[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DF7NQASBXNRNWTHBCRBZPM":3,"skill-same:01M6DF7NQASBXNRNWTHBCRBZPM":82},{"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":31,"publishedAt":51,"linkOnly":52,"markdownContent":53,"markdownBody":54,"frontMatter":55,"refName":60,"commitSha":61,"skillDirectory":62,"forksCount":63,"repositoryHtmlUrl":64,"repositoryHomepageUrl":6,"ownerHtmlUrl":65,"ownerBlogUrl":6,"ownerDescription":66,"updatedAt":67,"install":68,"resources":81},"01M6DF7NQASBXNRNWTHBCRBZPM","render-env-vars",null,"Configures environment variables, secrets, and env groups on Render. Use when the user needs to set env vars, wire secrets between services, create env groups, use generateValue, set sync: false, or troubleshoot missing or incorrect environment variable values in Blueprints or the Dashboard.","zapabob\u002FSkills","zapabob","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130830376?v=4","01M6DBMYZAGRTFQDSQYW3W764P","峯岸 亮","01M6DBMZ3GKDSJ01NZ9XTZD7JD",2,"MIT","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F48\u002F48ccac1b1f4ca36ae51f7695e84489b6ca0a4bfd70ab8944dc152609aeef7eb1\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50],"render env vars","env","env vars","SET","false","configuration","use","environment","user","secrets","Tools","MCP","services","mcp tools","create","sync","troubleshoot","dashboard","cli","2026-11-10 10:12:30",false,"---\r\nname: render-env-vars\r\ndescription: >-\r\n  Configures environment variables, secrets, and env groups on Render. Use when\r\n  the user needs to set env vars, wire secrets between services, create env\r\n  groups, use generateValue, set sync: false, or troubleshoot missing or\r\n  incorrect environment variable values in Blueprints or the Dashboard.\r\nlicense: MIT\r\ncompatibility: Render Dashboard, CLI, or MCP tools\r\nmetadata:\r\n  author: Render\r\n  version: \"1.0.0\"\r\n  category: configuration\r\n---\r\n\r\n# Environment Variables on Render\r\n\r\nRender exposes configuration to services as **environment variables**. Values are always **strings** at the platform layer—applications must parse numbers, booleans, and structured data explicitly.\r\n\r\nThere are **three** primary ways to set variables:\r\n\r\n1. **Render Dashboard** — per-service UI, bulk import from `.env`, save\u002Fredeploy options\r\n2. **Blueprint** — `envVars` (and related keys) in `render.yaml`\r\n3. **MCP \u002F API** — e.g. `update_environment_variables` on a service\r\n\r\nDeep wiring patterns, full platform variable tables, and language-specific notes live under `references\u002F`.\r\n\r\n## When to Use This Skill\r\n\r\nUse this skill when users want to:\r\n\r\n- Add, change, or remove environment variables or secrets\r\n- Understand Dashboard vs Blueprint vs API\u002FMCP flows\r\n- Use **environment groups** for shared configuration\r\n- Wire `fromDatabase`, `fromService`, `fromGroup`, `sync: false`, or `generateValue` in Blueprints\r\n- Debug missing vars, secret files, precedence, or platform-injected names\r\n\r\nFor full Blueprint authoring, pair with **render-blueprints**. For first-time deploys, **render-deploy**. For web service behavior and ports, **render-web-services**.\r\n\r\n## Setting Variables\r\n\r\n### Dashboard\r\n\r\n- Add variables **individually** (name + value) or **in bulk** by pasting\u002Fuploading a `.env`-style file.\r\n- **Save options** typically include:\r\n  - **Save and rebuild & deploy** — picks up build-time changes\r\n  - **Deploy only** — runtime change without a full rebuild (when applicable)\r\n  - **Save only** — persist without triggering a deploy\r\n\r\nUse Dashboard edits when iterating quickly or when the repo should not carry certain values.