19},"01M76ZCC1SC68J42QK4MDC8RCG","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[]]