[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ACDDTW44MNT7YFKP1BRQMS":3,"skill-same:01M6ACDDTW44MNT7YFKP1BRQMS":61},{"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":23,"linkOnly":24,"markdownContent":25,"markdownBody":26,"frontMatter":27,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M6ACDDTW44MNT7YFKP1BRQMS","codex-expo-run-actions",null,"Wire Expo projects into the Codex app with project-local run scripts and .codex\u002Fenvironments\u002Fenvironment.toml actions. Use when the user wants the Codex app Run button, build\u002Frun actions, action buttons, or a stable Expo start\u002Frun workflow from Codex.","openai\u002Fplugins","openai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F14957082?v=4","01M6AC29YGCR4S2NTJFV0G8B81","OpenAI","01M6AC38CEN570NMR96RNGD2NK",7942,"MIT","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fexpo\u002Fskills\u002Fcodex-expo-run-actions\u002FSKILL.md",[],[19,20,21,22],"codex","run","codex expo run actions","workflow","2026-11-10 10:12:30",false,"---\nname: codex-expo-run-actions\ndescription: Wire Expo projects into the Codex app with project-local run scripts and .codex\u002Fenvironments\u002Fenvironment.toml actions. Use when the user wants the Codex app Run button, build\u002Frun actions, action buttons, or a stable Expo start\u002Frun workflow from Codex.\nversion: 1.0.0\nlicense: MIT\n---\n\n# Codex Run Actions for Expo\n\nUse this skill to connect an Expo project to the Codex app action bar.\n\nThe goal is one project-local script plus `.codex\u002Fenvironments\u002Fenvironment.toml`,\nso the user can press `Run` in the Codex app and see the Expo CLI \u002F Metro logs in\nan action terminal.\n\n## Workflow\n\n1. Confirm the current workspace is an Expo app.\n   - Look for `package.json`.\n   - Look for `app.json`, `app.config.js`, `app.config.ts`, or `expo` in `package.json`.\n   - Do not wire the Codex action at a monorepo root if the Expo app is in a child package.\n\n2. Discover the package runner.\n   - Prefer the package manager declared in `packageManager`.\n   - Otherwise infer from lockfiles.\n   - The generated run script should still have a safe fallback to `npx expo`.\n\n3. Create or update `script\u002Fbuild_and_run.sh`.\n   - Use the reference file for the script shape.\n   - Default no-argument mode starts the Expo dev server: `expo start`.\n   - Keep the dev server in the foreground so the Codex action terminal owns logs and Ctrl-C behavior.\n   - Support optional modes for direct buttons:\n     - `--ios` starts Expo and opens iOS simulator.\n     - `--android` starts Expo and opens Android.\n     - `--web` starts Expo for web.\n     - `--dev-client` starts in dev-client mode.\n     - `--tunnel` starts a tunnel.\n     - `--export-web` exports web.\n\n4. Write `.codex\u002Fenvironments\u002Fenvironment.toml`.\n   - Always add or update one primary action named `Run`.\n   - Wire `Run` to `.\u002Fscript\u002Fbuild_and_run.sh`.\n   - Add direct `Run iOS`, `Run Android`, `Run Web`, or `Run Dev Client`\n     actions only when the user asks for those buttons or the project clearly needs them.\n   - If the environment file already exists, update the existing matching action instead of duplicating it.\n\n5. Use the action script as the default local run path.\n   - After wiring, run `.\u002Fscript\u002Fbuild_and_run.sh --help` or a short non-server mode if you need to sanity-check syntax.\n   - Do not start a long-lived Metro server during a setup-only task unless the user asked you to run the app.\n\n## References\n\n- `references\u002Fexpo-run-button-bootstrap.md`: canonical Expo `script\u002Fbuild_and_run.sh` and Codex environment action examples.\n\n## Guardrails\n\n- Try Expo Go \u002F `expo start` first; do not default the Codex Run button to `expo run:ios`, `expo run:android`, prebuild, or EAS Build.\n- Do not wire cloud actions such as `eas build`, `eas submit`, or store deployment into Codex buttons unless the user explicitly asks and accepts the auth \u002F time \u002F cost tradeoff.\n- Do not create a nested git repo.\n- Do not put secrets in `.codex\u002Fenvironments\u002Fenvironment.toml` or in the run script.\n- Do not background Metro from the run script; the action terminal should show the active server logs.\n- Do not hard-code npm if the project uses pnpm, yarn, or bun.\n\n## Output Expectations\n\nWhen setup changes are made, summarize:\n\n- the Expo app root you wired\n- the run script path\n- the Codex environment file path\n- the actions added or updated\n- how to launch the same path from shell\n","# Codex Run Actions for Expo\n\nUse this skill to connect an Expo project to the Codex app action bar.