\r\n\r\n### Blueprint (`render.yaml`)\r\n\r\nDeclare `envVars` on each service. Values can be literals, generated secrets, sync-disabled prompts, or references to databases, other services, or env groups. See **Blueprint Wiring** below and `references\u002Fwiring-reference.md` for exhaustive patterns and YAML.\r\n\r\n### MCP \u002F API\r\n\r\nAutomation tools can set variables on existing services (e.g. `update_environment_variables`). Useful for CI, rotation, or keeping Dashboard state in sync with external secret stores—without committing secrets to Git.\r\n\r\n## Secret Management\r\n\r\n- **`sync: false`** — Render prompts in the Dashboard for the value **only on initial Blueprint setup** when the resource is first created. On **Blueprint updates**, `sync: false` is **ignored** (values are not re-prompted from the file alone). These vars are **excluded from preview environments** and are **invalid inside environment groups**.\r\n- **`generateValue: true`** — Render generates a **base64-encoded 256-bit** random value at provision time. Use for passwords, signing keys, or tokens that do not need human-chosen values.\r\n- **Never commit real secrets** in `render.yaml` as plain `value:` entries. Prefer Dashboard, secret manager integration, `generateValue`, or `sync: false` with Dashboard entry.\r\n\r\n### Secret files\r\n\r\n- Store sensitive file content as **secret files** (not inline env strings). They appear as **plaintext files** under **`\u002Fetc\u002Fsecrets\u002F\u003Cfilename>`**.\r\n- **Combined limit**: **1 MB** total secret file payload per service or per linked env group (as applicable to your setup).\r\n- **Docker**: secret files are available under **`\u002Fetc\u002Fsecrets\u002F`** on the running instance.\r\n\r\n## Environment Groups\r\n\r\n**Environment groups** are named collections of variables linked to **multiple services**.\r\n\r\n- **Precedence**: **Service-level** variables **override** variables from linked groups with the same name.\r\n- **Multiple groups** on one service: the group that was **most recently created** wins for overlapping keys. This ordering is **not documented as stable**—avoid relying on it; use distinct names or consolidate groups.\r\n- Groups can be **scoped to a project environment** so staging and production differ without duplicating every service definition.\r\n\r\n## Blueprint Wiring (Summary)\r\n\r\nFull syntax, examples, and edge cases: `references\u002Fwiring-reference.md`. Authoritative Blueprint docs: **render-blueprints** skill.\r\n\r\n| Mechanism | Role |\r\n|-----------|------|\r\n| `value` | Hardcoded string (non-secret config only) |\r\n| `generateValue: true` | Platform-generated secret |\r\n| `sync: false` | Dashboard prompt on **initial** create only |\r\n| `fromDatabase` | Inject DB fields (`connectionString`, `host`, `port`, `user`, `password`, `database`) |\r\n| `fromService` | Key Value: `type: keyvalue` + properties; private\u002Fweb: `host`, `hostport`, or `envVarKey` |\r\n| `fromGroup` | Link all vars from a named group |\r\n\r\n## Platform-Injected Variables\r\n\r\nRender sets **read-only** variables your app can read at runtime (and some at build). A concise list:\r\n\r\n| Variable | Typical meaning |\r\n|----------|-----------------|\r\n| `RENDER` | `\"true\"` when running on Render |\r\n| `RENDER_SERVICE_TYPE` | Service kind (e.g. web, worker) |\r\n| `RENDER_SERVICE_ID` | Service identifier |\r\n| `RENDER_SERVICE_NAME` | Human-readable service name |\r\n| `RENDER_INSTANCE_ID` | Current instance |\r\n| `RENDER_EXTERNAL_URL` | Public URL (when applicable) |\r\n| `RENDER_EXTERNAL_HOSTNAME` | Public hostname |\r\n| `RENDER_DISCOVERY_SERVICE` | Service discovery hostname (private network) |\r\n| `RENDER_GIT_COMMIT` | Deployed commit SHA |\r\n| `RENDER_GIT_BRANCH` | Branch for this deploy |\r\n| `PORT` | HTTP port to bind (**default `10000`**) |\r\n| `IS_PULL_REQUEST` | Preview deploy indicator |\r\n| `RENDER_CPU_COUNT` | vCPU count for the instance |\r\n| `RENDER_WEB_CONCURRENCY` | Suggested worker\u002Fprocess count hint |\r\n\r\nBuild vs runtime availability, language version env vars, and **WEB_CONCURRENCY** defaults: `references\u002Fplatform-variables.md`.