[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MJ3XTM1GZDMQZTRTSX8N7R":3,"skill-same:01M6MJ3XTM1GZDMQZTRTSX8N7R":115},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M6MJ3XTM1GZDMQZTRTSX8N7R","use-sealos",null,"Deploy and operate apps on Sealos Cloud: sign in to a Sealos account, deploy any project or self-hosted app (from the template store, an official Docker image, or project source code), provision managed databases (PostgreSQL, MySQL, MongoDB, Redis, Kafka), create S3-compatible object storage, expose public HTTPS domains, check status and logs, and troubleshoot failures. Use this skill whenever the user mentions Sealos (in any language, e.g. \"部署到 Sealos\"), or asks to deploy, host, or self-host an application, website, or database without naming another platform. Typical trigger: \"deploy X to Sealos\" \u002F \"帮我把 X 部署到 Sealos\".","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Flabring\u002Fsealos-skills\u002Fplugins\u002Fsealos\u002Fskills\u002Fuse-sealos\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"use sealos","use","databases","managed","operate","domains","apps","host","app","project","self","image","Bash","mongodb","logs","postgresql","mysql","database","code","official","2026-11-10 10:12:30",false,"---\nname: use-sealos\ndescription: >\n  Deploy and operate apps on Sealos Cloud: sign in to a Sealos account, deploy\n  any project or self-hosted app (from the template store, an official Docker\n  image, or project source code), provision managed databases (PostgreSQL,\n  MySQL, MongoDB, Redis, Kafka), create S3-compatible object storage, expose\n  public HTTPS domains, check status and logs, and troubleshoot failures. Use\n  this skill whenever the user mentions Sealos (in any language, e.g. \"部署到\n  Sealos\"), or asks to deploy, host, or self-host an application, website, or\n  database without naming another platform. Typical trigger: \"deploy X to\n  Sealos\" \u002F \"帮我把 X 部署到 Sealos\".\nallowed-tools: Bash(kubectl:*), Bash(python3:*), Bash(docker:*), Bash(curl:*), Bash(bash:*), Bash(git:*), Bash(gh:*), Bash(command:*)\n---\n\n# Use Sealos\n\n## Sealos resource model\n\nSealos Cloud is a multi-tenant Kubernetes platform. Everything a user owns\nlives in one **namespace** (`ns-xxx`) per **workspace**, accessed with a\nrestricted **kubeconfig** (`~\u002F.sealos\u002Fkubeconfig`). Within the namespace:\n\n- **Apps** are ordinary Deployments\u002FStatefulSets + Service + Ingress, labeled\n  `cloud.sealos.io\u002Fapp-deploy-manager: \u003Capp>` so the Sealos \"App Launchpad\" UI\n  can manage them. Public HTTPS comes free via `\u003Chost>.\u003Cregion-domain>` and a\n  wildcard cert.\n- **Databases** are KubeBlocks `Cluster` CRs managed by the \"Database\" UI.\n- **Template store** hosts 200+ one-click templates (`sealos-api.py\n  store-list`); deployed templates are tracked as instances and appear in the\n  UI.\n- **Object storage** buckets are `ObjectStorageBucket` CRs with S3-compatible\n  credentials in managed secrets.\n- A **region** is one cluster + domain (e.g. `usw-1.sealos.io` for\n  international, `bja.sealos.run` etc. for China). The Template API lives at\n  `https:\u002F\u002Ftemplate.\u003Cregion-domain>`.\n\n## Tools\n\nResolve `scripts\u002F` and `references\u002F` against this skill's directory, not the\nproject working directory.\n\n- `scripts\u002Fsealos-api.py` — auth (`status`, `login`, `workspaces`, `switch`)\n  and the Template API (`deploy`, `store-list`). Deploying through the\n  Template API (not raw `kubectl apply`) is what makes resources show up as a\n  deletable unit in the Sealos UI.\n- `kubectl` with `export KUBECONFIG=~\u002F.sealos\u002Fkubeconfig` — all reads,\n  debugging, and deletions. The kubeconfig is namespace-scoped; you cannot see\n  or touch other tenants.\n- `scripts\u002Fwait-app.sh` — post-deploy verification (workload readiness + URL\n  probe + failure diagnostics).\n- `docker buildx` — only for the source-build path.