[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71FNCKK74MFE7MYSPVN0YAT":3,"skill-same:01M71FNCKK74MFE7MYSPVN0YAT":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":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M71FNCKK74MFE7MYSPVN0YAT","publish",null,"Publish a Harbor task or dataset to the registry. Use when the user wants to upload, publish, or share tasks or datasets\u002Fbenchmarks on the Harbor registry.","pku-liang\u002Fhwe-bench","pku-liang","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F81861363?v=4","01M71FMJQ2VZ4YEERAS5FJ438T","PKU Yun (Eric) Liang Research Group","01M71FMJR6AXWMX6K35KS4ZS6G",73,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fpku-liang\u002Fhwe-bench\u002Fblob\u002Fmain\u002Fdeps\u002Fharbor\u002Fskills\u002Fpublish\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31],"datasets","registry","use","when","dataset","tasks","upload","benchmarks","user","task","path","harbor","share","2026-11-10 10:12:30",false,"---\nname: publish\ndescription: Publish a Harbor task or dataset to the registry. Use when the user wants to upload, publish, or share tasks or datasets\u002Fbenchmarks on the Harbor registry.\nargument-hint: [path\u002Fto\u002Ftask-or-dataset]\n---\n\nHelp the user publish a Harbor task or dataset to the registry. Walk them through each step, checking prerequisites and confirming before running publish commands.\n\nAll commands use `uvx harbor` so the user does not need to install the CLI globally.\n\n## Prerequisites\n\n1. **Auth**: Ensure the user is logged in by running `uvx harbor auth status`. If not logged in, prompt them to run `uvx harbor auth login`.\n\n2. **Task identifiers**: All tasks must have a `[task]` section in their `task.toml` with a name like `\u003Corg>\u002F\u003Cname>`. If missing, run:\n   ```bash\n   uvx harbor task update \"\u003Cpath\u002Fto\u002Ftask>\" --org \"\u003Corg>\"\n   ```\n   To update all tasks in a directory:\n   ```bash\n   uvx harbor task update \"\u003Cpath\u002Fto\u002Ftasks>\" --org \"\u003Corg>\" --scan\n   ```\n\n## Publishing a task\n\n```bash\nuvx harbor publish \"\u003Cpath\u002Fto\u002Ftask>\"\n```\n\nPublish multiple tasks or all tasks in a directory:\n```bash\nuvx harbor publish \"\u003Cpath\u002Fto\u002Ftask-a>\" \"\u003Cpath\u002Fto\u002Ftask-b>\"\nuvx harbor publish \"\u003Cpath\u002Fto\u002Ftasks>\"\n```\n\n## Publishing a dataset\n\n### 1. Initialize the dataset manifest (if no `dataset.toml` exists)\n\n```bash\nuvx harbor dataset init \"\u003Corg>\u002F\u003Cdataset>\" \\\n  --description \"\u003Cdescription>\" \\\n  --author \"Jane Doe \u003Cjane@example.com>\"\n```\n\nAdd `--with-metric` if the user needs a custom metric script. If omitted, the dataset uses the default metric (average reward across tasks, with missing values treated as 0).\n\n**Auto-add behavior:** If `dataset init` is run in a directory that already contains tasks, those tasks are automatically added to the manifest. After init, **ask the user if they want to add additional tasks** — either from the Harbor registry or from other local folders.