\r\n\r\n## Runtime-Specific Defaults\r\n\r\nRender and buildpacks may set defaults (verify in your service’s **Environment** tab):\r\n\r\n| Runtime | Notable defaults |\r\n|---------|------------------|\r\n| **Node.js** | `NODE_ENV=production` |\r\n| **Python** | `PYTHON_VERSION` (pinned by build); Gunicorn-oriented images often set `GUNICORN_CMD_ARGS` to bind **`0.0.0.0:10000`** |\r\n| **Ruby** | `RAILS_ENV=production`, `RAILS_LOG_TO_STDOUT=true` |\r\n| **Go** | `GO111MODULE=on` (legacy modules flag; still seen on older stacks) |\r\n| **Rust** | `ROCKET_PORT=10000` (Rocket convention) |\r\n\r\nAlways bind HTTP servers to **`0.0.0.0`** and **`PORT`** (or the stack’s documented port env) unless using a static site or custom Docker entrypoint.\r\n\r\n## Common Issues\r\n\r\n1. **Everything is a string** — `DEBUG=false` is truthy in many parsers; use explicit comparison or typed config loaders.\r\n2. **`WEB_CONCURRENCY`** — Default behavior changed for services **created after December 8, 2025**. Compare with older services when debugging worker counts; see `references\u002Fplatform-variables.md`.\r\n3. **Undocumented `RENDER_*` variables** — Names and semantics may change; do not depend on undocumented injection for critical logic.\r\n4. **Blueprint vs Dashboard drift** — Editing only `render.yaml` does not retroactively apply `sync: false` prompts on update; merge strategy for env keys is easy to misunderstand—test in a scratch service.\r\n5. **Secret file paths** — Code must read **`\u002Fetc\u002Fsecrets\u002F\u003Cfilename>`**; wrong paths or missing mounts usually show as file-not-found at runtime.\r\n\r\n## References\r\n\r\n- `references\u002Fwiring-reference.md` — Complete Blueprint `envVar` wiring, YAML examples, precedence, edge cases\r\n- `references\u002Fplatform-variables.md` — Injected variables (build vs runtime), language versions, concurrency, reading vars from code\r\n\r\n## Related Skills\r\n\r\n- **render-blueprints** — Full Blueprint authoring, validation, multi-service layouts\r\n- **render-deploy** — First deploy, repo requirements, MCP vs YAML\r\n- **render-web-services** — Ports, health checks, scaling behavior tied to env-driven servers\r\n","# Environment Variables on Render\r\n\r\nRender exposes configuration to services as **environment variables**. Values are always **strings** at the platform layer—applications must parse numbers, booleans, and structured data explicitly.\r\n\r\nThere are **three** primary ways to set variables:\r\n\r\n1. **Render Dashboard** — per-service UI, bulk import from `.env`, save\u002Fredeploy options\r\n2. **Blueprint** — `envVars` (and related keys) in `render.yaml`\r\n3. **MCP \u002F API** — e.g. `update_environment_variables` on a service\r\n\r\nDeep wiring patterns, full platform variable tables, and language-specific notes live under `references\u002F`.\r\n\r\n## When to Use This Skill\r\n\r\nUse this skill when users want to:\r\n\r\n- Add, change, or remove environment variables or secrets\r\n- Understand Dashboard vs Blueprint vs API\u002FMCP flows\r\n- Use **environment groups** for shared configuration\r\n- Wire `fromDatabase`, `fromService`, `fromGroup`, `sync: false`, or `generateValue` in Blueprints\r\n- Debug missing vars, secret files, precedence, or platform-injected names\r\n\r\nFor full Blueprint authoring, pair with **render-blueprints**. For first-time deploys, **render-deploy**. For web service behavior and ports, **render-web-services**.\r\n\r\n## Setting Variables\r\n\r\n### Dashboard\r\n\r\n- Add variables **individually** (name + value) or **in bulk** by pasting\u002Fuploading a `.env`-style file.