\n\n## Preflight\n\nIf `SEALAI_DEPLOY_MODE` is `managed` (a Brain-managed sandbox), stop here and\nfollow [..\u002Fsealos-deploy\u002FSKILL.md](..\u002Fsealos-deploy\u002FSKILL.md) instead — that\nmode forbids login and interactive prompts. Everything below is the local\ninteractive path.\n\n```bash\npython3 scripts\u002Fsealos-api.py status\n```\n\n- `authenticated: true` → proceed; note `namespace` and `region_domain`.\n- Not authenticated → run `python3 scripts\u002Fsealos-api.py login` **in the\n  background**, watch its stderr, and relay the sign-in URL to the user the\n  moment it prints (the code expires; never sit silently until the command\n  ends). Users can alternatively paste a kubeconfig from the Sealos web\n  console (top-left avatar → kubeconfig) into `~\u002F.sealos\u002Fkubeconfig`.\n- Wrong region? `login --region \u003Curl>`. Wrong workspace? `workspaces` +\n  `switch \u003Cname>`.\n\nDeploys, database creation, and storage consume the account's quota\u002Fbalance —\nif a deploy is rejected with a quota error, report it; do not silently retry\nwith smaller numbers.\n\n## Deploy decision tree (the 15-minute path)\n\nWhen the user wants something deployed, classify it FIRST — the wrong path\nwastes the whole time budget:\n\n1. **Known self-hosted product** (Uptime Kuma, Metabase, n8n, ...):\n   `python3 scripts\u002Fsealos-api.py store-list --search \u003Cname>`.\n   - Store hit → deploy the store template ([deploy.md](references\u002Fdeploy.md),\n     Path A). Fastest and battle-tested; done in ~3 min.\n   - No store hit → check [recipes.md](references\u002Frecipes.md) for a\n     ready-made recipe, else use the official Docker image and write a\n     template ([deploy.md](references\u002Fdeploy.md), Path B). **Never build a\n     product from source when an official image exists.**\n2. **User's own project (has source code)**: look for an existing\n   Dockerfile\u002Fcompose file, else generate one, build for **linux\u002Famd64**,\n   push, then deploy the image ([build.md](references\u002Fbuild.md) then\n   [deploy.md](references\u002Fdeploy.md) Path B).\n3. **Just a database \u002F bucket**: [databases.md](references\u002Fdatabases.md) \u002F\n   platform.md's object storage section — deploy as a minimal template.\n\nAfter ANY deploy, verify before reporting:\n\n```bash\nbash scripts\u002Fwait-app.sh -u https:\u002F\u002F\u003Chost>.\u003Cregion-domain> deployment\u002F\u003Cname> [cluster\u002F\u003Cname>-pg ...]\n```\n\nOn `*.sealos.io` regions, local deploys also claim a Brain Project in-script;\nif `brain_adoption.ok` is false, or `warnings` still lists\n`incompleteResourceSet` after verify, run `sealos-api.py adopt \u003Cinstance>` —\nnever redeploy. On `*.sealos.run` this is skipped\n(`brain_adoption.reason: not-sealos-io`). See\n[deploy.md](references\u002Fdeploy.md).\n\n## Quick operations\n\n```bash\nexport KUBECONFIG=~\u002F.sealos\u002Fkubeconfig\nkubectl get deploy,sts,pods                                   # what's running\nkubectl get clusters.apps.kubeblocks.io                       # databases\nkubectl get ingress -o custom-columns='NAME:.metadata.name,HOST:.spec.rules[0].host'  # public URLs\nkubectl logs deploy\u002F\u003Cname> --tail=100                         # app logs\nkubectl describe pod \u003Cpod>                                    # scheduling\u002Fpull issues\nkubectl get events --field-selector type=Warning --sort-by=.lastTimestamp | tail -20\nkubectl scale deploy\u002F\u003Cname> --replicas=2                      # scale\npython3 scripts\u002Fsealos-api.py store-list --search \u003Cquery>     # template store\n```\n\n## Routing\n\n| Intent | Reference |\n|---|---|\n| Deploy anything (store template, image, or built artifact) | [deploy.md](references\u002Fdeploy.md) |\n| Dockerfile \u002F image build \u002F registry push for user source | [build.md](references\u002Fbuild.md) |\n| Provision or connect PostgreSQL\u002FMySQL\u002FMongoDB\u002FRedis\u002FKafka | [databases.md](references\u002Fdatabases.md) |\n| Manifest rules when writing template YAML (labels, Ingress, storage, quota ladder, object storage) | [platform.md](references\u002Fplatform.md) |\n| Status, logs, debugging, scaling, deletion, cost hygiene | [operate.md](references\u002Foperate.md) |\n| Per-app recipes for popular self-hosted software | [recipes.md](references\u002Frecipes.md) |\n| Brain managed sandbox (`SEALAI_DEPLOY_MODE=managed`) | [..