[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CTRVK1TSWD7XDZJ2MH6DWH":3,"skill-same:01M7CTRVK1TSWD7XDZJ2MH6DWH":47},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M7CTRVK1TSWD7XDZJ2MH6DWH","copilotkit-cli",null,"Use for the CopilotKit CLI — `npx copilotkit@latest`. Covers proving a project's wiring with `verify` before debugging anything by hand, scaffolding with `create`, signing in and selecting a hosted Intelligence project, agent-assisted onboarding of an existing app, generating type-safe agent ids, and importing thread history. Reach for `verify` first whenever a CopilotKit app is not working.","amoai-tech\u002Fmdeai","amoai-tech","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F320616881?v=4","01M7CTJYGWP82J2HHMQC5NN9JP","amo","01M7CTJYHE5YQRGQSDJES3Z0QE",2,"MIT","https:\u002F\u002Fgithub.com\u002Famoai-tech\u002Fmdeai\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcopilotkit\u002Freferences\u002Fofficial\u002Fcopilotkit-cli\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: copilotkit-cli\ndescription: \"Use for the CopilotKit CLI — `npx copilotkit@latest`. Covers proving a project's wiring with `verify` before debugging anything by hand, scaffolding with `create`, signing in and selecting a hosted Intelligence project, agent-assisted onboarding of an existing app, generating type-safe agent ids, and importing thread history. Reach for `verify` first whenever a CopilotKit app is not working.\"\nversion: 1.1.0\n---\n\n# CopilotKit CLI\n\n```bash\nnpx copilotkit@latest \u003Ccommand> --via skill:copilotkit-cli\n```\n\nKeep `--via skill:copilotkit-cli` on every command you run from this skill. It only tells\nCopilotKit's telemetry that the call came from this skill, and the command ignores it.\nIf the CLI reports `Unknown option '--via'`, npx ran an old cached version: run the command\nagain without the flag.\n\n`--help` on any command prints its flags. The commands below are the ones worth knowing\nbefore you start reading someone's project by hand.\n\n## `verify` — do this before debugging\n\nFirst decide whether the app uses hosted Intelligence. `verify` checks for it by default, and\nan open-source app fails those checks every time.\n\n- **No Intelligence:** nothing constructs `CopilotKitIntelligence` where the runtime is\n  built, and there is no `.copilotkit\u002Fproject.json`. Run the open-source check, with an agent\n  id the runtime registers:\n\n  ```bash\n  npx copilotkit@latest verify --expect-runtime oss --round-trip --agent \u003Cid> --json --via skill:copilotkit-cli\n  ```\n\n  `--round-trip --agent \u003Cid>` is required here. Without it the round trip is not attempted\n  and the command cannot pass.\n\n- **Otherwise:** run the default check.\n\n  ```bash\n  npx copilotkit@latest verify --json --via skill:copilotkit-cli\n  ```\n\nDo not run `login` or `project select` only to make `verify` pass. Those commands set up\nhosted Intelligence. They do not fix an open-source app, and `verify` still fails on it\nafterward, because the runtime never consumes the credential.\n\nOne command replaces the manual survey. It settles up to eleven things: a hosted project is\nselected; the project API key is present, loadable by the app, and authenticates; the runtime\nresponds, declares an agent, actually consumes the credential, and serves the thread routes;\nthe frontend serves its own assets; the runtime accepts the browser's origin; and the\ninstalled CopilotKit packages match the version the runtime reports. It also reports the\nruntime version, the agent framework in use, whether transcription is wired, the realtime\ngateway wiring, and the license state.\n\nEleven is the ceiling, not a promise. The last three are omitted when there was nothing to\ncheck them against — no frontend origin was found, or no installed packages were. Count\n`checks[]` rather than assuming a fixed set. With `--expect-runtime oss` the hosted-project\nand credential checks do not apply at all, so that run is a smaller set.\n\nCrucially it names **which URL it probed and where that URL came from** — the project's\n`runtimeUrl`, an environment variable, the app's own dev configuration, or an assumed\ndefault. A survey done by hand cannot tell you that, and the provenance changes the verdict:\nnothing answering at a URL **the project named** is a FAIL, while nothing answering at an\n**assumed** default is UNKNOWN, because an app on a port the command never learned is not a\nwiring failure.