\n\nThe goal is one project-local script plus `.codex\u002Fenvironments\u002Fenvironment.toml`,\nso the user can press `Run` in the Codex app and see the Expo CLI \u002F Metro logs in\nan action terminal.\n\n## Workflow\n\n1. Confirm the current workspace is an Expo app.\n   - Look for `package.json`.\n   - Look for `app.json`, `app.config.js`, `app.config.ts`, or `expo` in `package.json`.\n   - Do not wire the Codex action at a monorepo root if the Expo app is in a child package.\n\n2. Discover the package runner.\n   - Prefer the package manager declared in `packageManager`.\n   - Otherwise infer from lockfiles.\n   - The generated run script should still have a safe fallback to `npx expo`.\n\n3. Create or update `script\u002Fbuild_and_run.sh`.\n   - Use the reference file for the script shape.\n   - Default no-argument mode starts the Expo dev server: `expo start`.\n   - Keep the dev server in the foreground so the Codex action terminal owns logs and Ctrl-C behavior.\n   - Support optional modes for direct buttons:\n     - `--ios` starts Expo and opens iOS simulator.\n     - `--android` starts Expo and opens Android.\n     - `--web` starts Expo for web.\n     - `--dev-client` starts in dev-client mode.\n     - `--tunnel` starts a tunnel.\n     - `--export-web` exports web.\n\n4. Write `.codex\u002Fenvironments\u002Fenvironment.toml`.\n   - Always add or update one primary action named `Run`.\n   - Wire `Run` to `.\u002Fscript\u002Fbuild_and_run.sh`.\n   - Add direct `Run iOS`, `Run Android`, `Run Web`, or `Run Dev Client`\n     actions only when the user asks for those buttons or the project clearly needs them.\n   - If the environment file already exists, update the existing matching action instead of duplicating it.\n\n5. Use the action script as the default local run path.\n   - After wiring, run `.\u002Fscript\u002Fbuild_and_run.sh --help` or a short non-server mode if you need to sanity-check syntax.\n   - Do not start a long-lived Metro server during a setup-only task unless the user asked you to run the app.\n\n## References\n\n- `references\u002Fexpo-run-button-bootstrap.md`: canonical Expo `script\u002Fbuild_and_run.sh` and Codex environment action examples.\n\n## Guardrails\n\n- Try Expo Go \u002F `expo start` first; do not default the Codex Run button to `expo run:ios`, `expo run:android`, prebuild, or EAS Build.\n- Do not wire cloud actions such as `eas build`, `eas submit`, or store deployment into Codex buttons unless the user explicitly asks and accepts the auth \u002F time \u002F cost tradeoff.\n- Do not create a nested git repo.\n- Do not put secrets in `.codex\u002Fenvironments\u002Fenvironment.toml` or in the run script.\n- Do not background Metro from the run script; the action terminal should show the active server logs.\n- Do not hard-code npm if the project uses pnpm, yarn, or bun.\n\n## Output Expectations\n\nWhen setup changes are made, summarize:\n\n- the Expo app root you wired\n- the run script path\n- the Codex environment file path\n- the actions added or updated\n- how to launch the same path from shell\n",{"name":5,"license":15,"version":28,"description":7},"1.0.0","main","0722921d5542fc593105c27bd52630babd8b8c2a","plugins\u002Fexpo\u002Fskills\u002Fcodex-expo-run-actions",1025,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","https:\u002F\u002Fgithub.com\u002Fopenai","https:\u002F\u002Fopenai.com\u002F","2026-11-14 08:11:13",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add openai\u002Fplugins --skill codex-expo-run-actions",{"tool":43,"command":44},"bunx","bunx skills add openai\u002Fplugins --skill codex-expo-run-actions",{"tool":46,"command":47},"pnpm","pnpm dlx skills add openai\u002Fplugins --skill codex-expo-run-actions","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fexpo\u002Fskills\u002Fcodex-expo-run-actions\u002FSKILL.md",true,[51,57],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"agents\u002Fopenai.yaml","REFERENCE","参考文档",394,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fexpo\u002Fskills\u002Fcodex-expo-run-actions\u002Fagents\u002Fopenai.yaml",{"path":58,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fexpo-run-button-bootstrap.md",4972,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fexpo\u002Fskills\u002Fcodex-expo-run-actions\u002Freferences\u002Fexpo-run-button-bootstrap.md",[62,83,96,114,140,153],{"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":73,"publishedAt":23},"01M6ACYN431ER9AFG508JJH3VT","supabase-postgres-best-practices","Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsupabase\u002Fskills\u002Fsupabase-postgres-best-practices\u002FSKILL.md",[68],{"categoryNo":69,"categoryName":70,"taxonomyType":71,"taxonomyTypeDesc":72},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",[74,75,76,77,78,79,80,81,82],"best