\u002Fsealos-deploy\u002FSKILL.md](..\u002Fsealos-deploy\u002FSKILL.md) |\n\nLoad only what the task needs — usually one reference, two at most.\n\n## Execution rules\n\n1. **Never report a deploy as successful without evidence**: `wait-app.sh`\n   exits 0 AND the public URL returns a real page (2xx\u002F3xx, and for\n   SSR apps the body is not an error page). If verification fails, triage via\n   [operate.md](references\u002Foperate.md) — do not re-deploy blindly.\n2. Production images are built and pushed as **linux\u002Famd64** (`docker buildx\n   build --platform linux\u002Famd64`). Apple Silicon defaults produce arm64\n   images that crash-loop on Sealos with `exec format error`.\n3. Resource requests\u002Flimits follow the platform ladder\n   ([platform.md](references\u002Fplatform.md)); requests are derived from limits,\n   and memory always uses `Mi` values.\n4. Deploy through the Template API. Fall back to `kubectl apply` only for\n   single resources during debugging, and remember `kubectl apply` rejects\n   Deployment+`volumeClaimTemplates` (use StatefulSet).\n5. Destructive actions (deleting apps, databases, buckets; switching\n   workspace on a shared machine), public-access changes, credential rotation,\n   and system-tool installation require explicit user confirmation first.\n6. Never print secret values. Read them into shell variables or pipe them;\n   show the user only names and how to fetch values.\n7. After mutations, read back state (`kubectl get ...`) before describing it.\n8. One deploy at a time per app name; name collisions in a shared namespace\n   break selectors. Random suffixes (`-a1b2c3d4`) are there for a reason —\n   keep them.\n9. If the agent sandbox blocks writes outside the workspace, escalate file\n   access for writing `~\u002F.sealos\u002Fkubeconfig`, using the Docker socket, and any\n   command that must read that kubeconfig.\n\n## Response format\n\nAfter each operation report: what was deployed\u002Fchanged (names + namespace),\nthe public URL if any, verification evidence (ready state, HTTP code), and\ncredentials location (secret names, never values). On failure: the failing\nresource, the decisive log\u002Fevent lines, and the next action you are taking.\n","# Use Sealos\n\n## Sealos resource model\n\nSealos Cloud is a multi-tenant Kubernetes platform. Everything a user owns\nlives in one **namespace** (`ns-xxx`) per **workspace**, accessed with a\nrestricted **kubeconfig** (`~\u002F.sealos\u002Fkubeconfig`). Within the namespace:\n\n- **Apps** are ordinary Deployments\u002FStatefulSets + Service + Ingress, labeled\n  `cloud.sealos.io\u002Fapp-deploy-manager: \u003Capp>` so the Sealos \"App Launchpad\" UI\n  can manage them. Public HTTPS comes free via `\u003Chost>.\u003Cregion-domain>` and a\n  wildcard cert.\n- **Databases** are KubeBlocks `Cluster` CRs managed by the \"Database\" UI.\n- **Template store** hosts 200+ one-click templates (`sealos-api.py\n  store-list`); deployed templates are tracked as instances and appear in the\n  UI.\n- **Object storage** buckets are `ObjectStorageBucket` CRs with S3-compatible\n  credentials in managed secrets.\n- A **region** is one cluster + domain (e.g. `usw-1.sealos.io` for\n  international, `bja.sealos.run` etc. for China). The Template API lives at\n  `https:\u002F\u002Ftemplate.\u003Cregion-domain>`.\n\n## Tools\n\nResolve `scripts\u002F` and `references\u002F` against this skill's directory, not the\nproject working directory.