\n\nUseful flags:\n\n- `--frontend-url \u003Corigin you actually open>` — adds the browser-facing checks, including a\n  real CORS preflight when that origin differs from the runtime's\n- `--round-trip` — also runs the agent and reads its answer back. Costs a model call, so it\n  is opt-in\n- `--expect-runtime oss` — for a self-hosted runtime with no Intelligence. It exits zero\n  only when `\u002Finfo` declares the named agent, reports no Intelligence entitlement, and\n  `--round-trip --agent \u003Cid>` passes\n- `--agent \u003Cid>` — which declared agent to run, when several are registered\n- `--runtime-url \u003Curl>` — probe this endpoint instead of the one read from the project\n- `--header '\u003Cname>: \u003Cvalue>'` — repeatable. Needed when the project's `identifyUser` reads\n  a session the CLI does not carry\n- `--timeout \u003Cseconds>` — how long to wait for an answer, default 90\n\nRead `checks[]` and fix in the order given:\n\n- The checks **chain**. A later check that could not run says so and names the earlier one to\n  fix first, so the first failure is the real one.\n- `UNKNOWN` means the check could not run. It never means the check passed, and the command\n  exits non-zero unless every check passed.\n\n### What `verify` does not cover\n\nReach past it only once it is clean.\n\n- **Tool execution.** `--round-trip` deliberately asks a question that needs no tools and\n  sends no context, so a passing round trip says nothing about whether your tools work.\n- **Event ordering and streaming.** It reports pass or fail on a run, not the sequence inside\n  it. A run that starts and never finishes, or stalls mid-stream, is a job for the Inspector.\n- **State synchronisation.** Snapshot-versus-delta divergence is agent behaviour, not wiring.\n\n## Starting a project\n\n```bash\nnpx copilotkit@latest init --via skill:copilotkit-cli   # `create` is an alias for it\n```\n\nPrompts for a name and framework, scaffolds a starter, signs you in when needed, and connects\nthe app to a cloud-hosted Intelligence project. The name it asks for names the new directory,\nso this is the path for a project that does not exist yet. For an app you already have, use\n`onboard start` below.\n\nTo add CopilotKit to an existing app, either follow the [quickstart](\u002Fquickstart), or hand\nthe job to your coding agent:\n\n```bash\nnpx copilotkit@latest onboard start --via skill:copilotkit-cli\n```\n\nThat runs an agent-guided flow over the repository you are already in, with checkpoints and\nproof steps rather than a scaffold. `onboard start --intent \u003Cfeature>` targets one feature on\nan app that already has CopilotKit.\n\n## Signing in and picking a project\n\n```bash\nnpx copilotkit@latest login --json --via skill:copilotkit-cli   # agent-readable JSON lines, no browser launch\nnpx copilotkit@latest login --via skill:copilotkit-cli          # interactive: opens a browser\nnpx copilotkit@latest whoami --via skill:copilotkit-cli         # who is signed in, and the active organization\nnpx copilotkit@latest project select --via skill:copilotkit-cli # pick or create a hosted project for this directory\nnpx copilotkit@latest project list --json --via skill:copilotkit-cli\n```\n\nUse `login --json` when you are driving the CLI. Bare `login` tries to open a browser, which\nis not something you can complete.\n\nThere is no `auth` command. It is `login`.\n\n`project select` records the choice in `.copilotkit\u002Fproject.json` and provisions a\nproject-scoped runtime key into `.env`:\n\n```\nCPK_INTELLIGENCE_API_KEY=cpk_...\n```\n\n`CPK_INTELLIGENCE_API_KEY` is the canonical name and the only one the CLI writes. Keep it\nserver-side — it is a runtime key, not a frontend token, so it takes **no** `NEXT_PUBLIC_` or\n`VITE_` prefix. Do not set the platform URLs: they default to the managed hosts, so any value\nyou supply can only replace a correct default with a worse one.\n\nWithout a TTY — which is what a coding agent has — use `project list --json` to see the\nchoices and `project select --project \u003Cid>` or `--create \u003Cname>` to name the answer up front.