practices","supabase postgres best practices","writing","performance","sql","code","database","metrics","examples",{"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":92,"publishedAt":23},"01M6ACQRGGJYVNDPQWB9XGWRNZ","minimal-skill","Minimal example skill for plugin-eval tests. Use when the user wants a compact demonstration of a well-structured skill.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fplugin-eval\u002Ffixtures\u002Fminimal-skill\u002FSKILL.md",[89],{"categoryNo":90,"categoryName":91,"taxonomyType":71,"taxonomyTypeDesc":72},"01JBSEEDCAT000000000000023","Skill与智能体开发",[93,94,95],"minimal skill","example skill","plugin",{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":100,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":23},"01M6ACQ406M83341YPKPEXBXDZ","physical-ai-neural-reconstruction","Router for NVIDIA NuRec\u002FNRE: USDZ rendering, NCore conversion, 3DGS, gRPC sensor sim, PhysicalAI HF datasets. Do NOT use for SimReady or infra setup.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnvidia\u002Fskills\u002Fphysical-ai-neural-reconstruction\u002FSKILL.md",[],[104,105,106,107,108,109,110,111,112,113],"physical ai neural reconstruction","https","python","github","docker","setup","toolkit","gpu","index","grpc",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":100,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":123,"publishedAt":23},"01M6ACPVRFPVATXD7H38Z56QC5","physical-ai-infrastructure-setup-and-resilient-scaling","Use when the user wants to set up, scale, validate, or harden NVIDIA physical AI infrastructure for synthetic data generation workflows across local MicroK8s or Azure AKS, including Kubernetes clusters, inference endpoint deployment, OSMO deployment, workload submission readiness, and infrastructure failure recovery. Trigger keywords: physical ai infrastructure, resilient scaling, SDG infrastructure, microk8s, azure aks, NVCF deployment, NIM Operator, OSMO deploy, workflow scaling. Don't trigger for: OSMO log summarization or workload-only operations unless infrastructure setup, scaling, validation, or recovery is requested.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnvidia\u002Fskills\u002Fphysical-ai-infrastructure-setup-and-resilient-scaling\u002FSKILL.md",[120],{"categoryNo":121,"categoryName":122,"taxonomyType":71,"taxonomyTypeDesc":72},"01JBSEEDCAT000000000000011","运维与部署",[124,109,125,126,127,128,129,130,131,132,133,134,22,135,136,137,138,139],"physical ai infrastructure setup and resilient scaling","infrastructure","validation","terraform","deployment","synthetic data","workload","ml","cli","kubernetes","inference","workflows","component","validate","deploy","azure",{"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":100,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":147,"publishedAt":23},"01M6ACPG9JPDSS6MMKVKR3P56E","omniverse-usd-performance-tuning","Top-level workflow skill for USD performance diagnosis and optimization. Use for slow loading, high memory, low FPS, or 'optimize my scene' requests; delegates auth\u002Fruntime setup to Phase 0 owners.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnvidia\u002Fskills\u002Fomniverse-usd-performance-tuning\u002FSKILL.md",[146],{"categoryNo":90,"categoryName":91,"taxonomyType":71,"taxonomyTypeDesc":72},[148,77,149,106,150,151,22,109,131,152],"omniverse usd performance tuning","auth","memory","triage","authentication",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":100,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":160,"publishedAt":23},"01M6ACP73X9YS5Y730C2WE58YF","omniverse-realtime-viewer","Use as the top-level router for Omniverse Realtime Viewer USD app requests and focused viewer reference documents.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnvidia\u002Fskills\u002Fomniverse-realtime-viewer\u002FSKILL.md",[159],{"categoryNo":90,"categoryName":91,"taxonomyType":71,"taxonomyTypeDesc":72},[161,162,106,22,163,164,165,131,128,166,111,167],"omniverse realtime viewer","realtime","electron","react","documents","cpp","typescript"]