\n\n### 2. Add additional tasks and files (optional)\n\n```bash\ncd \"\u003Cpath\u002Fto\u002Fdataset>\"\nuvx harbor add \"\u003Cpath\u002Fto\u002Ftask-a>\" \"\u003Cpath\u002Fto\u002Ftask-b>\"   # local tasks from elsewhere\nuvx harbor add \"\u003Cpath\u002Fto\u002Ffolder>\" --scan                 # all tasks in another folder\nuvx harbor add org\u002Ftask-name                             # published tasks from registry\nuvx harbor add org\u002Fdataset-name                          # all tasks from a published dataset\nuvx harbor add metric.py                                 # metric file (same dir as dataset.toml)\nuvx harbor remove \"\u003Corg>\u002F\u003Ctask-name>\"                     # remove a task\n```\n\nSpecific versions: `org\u002Ftask@tag`, `org\u002Ftask@revision`, or `org\u002Ftask@sha256:\u003Chash>`.\n\n### 3. Sync digests (if tasks\u002Fmetrics changed since last publish)\n\n```bash\nuvx harbor sync\nuvx harbor sync --upgrade   # also upgrade remote tasks to latest\n```\n\n### 4. Publish the dataset\n\n```bash\nuvx harbor publish \"\u003Cpath\u002Fto\u002Fdataset>\"\n```\n\n`uvx harbor publish` automatically refreshes digests of local tasks in the dataset directory.\n\n## Publish options (tasks and datasets)\n\n- `-t \u002F --tag`: add tags (repeatable). `latest` is always included.\n- `-c \u002F --concurrency`: control upload concurrency.\n- `--public`: make public (private by default).\n- `--no-tasks` (datasets only): skip publishing tasks in the dataset directory.\n\nExample:\n```bash\nuvx harbor publish \"\u003Cpath>\" -t v1.0 --public\n```\n\n## After publishing\n\n- Visibility can be changed later with `uvx harbor task visibility` \u002F `uvx harbor dataset visibility` or on https:\u002F\u002Fhub.harborframework.com\u002F.\n- Run a published dataset with:\n  ```bash\n  uvx harbor run -d \"\u003Corg>\u002F\u003Cdataset>@v1.0\" -a \"\u003Cagent>\" -m \"\u003Cmodel>\"\n  ```\n","Help the user publish a Harbor task or dataset to the registry. Walk them through each step, checking prerequisites and confirming before running publish commands.\n\nAll commands use `uvx harbor` so the user does not need to install the CLI globally.\n\n## Prerequisites\n\n1. **Auth**: Ensure the user is logged in by running `uvx harbor auth status`. If not logged in, prompt them to run `uvx harbor auth login`.\n\n2. **Task identifiers**: All tasks must have a `[task]` section in their `task.toml` with a name like `\u003Corg>\u002F\u003Cname>`. If missing, run:\n   ```bash\n   uvx harbor task update \"\u003Cpath\u002Fto\u002Ftask>\" --org \"\u003Corg>\"\n   ```\n   To update all tasks in a directory:\n   ```bash\n   uvx harbor task update \"\u003Cpath\u002Fto\u002Ftasks>\" --org \"\u003Corg>\" --scan\n   ```\n\n## Publishing a task\n\n```bash\nuvx harbor publish \"\u003Cpath\u002Fto\u002Ftask>\"\n```\n\nPublish multiple tasks or all tasks in a directory:\n```bash\nuvx harbor publish \"\u003Cpath\u002Fto\u002Ftask-a>\" \"\u003Cpath\u002Fto\u002Ftask-b>\"\nuvx harbor publish \"\u003Cpath\u002Fto\u002Ftasks>\"\n```\n\n## Publishing a dataset\n\n### 1. Initialize the dataset manifest (if no `dataset.toml` exists)\n\n```bash\nuvx harbor dataset init \"\u003Corg>\u002F\u003Cdataset>\" \\\n  --description \"\u003Cdescription>\" \\\n  --author \"Jane Doe \u003Cjane@example.com>\"\n```\n\nAdd `--with-metric` if the user needs a custom metric script. If omitted, the dataset uses the default metric (average reward across tasks, with missing values treated as 0).\n\n**Auto-add behavior:** If `dataset init` is run in a directory that already contains tasks, those tasks are automatically added to the manifest. After init, **ask the user if they want to add additional tasks** — either from the Harbor registry or from other local folders.