\r\n- **Save options** typically include:\r\n  - **Save and rebuild & deploy** — picks up build-time changes\r\n  - **Deploy only** — runtime change without a full rebuild (when applicable)\r\n  - **Save only** — persist without triggering a deploy\r\n\r\nUse Dashboard edits when iterating quickly or when the repo should not carry certain values.\r\n\r\n### Blueprint (`render.yaml`)\r\n\r\nDeclare `envVars` on each service. Values can be literals, generated secrets, sync-disabled prompts, or references to databases, other services, or env groups. See **Blueprint Wiring** below and `references\u002Fwiring-reference.md` for exhaustive patterns and YAML.\r\n\r\n### MCP \u002F API\r\n\r\nAutomation tools can set variables on existing services (e.g. `update_environment_variables`). Useful for CI, rotation, or keeping Dashboard state in sync with external secret stores—without committing secrets to Git.\r\n\r\n## Secret Management\r\n\r\n- **`sync: false`** — Render prompts in the Dashboard for the value **only on initial Blueprint setup** when the resource is first created. On **Blueprint updates**, `sync: false` is **ignored** (values are not re-prompted from the file alone). These vars are **excluded from preview environments** and are **invalid inside environment groups**.\r\n- **`generateValue: true`** — Render generates a **base64-encoded 256-bit** random value at provision time. Use for passwords, signing keys, or tokens that do not need human-chosen values.\r\n- **Never commit real secrets** in `render.yaml` as plain `value:` entries. Prefer Dashboard, secret manager integration, `generateValue`, or `sync: false` with Dashboard entry.\r\n\r\n### Secret files\r\n\r\n- Store sensitive file content as **secret files** (not inline env strings). They appear as **plaintext files** under **`\u002Fetc\u002Fsecrets\u002F\u003Cfilename>`**.\r\n- **Combined limit**: **1 MB** total secret file payload per service or per linked env group (as applicable to your setup).\r\n- **Docker**: secret files are available under **`\u002Fetc\u002Fsecrets\u002F`** on the running instance.\r\n\r\n## Environment Groups\r\n\r\n**Environment groups** are named collections of variables linked to **multiple services**.\r\n\r\n- **Precedence**: **Service-level** variables **override** variables from linked groups with the same name.\r\n- **Multiple groups** on one service: the group that was **most recently created** wins for overlapping keys. This ordering is **not documented as stable**—avoid relying on it; use distinct names or consolidate groups.\r\n- Groups can be **scoped to a project environment** so staging and production differ without duplicating every service definition.\r\n\r\n## Blueprint Wiring (Summary)\r\n\r\nFull syntax, examples, and edge cases: `references\u002Fwiring-reference.md`. Authoritative Blueprint docs: **render-blueprints** skill.\r\n\r\n| Mechanism | Role |\r\n|-----------|------|\r\n| `value` | Hardcoded string (non-secret config only) |\r\n| `generateValue: true` | Platform-generated secret |\r\n| `sync: false` | Dashboard prompt on **initial** create only |\r\n| `fromDatabase` | Inject DB fields (`connectionString`, `host`, `port`, `user`, `password`, `database`) |\r\n| `fromService` | Key Value: `type: keyvalue` + properties; private\u002Fweb: `host`, `hostport`, or `envVarKey` |\r\n| `fromGroup` | Link all vars from a named group |\r\n\r\n## Platform-Injected Variables\r\n\r\nRender sets **read-only** variables your app can read at runtime (and some at build). A concise list:\r\n\r\n| Variable | Typical meaning |\r\n|----------|-----------------|\r\n| `RENDER` | `\"true\"` when running on Render |\r\n| `RENDER_SERVICE_TYPE` | Service kind (e.g. web, worker) |\r\n| `RENDER_SERVICE_ID` | Service identifier |\r\n| `RENDER_SERVICE_NAME` | Human-readable service name |\r\n| `RENDER_INSTANCE_ID` | Current instance |\r\n| `RENDER_EXTERNAL_URL` | Public URL (when applicable) |\r\n| `RENDER_EXTERNAL_HOSTNAME` | Public hostname |\r\n| `RENDER_DISCOVERY_SERVICE` | Service discovery hostname (private network) |\r\n| `RENDER_GIT_COMMIT` | Deployed commit SHA |\r\n| `RENDER_GIT_BRANCH` | Branch for this deploy |\r\n| `PORT` | HTTP port to bind (**default `10000`**) |\r\n| `IS_PULL_REQUEST` | Preview deploy indicator |\r\n| `RENDER_CPU_COUNT` | vCPU count for the instance |\r\n| `RENDER_WEB_CONCURRENCY` | Suggested worker\u002Fprocess count hint |\r\n\r\nBuild vs runtime availability, language version env vars, and **WEB_CONCURRENCY** defaults: `references\u002Fplatform-variables.md`.\r\n\r\n## Runtime-Specific Defaults\r\n\r\nRender and buildpacks may set defaults (verify in your service’s **Environment** tab):\r\n\r\n| Runtime | Notable defaults |\r\n|---------|------------------|\r\n| **Node.js** | `NODE_ENV=production` |\r\n| **Python** | `PYTHON_VERSION` (pinned by build); Gunicorn-oriented images often set `GUNICORN_CMD_ARGS` to bind **`0.0.0.0:10000`** |\r\n| **Ruby** | `RAILS_ENV=production`, `RAILS_LOG_TO_STDOUT=true` |\r\n| **Go** | `GO111MODULE=on` (legacy modules flag; still seen on older stacks) |\r\n| **Rust** | `ROCKET_PORT=10000` (Rocket convention) |\r\n\r\nAlways bind HTTP servers to **`0.0.0.0`** and **`PORT`** (or the stack’s documented port env) unless using a static site or custom Docker entrypoint.\r\n\r\n## Common Issues\r\n\r\n1. **Everything is a string** — `DEBUG=false` is truthy in many parsers; use explicit comparison or typed config loaders.\r\n2. **`WEB_CONCURRENCY`** — Default behavior changed for services **created after December 8, 2025**. Compare with older services when debugging worker counts; see `references\u002Fplatform-variables.md`.\r\n3. **Undocumented `RENDER_*` variables** — Names and semantics may change; do not depend on undocumented injection for critical logic.\r\n4. **Blueprint vs Dashboard drift** — Editing only `render.yaml` does not retroactively apply `sync: false` prompts on update; merge strategy for env keys is easy to misunderstand—test in a scratch service.\r\n5. **Secret file paths** — Code must read **`\u002Fetc\u002Fsecrets\u002F\u003Cfilename>`**; wrong paths or missing mounts usually show as file-not-found at runtime.\r\n\r\n## References\r\n\r\n- `references\u002Fwiring-reference.md` — Complete Blueprint `envVar` wiring, YAML examples, precedence, edge cases\r\n- `references\u002Fplatform-variables.md` — Injected variables (build vs runtime), language versions, concurrency, reading vars from code\r\n\r\n## Related Skills\r\n\r\n- **render-blueprints** — Full Blueprint authoring, validation, multi-service layouts\r\n- **render-deploy** — First deploy, repo requirements, MCP vs YAML\r\n- **render-web-services** — Ports, health checks, scaling behavior tied to env-driven servers\r\n",{"name":5,"license":15,"metadata":56,"description":7,"compatibility":59},{"author":57,"version":58,"category":37},"Render","1.0.0","Render Dashboard, CLI, or MCP tools","main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002F48\u002F48ccac1b1f4ca36ae51f7695e84489b6ca0a4bfd70ab8944dc152609aeef7eb1",0,"https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills","https:\u002F\u002Fgithub.com\u002Fzapabob","The Open University of JAPAN　2019-now\r\n\r\nTokyo University of Science　2007-2010","2026-10-26 16:29:01",{"source":8,"skillName":5,"commands":69,"prompt":79,"zipAvailable":80},[70,73,76],{"tool":71,"command":72},"npx","npx skills add zapabob\u002FSkills --skill render-env-vars",{"tool":74,"command":75},"bunx","bunx skills add zapabob\u002FSkills --skill render-env-vars",{"tool":77,"command":78},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill render-env-vars","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F48\u002F48ccac1b1f4ca36ae51f7695e84489b6ca0a4bfd70ab8944dc152609aeef7eb1\u002FSKILL.md",true,[],[83,114,149,175,200,217],{"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":96,"publishedAt":51},"01M6GJTE1GESGGF9K028Y7753E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fxurl\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[89,92,93],{"categoryNo":90,"categoryName":91,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":94,"categoryName":95,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000030","开发工程师",[85,97,98,50,99,100,101,102,103,104,105,106,107,108,109,110,60,111,112,113],"openclaw","macos","github","linux","windows","official","search","https","social-media","api","Media","hermes","hermes agent","twitter","social","via","post",{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":131,"publishedAt":51},"01M6GJT8S1PXQ8WPXT1HSNBWH2","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwriting-plans\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[120,123,126,127,128],{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":124,"categoryName":125,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":94,"categoryName":95,"taxonomyType":29,"taxonomyTypeDesc":30},{"categoryNo":129,"categoryName":130,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000036","内容创作者",[132,133,134,135,98,136,100,137,101,138,139,140,141,142,143,144,145,146,147,148],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":158,"publishedAt":51},"01M6GJST0H5X7WHBJ3BZK0DVKH","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwhisper\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[155],{"categoryNo":156,"categoryName":157,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[151,98,100,159,160,161,162,163,164,165,166,167,38,168,169,170,171,172,173,174],"openai","speech","multimodal","Transformers","ASR","Audio","text","model","speech recognition","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":182,"publishedAt":51},"01M6GJSMRQ8EETZTYMG72P70EA","weights-and-biases","W&B: log ML experiments, sweeps, model registry, dashboards.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fweights-and-biases\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[181],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[183,98,184,185,101,186,187,188,189,190,191,166,192,193,194,195,196,197,198,199],"weights and biases","tensorflow","experiments","pytorch","visualization","registry","real-time","tuning","dashboards","experiment","log","time","Experiment Tracking","Model Registry","Hyperparameter Tuning","WandB","Real-Time Visualization",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":207,"publishedAt":51},"01M6GJS19KDPRY112JTR326S06","watchers","Poll RSS, JSON APIs, and GitHub with watermark dedup.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwatchers\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[206],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[202,98,208,99,100,209,210,211,212,213,214,108,109,215,216],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":218,"name":219,"nameZh":6,"description":220,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":221,"categories":222,"keywords":225,"publishedAt":51},"01M6GJRHJD2A6Q830SWF9W48BC","serving-llms-vllm","vLLM: high-throughput LLM serving, OpenAI API, quantization.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fvllm\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[223,224],{"categoryNo":90,"categoryName":91,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":94,"categoryName":95,"taxonomyType":29,"taxonomyTypeDesc":30},[226,227,228,100,229,159,230,231,232,162,233,106,234,235,236,237,238,239,240,241],"llms","vLLM","serving llms vllm","research","openai api","tensor","Inference Serving","Production","llm serving","High Throughput","PagedAttention","Continuous Batching","Quantization","Tensor Parallelism","high-throughput","throughput"]