\n\n## Other commands\n\n| Command                                    | What it does                                                                   |\n| ------------------------------------------ | ------------------------------------------------------------------------------ |\n| `skills install`                           | Installs these skills into a project (`skills onboard` also starts onboarding) |\n| `typegen`                                  | Generates type-safe agent ids from a running runtime                           |\n| `import --source adk\\|langgraph --dry-run` | Previews importing historical threads into Intelligence                        |\n| `license create` \u002F `license list`          | Issues and lists license tokens                                                |\n| `channels`                                 | Sets up managed Intelligence Channels for Slack or Microsoft Teams             |\n| `framework list`                           | The agent frameworks `create` accepts, and their flags                         |\n| `logs`                                     | The CLI log path, or recent lines                                              |\n| `telemetry`                                | Shows or changes the CLI telemetry preference                                  |\n| `docs`                                     | Opens the documentation                                                        |\n| `version`                                  | Version, build, and commit                                                     |\n\nThe CLI collects usage data. `DO_NOT_TRACK=1` or `COPILOTKIT_TELEMETRY_DISABLED=1` opts out.\n","# CopilotKit CLI\n\n```bash\nnpx copilotkit@latest \u003Ccommand> --via skill:copilotkit-cli\n```\n\nKeep `--via skill:copilotkit-cli` on every command you run from this skill. It only tells\nCopilotKit's telemetry that the call came from this skill, and the command ignores it.\nIf the CLI reports `Unknown option '--via'`, npx ran an old cached version: run the command\nagain without the flag.\n\n`--help` on any command prints its flags. The commands below are the ones worth knowing\nbefore you start reading someone's project by hand.\n\n## `verify` — do this before debugging\n\nFirst decide whether the app uses hosted Intelligence. `verify` checks for it by default, and\nan open-source app fails those checks every time.\n\n- **No Intelligence:** nothing constructs `CopilotKitIntelligence` where the runtime is\n  built, and there is no `.copilotkit\u002Fproject.json`. Run the open-source check, with an agent\n  id the runtime registers:\n\n  ```bash\n  npx copilotkit@latest verify --expect-runtime oss --round-trip --agent \u003Cid> --json --via skill:copilotkit-cli\n  ```\n\n  `--round-trip --agent \u003Cid>` is required here. Without it the round trip is not attempted\n  and the command cannot pass.\n\n- **Otherwise:** run the default check.\n\n  ```bash\n  npx copilotkit@latest verify --json --via skill:copilotkit-cli\n  ```\n\nDo not run `login` or `project select` only to make `verify` pass. Those commands set up\nhosted Intelligence. They do not fix an open-source app, and `verify` still fails on it\nafterward, because the runtime never consumes the credential.\n\nOne command replaces the manual survey. It settles up to eleven things: a hosted project is\nselected; the project API key is present, loadable by the app, and authenticates; the runtime\nresponds, declares an agent, actually consumes the credential, and serves the thread routes;\nthe frontend serves its own assets; the runtime accepts the browser's origin; and the\ninstalled CopilotKit packages match the version the runtime reports. It also reports the\nruntime version, the agent framework in use, whether transcription is wired, the realtime\ngateway wiring, and the license state.\n\nEleven is the ceiling, not a promise. The last three are omitted when there was nothing to\ncheck them against — no frontend origin was found, or no installed packages were. Count\n`checks[]` rather than assuming a fixed set. With `--expect-runtime oss` the hosted-project\nand credential checks do not apply at all, so that run is a smaller set.\n\nCrucially it names **which URL it probed and where that URL came from** — the project's\n`runtimeUrl`, an environment variable, the app's own dev configuration, or an assumed\ndefault. A survey done by hand cannot tell you that, and the provenance changes the verdict:\nnothing answering at a URL **the project named** is a FAIL, while nothing answering at an\n**assumed** default is UNKNOWN, because an app on a port the command never learned is not a\nwiring failure.