\n\n- `scripts\u002Fsealos-api.py` — auth (`status`, `login`, `workspaces`, `switch`)\n  and the Template API (`deploy`, `store-list`). Deploying through the\n  Template API (not raw `kubectl apply`) is what makes resources show up as a\n  deletable unit in the Sealos UI.\n- `kubectl` with `export KUBECONFIG=~\u002F.sealos\u002Fkubeconfig` — all reads,\n  debugging, and deletions. The kubeconfig is namespace-scoped; you cannot see\n  or touch other tenants.\n- `scripts\u002Fwait-app.sh` — post-deploy verification (workload readiness + URL\n  probe + failure diagnostics).\n- `docker buildx` — only for the source-build path.\n\n## Preflight\n\nIf `SEALAI_DEPLOY_MODE` is `managed` (a Brain-managed sandbox), stop here and\nfollow [..\u002Fsealos-deploy\u002FSKILL.md](..\u002Fsealos-deploy\u002FSKILL.md) instead — that\nmode forbids login and interactive prompts. Everything below is the local\ninteractive path.\n\n```bash\npython3 scripts\u002Fsealos-api.py status\n```\n\n- `authenticated: true` → proceed; note `namespace` and `region_domain`.\n- Not authenticated → run `python3 scripts\u002Fsealos-api.py login` **in the\n  background**, watch its stderr, and relay the sign-in URL to the user the\n  moment it prints (the code expires; never sit silently until the command\n  ends). Users can alternatively paste a kubeconfig from the Sealos web\n  console (top-left avatar → kubeconfig) into `~\u002F.sealos\u002Fkubeconfig`.\n- Wrong region? `login --region \u003Curl>`. Wrong workspace? `workspaces` +\n  `switch \u003Cname>`.\n\nDeploys, database creation, and storage consume the account's quota\u002Fbalance —\nif a deploy is rejected with a quota error, report it; do not silently retry\nwith smaller numbers.\n\n## Deploy decision tree (the 15-minute path)\n\nWhen the user wants something deployed, classify it FIRST — the wrong path\nwastes the whole time budget:\n\n1. **Known self-hosted product** (Uptime Kuma, Metabase, n8n, ...):\n   `python3 scripts\u002Fsealos-api.py store-list --search \u003Cname>`.\n   - Store hit → deploy the store template ([deploy.md](references\u002Fdeploy.md),\n     Path A). Fastest and battle-tested; done in ~3 min.\n   - No store hit → check [recipes.md](references\u002Frecipes.md) for a\n     ready-made recipe, else use the official Docker image and write a\n     template ([deploy.md](references\u002Fdeploy.md), Path B). **Never build a\n     product from source when an official image exists.**\n2. **User's own project (has source code)**: look for an existing\n   Dockerfile\u002Fcompose file, else generate one, build for **linux\u002Famd64**,\n   push, then deploy the image ([build.md](references\u002Fbuild.md) then\n   [deploy.md](references\u002Fdeploy.md) Path B).\n3. **Just a database \u002F bucket**: [databases.md](references\u002Fdatabases.md) \u002F\n   platform.md's object storage section — deploy as a minimal template.\n\nAfter ANY deploy, verify before reporting:\n\n```bash\nbash scripts\u002Fwait-app.sh -u https:\u002F\u002F\u003Chost>.\u003Cregion-domain> deployment\u002F\u003Cname> [cluster\u002F\u003Cname>-pg ...]\n```\n\nOn `*.sealos.io` regions, local deploys also claim a Brain Project in-script;\nif `brain_adoption.ok` is false, or `warnings` still lists\n`incompleteResourceSet` after verify, run `sealos-api.py adopt \u003Cinstance>` —\nnever redeploy. On `*.sealos.run` this is skipped\n(`brain_adoption.reason: not-sealos-io`). See\n[deploy.md](references\u002Fdeploy.md).\n\n## Quick operations\n\n```bash\nexport KUBECONFIG=~\u002F.sealos\u002Fkubeconfig\nkubectl get deploy,sts,pods                                   # what's running\nkubectl get clusters.apps.kubeblocks.io                       # databases\nkubectl get ingress -o custom-columns='NAME:.metadata.name,HOST:.spec.rules[0].host'  # public URLs\nkubectl logs deploy\u002F\u003Cname> --tail=100                         # app logs\nkubectl describe pod \u003Cpod>                                    # scheduling\u002Fpull issues\nkubectl get events --field-selector type=Warning --sort-by=.lastTimestamp | tail -20\nkubectl scale