\n\n### 2. Add additional tasks and files (optional)\n\n```bash\ncd \"\u003Cpath\u002Fto\u002Fdataset>\"\nuvx harbor add \"\u003Cpath\u002Fto\u002Ftask-a>\" \"\u003Cpath\u002Fto\u002Ftask-b>\"   # local tasks from elsewhere\nuvx harbor add \"\u003Cpath\u002Fto\u002Ffolder>\" --scan                 # all tasks in another folder\nuvx harbor add org\u002Ftask-name                             # published tasks from registry\nuvx harbor add org\u002Fdataset-name                          # all tasks from a published dataset\nuvx harbor add metric.py                                 # metric file (same dir as dataset.toml)\nuvx harbor remove \"\u003Corg>\u002F\u003Ctask-name>\"                     # remove a task\n```\n\nSpecific versions: `org\u002Ftask@tag`, `org\u002Ftask@revision`, or `org\u002Ftask@sha256:\u003Chash>`.\n\n### 3. Sync digests (if tasks\u002Fmetrics changed since last publish)\n\n```bash\nuvx harbor sync\nuvx harbor sync --upgrade   # also upgrade remote tasks to latest\n```\n\n### 4. Publish the dataset\n\n```bash\nuvx harbor publish \"\u003Cpath\u002Fto\u002Fdataset>\"\n```\n\n`uvx harbor publish` automatically refreshes digests of local tasks in the dataset directory.\n\n## Publish options (tasks and datasets)\n\n- `-t \u002F --tag`: add tags (repeatable). `latest` is always included.\n- `-c \u002F --concurrency`: control upload concurrency.\n- `--public`: make public (private by default).\n- `--no-tasks` (datasets only): skip publishing tasks in the dataset directory.\n\nExample:\n```bash\nuvx harbor publish \"\u003Cpath>\" -t v1.0 --public\n```\n\n## After publishing\n\n- Visibility can be changed later with `uvx harbor task visibility` \u002F `uvx harbor dataset visibility` or on https:\u002F\u002Fhub.harborframework.com\u002F.\n- Run a published dataset with:\n  ```bash\n  uvx harbor run -d \"\u003Corg>\u002F\u003Cdataset>@v1.0\" -a \"\u003Cagent>\" -m \"\u003Cmodel>\"\n  ```\n",{"name":5,"description":7,"argument-hint":37},[38],"path\u002Fto\u002Ftask-or-dataset","main","10c78a87e1f92695d78d15b1464a6107dcac8837","deps\u002Fharbor\u002Fskills\u002Fpublish",9,"https:\u002F\u002Fgithub.com\u002Fpku-liang\u002Fhwe-bench","https:\u002F\u002Fgithub.com\u002Fpku-liang","https:\u002F\u002Fericlyun.github.io\u002F","2026-11-11 10:00:32",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add pku-liang\u002Fhwe-bench --skill publish",{"tool":53,"command":54},"bunx","bunx skills add pku-liang\u002Fhwe-bench --skill publish",{"tool":56,"command":57},"pnpm","pnpm dlx skills add pku-liang\u002Fhwe-bench --skill publish","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpku-liang\u002Fhwe-bench\u002Fblob\u002Fmain\u002Fdeps\u002Fharbor\u002Fskills\u002Fpublish\u002FSKILL.md",true,[],[62,84,101,123,143,165],{"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":32},"01M71FNJ6S5MATHHD81PMD42MM","upload-parity-experiments","Create or reuse Hugging Face dataset PRs for `harborframework\u002Fparity-experiments` and upload Harbor parity\u002Foracle result folders efficiently with sparse checkout, raw git pushes, and Git LFS.","https:\u002F\u002Fgithub.com\u002Fpku-liang\u002Fhwe-bench\u002Fblob\u002Fmain\u002Fdeps\u002Fharbor\u002Fskills\u002Fupload-parity-experiments\u002FSKILL.md",[],[25,69,70,71,72,73,74,23,75,76,77,78,79,80,81,82,83,30],"upload parity experiments","experiments","parity","hugging