\n\nUseful flags:\n\n- `--frontend-url \u003Corigin you actually open>` — adds the browser-facing checks, including a\n  real CORS preflight when that origin differs from the runtime's\n- `--round-trip` — also runs the agent and reads its answer back. Costs a model call, so it\n  is opt-in\n- `--expect-runtime oss` — for a self-hosted runtime with no Intelligence. It exits zero\n  only when `\u002Finfo` declares the named agent, reports no Intelligence entitlement, and\n  `--round-trip --agent \u003Cid>` passes\n- `--agent \u003Cid>` — which declared agent to run, when several are registered\n- `--runtime-url \u003Curl>` — probe this endpoint instead of the one read from the project\n- `--header '\u003Cname>: \u003Cvalue>'` — repeatable. Needed when the project's `identifyUser` reads\n  a session the CLI does not carry\n- `--timeout \u003Cseconds>` — how long to wait for an answer, default 90\n\nRead `checks[]` and fix in the order given:\n\n- The checks **chain**. A later check that could not run says so and names the earlier one to\n  fix first, so the first failure is the real one.\n- `UNKNOWN` means the check could not run. It never means the check passed, and the command\n  exits non-zero unless every check passed.\n\n### What `verify` does not cover\n\nReach past it only once it is clean.\n\n- **Tool execution.** `--round-trip` deliberately asks a question that needs no tools and\n  sends no context, so a passing round trip says nothing about whether your tools work.\n- **Event ordering and streaming.** It reports pass or fail on a run, not the sequence inside\n  it. A run that starts and never finishes, or stalls mid-stream, is a job for the Inspector.\n- **State synchronisation.** Snapshot-versus-delta divergence is agent behaviour, not wiring.\n\n## Starting a project\n\n```bash\nnpx copilotkit@latest init --via skill:copilotkit-cli   # `create` is an alias for it\n```\n\nPrompts for a name and framework, scaffolds a starter, signs you in when needed, and connects\nthe app to a cloud-hosted Intelligence project. The name it asks for names the new directory,\nso this is the path for a project that does not exist yet. For an app you already have, use\n`onboard start` below.\n\nTo add CopilotKit to an existing app, either follow the [quickstart](\u002Fquickstart), or hand\nthe job to your coding agent:\n\n```bash\nnpx copilotkit@latest onboard start --via skill:copilotkit-cli\n```\n\nThat runs an agent-guided flow over the repository you are already in, with checkpoints and\nproof steps rather than a scaffold. `onboard start --intent \u003Cfeature>` targets one feature on\nan app that already has CopilotKit.\n\n## Signing in and picking a project\n\n```bash\nnpx copilotkit@latest login --json --via skill:copilotkit-cli   # agent-readable JSON lines, no browser launch\nnpx copilotkit@latest login --via skill:copilotkit-cli          # interactive: opens a browser\nnpx copilotkit@latest whoami --via skill:copilotkit-cli         # who is signed in, and the active organization\nnpx copilotkit@latest project select --via skill:copilotkit-cli # pick or create a hosted project for this directory\nnpx copilotkit@latest project list --json --via skill:copilotkit-cli\n```\n\nUse `login --json` when you are driving the CLI. Bare `login` tries to open a browser, which\nis not something you can complete.\n\nThere is no `auth` command. It is `login`.\n\n`project select` records the choice in `.copilotkit\u002Fproject.json` and provisions a\nproject-scoped runtime key into `.env`:\n\n```\nCPK_INTELLIGENCE_API_KEY=cpk_...\n```\n\n`CPK_INTELLIGENCE_API_KEY` is the canonical name and the only one the CLI writes. Keep it\nserver-side — it is a runtime key, not a frontend token, so it takes **no** `NEXT_PUBLIC_` or\n`VITE_` prefix. Do not set the platform URLs: they default to the managed hosts, so any value\nyou supply can only replace a correct default with a worse one.\n\nWithout a TTY — which is what a coding agent has — use `project list --json` to see the\nchoices and `project select --project \u003Cid>` or `--create \u003Cname>` to name the answer up front.