deploy\u002F\u003Cname> --replicas=2                      # scale\npython3 scripts\u002Fsealos-api.py store-list --search \u003Cquery>     # template store\n```\n\n## Routing\n\n| Intent | Reference |\n|---|---|\n| Deploy anything (store template, image, or built artifact) | [deploy.md](references\u002Fdeploy.md) |\n| Dockerfile \u002F image build \u002F registry push for user source | [build.md](references\u002Fbuild.md) |\n| Provision or connect PostgreSQL\u002FMySQL\u002FMongoDB\u002FRedis\u002FKafka | [databases.md](references\u002Fdatabases.md) |\n| Manifest rules when writing template YAML (labels, Ingress, storage, quota ladder, object storage) | [platform.md](references\u002Fplatform.md) |\n| Status, logs, debugging, scaling, deletion, cost hygiene | [operate.md](references\u002Foperate.md) |\n| Per-app recipes for popular self-hosted software | [recipes.md](references\u002Frecipes.md) |\n| Brain managed sandbox (`SEALAI_DEPLOY_MODE=managed`) | [..\u002Fsealos-deploy\u002FSKILL.md](..\u002Fsealos-deploy\u002FSKILL.md) |\n\nLoad only what the task needs — usually one reference, two at most.\n\n## Execution rules\n\n1. **Never report a deploy as successful without evidence**: `wait-app.sh`\n   exits 0 AND the public URL returns a real page (2xx\u002F3xx, and for\n   SSR apps the body is not an error page). If verification fails, triage via\n   [operate.md](references\u002Foperate.md) — do not re-deploy blindly.\n2. Production images are built and pushed as **linux\u002Famd64** (`docker buildx\n   build --platform linux\u002Famd64`). Apple Silicon defaults produce arm64\n   images that crash-loop on Sealos with `exec format error`.\n3. Resource requests\u002Flimits follow the platform ladder\n   ([platform.md](references\u002Fplatform.md)); requests are derived from limits,\n   and memory always uses `Mi` values.\n4. Deploy through the Template API. Fall back to `kubectl apply` only for\n   single resources during debugging, and remember `kubectl apply` rejects\n   Deployment+`volumeClaimTemplates` (use StatefulSet).\n5. Destructive actions (deleting apps, databases, buckets; switching\n   workspace on a shared machine), public-access changes, credential rotation,\n   and system-tool installation require explicit user confirmation first.\n6. Never print secret values. Read them into shell variables or pipe them;\n   show the user only names and how to fetch values.\n7. After mutations, read back state (`kubectl get ...`) before describing it.\n8. One deploy at a time per app name; name collisions in a shared namespace\n   break selectors. Random suffixes (`-a1b2c3d4`) are there for a reason —\n   keep them.\n9. If the agent sandbox blocks writes outside the workspace, escalate file\n   access for writing `~\u002F.sealos\u002Fkubeconfig`, using the Docker socket, and any\n   command that must read that kubeconfig.\n\n## Response format\n\nAfter each operation report: what was deployed\u002Fchanged (names + namespace),\nthe public URL if any, verification evidence (ready state, HTTP code), and\ncredentials location (secret names, never values). On failure: the failing\nresource, the decisive log\u002Fevent lines, and the next action you are taking.\n",{"name":5,"description":49,"allowed-tools":50},"Deploy and operate apps on Sealos Cloud: sign in to a Sealos account, deploy any project or self-hosted app (from the template store, an official Docker image, or project source code), provision managed databases (PostgreSQL, MySQL, MongoDB, Redis, Kafka), create S3-compatible object storage, expose public HTTPS domains, check status and logs, and troubleshoot failures. Use this skill whenever the user mentions Sealos (in any language, e.g. \"部署到 Sealos\"), or asks to deploy, host, or self-host an application, website, or database without naming another platform. Typical trigger: \"deploy X to Sealos\" \u002F \"帮我把 X 部署到 Sealos\".