face","face","result","oracle","reuse","prs","lfs","for","checkout","with","create","git",{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":32},"01M71FNG0TQD738NZGZN1W31AF","rewardkit","Write Harbor task verifiers using Reward Kit. Use when creating or editing a task's tests\u002F directory, adding grading criteria, setting up LLM\u002Fagent judges, or designing verifiers that produce a reward score.","https:\u002F\u002Fgithub.com\u002Fpku-liang\u002Fhwe-bench\u002Fblob\u002Fmain\u002Fdeps\u002Fharbor\u002Fskills\u002Frewardkit\u002FSKILL.md",[],[86,91,28,92,93,94,95,96,21,97,98,99,100,30,22],"produce","kit","tests","up","editing","setting","grading","write","directory","Verifiers",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":32},"01M71FN9MJMRMA5E1AZCRFKN6M","harbor-exec","Use when working with Harbor's `harbor exec` CLI workflow: compiling files, directories, or globs into Harbor tasks; running map jobs; configuring artifacts and existence-only verification; using map-reduce; writing or reviewing ExecConfig YAML\u002FJSON\u002FTOML; or debugging command behavior, config validation, and job outputs.","https:\u002F\u002Fgithub.com\u002Fpku-liang\u002Fhwe-bench\u002Fblob\u002Fmain\u002Fdeps\u002Fharbor\u002Fskills\u002Fharbor-exec\u002FSKILL.md",[],[108,30,109,110,81,24,111,112,113,22,114,115,116,117,118,119,120,121,122,21],"exec","harbor exec","verification","artifacts","workflow","reduce","debugging","writing","files","map","only","outputs","toml","directories","running",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":32},"01M71FN6EG0E0TG5HVC5ZGV6PW","create-task","Create a new Harbor task for evaluating agents. Use when the user wants to scaffold, build, or design a new task, benchmark problem, or eval. Guides through instruction writing, environment setup, verifier design (pytest vs Reward Kit vs custom), and solution scripting.","https:\u002F\u002Fgithub.com\u002Fpku-liang\u002Fhwe-bench\u002Fblob\u002Fmain\u002Fdeps\u002Fharbor\u002Fskills\u002Fcreate-task\u002FSKILL.md",[],[130,28,82,131,132,133,134,92,135,21,136,137,79,138,139,140,141,22,115,142],"create task","design","eval","new task","problem","verifier","custom","environment","pytest","org","benchmark","guides","new",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":154,"publishedAt":32},"01M71FN46QH5B25X9SXCJ5PNWD","create-adapter","Scaffold a new Harbor benchmark adapter by running `harbor adapter init` and then guide implementation using the Adapters Agent Guide as the authoritative spec.","https:\u002F\u002Fgithub.com\u002Fpku-liang\u002Fhwe-bench\u002Fblob\u002Fmain\u002Fdeps\u002Fharbor\u002Fskills\u002Fcreate-adapter\u002FSKILL.md",[149],{"categoryNo":150,"categoryName":151,"taxonomyType":152,"taxonomyTypeDesc":153},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[82,155,156,157,158,159,160,161,162,140,30,142,163,164,122],"create adapter","adapter","spec","scaffold","guide","agent guide","Adapters","implementation","init","as",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"publishedAt":32},"01M71FN35PFRFKD7ZKMH9WHZDV","generate-greeting","Generate a greeting message and write it to a file.","https:\u002F\u002Fgithub.com\u002Fpku-liang\u002Fhwe-bench\u002Fblob\u002Fmain\u002Fdeps\u002Fharbor\u002Fexamples\u002Ftasks\u002Fhello-skills\u002Fenvironment\u002Fskills\u002Fgenerate-greeting\u002FSKILL.md",[],[172,173,174,98,175,176,177],"greeting","generate greeting","generate","it","file","message"]