\n\n## Other commands\n\n| Command                                    | What it does                                                                   |\n| ------------------------------------------ | ------------------------------------------------------------------------------ |\n| `skills install`                           | Installs these skills into a project (`skills onboard` also starts onboarding) |\n| `typegen`                                  | Generates type-safe agent ids from a running runtime                           |\n| `import --source adk\\|langgraph --dry-run` | Previews importing historical threads into Intelligence                        |\n| `license create` \u002F `license list`          | Issues and lists license tokens                                                |\n| `channels`                                 | Sets up managed Intelligence Channels for Slack or Microsoft Teams             |\n| `framework list`                           | The agent frameworks `create` accepts, and their flags                         |\n| `logs`                                     | The CLI log path, or recent lines                                              |\n| `telemetry`                                | Shows or changes the CLI telemetry preference                                  |\n| `docs`                                     | Opens the documentation                                                        |\n| `version`                                  | Version, build, and commit                                                     |\n\nThe CLI collects usage data. `DO_NOT_TRACK=1` or `COPILOTKIT_TELEMETRY_DISABLED=1` opts out.\n",{"name":5,"version":24,"description":7},"1.1.0","main","9955f6a8aa5de3c14fea562c7e6b72973366ba3c",".claude\u002Fskills\u002Fcopilotkit\u002Freferences\u002Fofficial\u002Fcopilotkit-cli",1,"https:\u002F\u002Fgithub.com\u002Famoai-tech\u002Fmdeai","https:\u002F\u002Fmdeai-psi.vercel.app","https:\u002F\u002Fgithub.com\u002Famoai-tech","2026-11-13 03:54:16",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add amoai-tech\u002Fmdeai --skill copilotkit-cli",{"tool":39,"command":40},"bunx","bunx skills add amoai-tech\u002Fmdeai --skill copilotkit-cli",{"tool":42,"command":43},"pnpm","pnpm dlx skills add amoai-tech\u002Fmdeai --skill copilotkit-cli","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Famoai-tech\u002Fmdeai\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcopilotkit\u002Freferences\u002Fofficial\u002Fcopilotkit-cli\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7CV3D59CQX8N178NN3W5DEQ","mde-pr-review-supabase","Use when reviewing MDE Supabase SQL, Auth and RLS changes in a pull request.","https:\u002F\u002Fgithub.com\u002Famoai-tech\u002Fmdeai\u002Fblob\u002Fmain\u002Fscripts\u002Fpr-agent\u002Fskills\u002Fsupabase\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7CV39XR1SPH7C4FNXAXMM36","mde-pr-review-stripe","Use when reviewing MDE Stripe payments and webhooks changes in a pull request.","https:\u002F\u002Fgithub.com\u002Famoai-tech\u002Fmdeai\u002Fblob\u002Fmain\u002Fscripts\u002Fpr-agent\u002Fskills\u002Fstripe\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7CV37HHNM5A144SEX2VE05N","mde-pr-review-nextjs","Use when reviewing MDE Next.js App Router changes in a pull request.","https:\u002F\u002Fgithub.com\u002Famoai-tech\u002Fmdeai\u002Fblob\u002Fmain\u002Fscripts\u002Fpr-agent\u002Fskills\u002Fnextjs\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7CV34C1M5STTKHX5CGVN3VS","mde-pr-review-mastra","Use when reviewing MDE Mastra agent, tool and workflow changes in a pull request.","https:\u002F\u002Fgithub.com\u002Famoai-tech\u002Fmdeai\u002Fblob\u002Fmain\u002Fscripts\u002Fpr-agent\u002Fskills\u002Fmastra\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7CV31A37VPRRASAVGE8K8SN","mde-pr-review-maps","Use when reviewing MDE Google Maps and Places changes in a pull request.","https:\u002F\u002Fgithub.com\u002Famoai-tech\u002Fmdeai\u002Fblob\u002Fmain\u002Fscripts\u002Fpr-agent\u002Fskills\u002Fmaps\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7CV2Y70DQJ1VXFHS732CSQ4","mde-pr-review-copilotkit","Use when reviewing MDE CopilotKit and AG-UI changes in a pull request.","https:\u002F\u002Fgithub.com\u002Famoai-tech\u002Fmdeai\u002Fblob\u002Fmain\u002Fscripts\u002Fpr-agent\u002Fskills\u002Fcopilotkit\u002FSKILL.md",[],[]]