\n","Bash(kubectl:*), Bash(python3:*), Bash(docker:*), Bash(curl:*), Bash(bash:*), Bash(git:*), Bash(gh:*), Bash(command:*)","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Flabring\u002Fsealos-skills\u002Fplugins\u002Fsealos\u002Fskills\u002Fuse-sealos",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill use-sealos",{"tool":67,"command":68},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill use-sealos",{"tool":70,"command":71},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill use-sealos","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Flabring\u002Fsealos-skills\u002Fplugins\u002Fsealos\u002Fskills\u002Fuse-sealos\u002FSKILL.md",true,[75,81,85,89,93,97,101,107,111],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fbuild.md","REFERENCE","参考文档",3262,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Flabring\u002Fsealos-skills\u002Fplugins\u002Fsealos\u002Fskills\u002Fuse-sealos\u002Freferences\u002Fbuild.md",{"path":82,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fdatabases.md",7511,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Flabring\u002Fsealos-skills\u002Fplugins\u002Fsealos\u002Fskills\u002Fuse-sealos\u002Freferences\u002Fdatabases.md",{"path":86,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fdeploy.md",5943,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Flabring\u002Fsealos-skills\u002Fplugins\u002Fsealos\u002Fskills\u002Fuse-sealos\u002Freferences\u002Fdeploy.md",{"path":90,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Foperate.md",3318,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Flabring\u002Fsealos-skills\u002Fplugins\u002Fsealos\u002Fskills\u002Fuse-sealos\u002Freferences\u002Foperate.md",{"path":94,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fplatform.md",9755,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Flabring\u002Fsealos-skills\u002Fplugins\u002Fsealos\u002Fskills\u002Fuse-sealos\u002Freferences\u002Fplatform.md",{"path":98,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Frecipes.md",8397,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Flabring\u002Fsealos-skills\u002Fplugins\u002Fsealos\u002Fskills\u002Fuse-sealos\u002Freferences\u002Frecipes.md",{"path":102,"resourceType":103,"resourceTypeDesc":104,"sizeBytes":105,"sourceHtmlUrl":106},"scripts\u002Fsealos-api.py","SCRIPT","脚本",30199,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Flabring\u002Fsealos-skills\u002Fplugins\u002Fsealos\u002Fskills\u002Fuse-sealos\u002Fscripts\u002Fsealos-api.py",{"path":108,"resourceType":103,"resourceTypeDesc":104,"sizeBytes":109,"sourceHtmlUrl":110},"scripts\u002Ftest_sealos_api_adopt.py",15008,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Flabring\u002Fsealos-skills\u002Fplugins\u002Fsealos\u002Fskills\u002Fuse-sealos\u002Fscripts\u002Ftest_sealos_api_adopt.py",{"path":112,"resourceType":103,"resourceTypeDesc":104,"sizeBytes":113,"sourceHtmlUrl":114},"scripts\u002Fwait-app.sh",6462,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Flabring\u002Fsealos-skills\u002Fplugins\u002Fsealos\u002Fskills\u002Fuse-sealos\u002Fscripts\u002Fwait-app.sh",[116,126,134,142,150,158],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":120,"licenseFileUrl":121,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":125},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"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":120,"licenseFileUrl":130,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":125},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":120,"licenseFileUrl":138,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":125},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":120,"licenseFileUrl":146,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":125},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":120,"licenseFileUrl":154,"sourceHtmlUrl":155,"categories":156,"keywords":157,"publishedAt":125},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":120,"licenseFileUrl":162,"sourceHtmlUrl":163,"categories":164,"keywords":165,"publishedAt":125},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]