[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CRSHTNCCRMKSAWQ51XH5KB":3,"skill-same:01M7CRSHTNCCRMKSAWQ51XH5KB":51},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M7CRSHTNCCRMKSAWQ51XH5KB","dataset-domain-token-counts-via-metadata-config",null,"Use when a HuggingFace dataset task asks for token counts or filtering by a named domain and the dataset has multiple configs, only one of which contains domain and token-text columns.","RUC-NLPIR\u002FFlashRSI","RUC-NLPIR","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F139615285?v=4","01M7CRKXQY1FA6Q3MQH7WAKFBN","01M7CRKXRMR1W5HAGYYN5T41DR",394,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FRUC-NLPIR\u002FFlashRSI\u002Fblob\u002Fmain\u002Fexports\u002Fharnesses\u002Fevoharness-miniagent-terminalbench\u002Fskills\u002Fdataset-domain-token-counts-via-metadata-config\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dataset-domain-token-counts-via-metadata-config\ndescription: Use when a HuggingFace dataset task asks for token counts or filtering by a named domain and the dataset has multiple configs, only one of which contains domain and token-text columns.\nflashrsi:\n  algorithm: evo_harness\n  level: topic\n  source_task_ids: [count-dataset-tokens]\n---\n# Use the metadata config for domain-filtered token counts on OpenThoughts-style datasets\n\nWhen a dataset task asks for domain-level token counts, do not assume the `default` config has the needed columns. Inspect the available configs and load the one that actually holds domain labels and reasoning\u002Fsolution text.\n\nProcedure:\n1. List configs before loading:\n   ```python\n   from datasets import get_dataset_config_names\n   print(get_dataset_config_names(\"ryanmarten\u002FOpenThoughts-1k-sample\"))\n   ```\n2. Read the dataset card or README for documented configs and domain groupings.\n3. Load the config with the domain and token-text columns, often `metadata`, instead of `default`:\n   ```python\n   from datasets import load_dataset\n   ds = load_dataset(\"ryanmarten\u002FOpenThoughts-1k-sample\", \"metadata\")\n   ```\n4. Map README category names to the actual metadata domain values. For example, a `Science` category usually corresponds to `physics`, `chemistry`, and `biology`; do not search for a literal `science` domain value.\n5. Validate before counting:\n   ```python\n   print(ds[\"train\"].column_names)\n   print(ds[\"train\"].unique(\"domain\"))\n   ```\n\nWhy: on `ryanmarten\u002FOpenThoughts-1k-sample` the `default` config only has `system` and `conversations`, while `domain`, `deepseek_reasoning`, and `deepseek_solution` live in the `metadata` config. Counting tokens by domain from `default` returns no domain labels and can silently count the wrong text.\n\nSupporting evidence: count-dataset-tokens (this batch).\n","# Use the metadata config for domain-filtered token counts on OpenThoughts-style datasets\n\nWhen a dataset task asks for domain-level token counts, do not assume the `default` config has the needed columns. Inspect the available configs and load the one that actually holds domain labels and reasoning\u002Fsolution text.\n\nProcedure:\n1. List configs before loading:\n   ```python\n   from datasets import get_dataset_config_names\n   print(get_dataset_config_names(\"ryanmarten\u002FOpenThoughts-1k-sample\"))\n   ```\n2. Read the dataset card or README for documented configs and domain groupings.\n3. Load the config with the domain and token-text columns, often `metadata`, instead of `default`:\n   ```python\n   from datasets import load_dataset\n   ds = load_dataset(\"ryanmarten\u002FOpenThoughts-1k-sample\", \"metadata\")\n   ```\n4. Map README category names to the actual metadata domain values. For example, a `Science` category usually corresponds to `physics`, `chemistry`, and `biology`; do not search for a literal `science` domain value.\n5. Validate before counting:\n   ```python\n   print(ds[\"train\"].column_names)\n   print(ds[\"train\"].unique(\"domain\"))\n   ```\n\nWhy: on `ryanmarten\u002FOpenThoughts-1k-sample` the `default` config only has `system` and `conversations`, while `domain`, `deepseek_reasoning`, and `deepseek_solution` live in the `metadata` config. Counting tokens by domain from `default` returns no domain labels and can silently count the wrong text.\n\nSupporting evidence: count-dataset-tokens (this batch).\n",{"name":5,"flashrsi":23,"description":7},{"level":24,"algorithm":25,"source_task_ids":26},"topic","evo_harness",[27],"count-dataset-tokens","main","37837ec5052aee24a252c88fd3b10215ccb4af7d","exports\u002Fharnesses\u002Fevoharness-miniagent-terminalbench\u002Fskills\u002Fdataset-domain-token-counts-via-metadata-config",23,"https:\u002F\u002Fgithub.com\u002FRUC-NLPIR\u002FFlashRSI","https:\u002F\u002Fruc-nlpir.github.io\u002FFlashRSI\u002F","https:\u002F\u002Fgithub.com\u002FRUC-NLPIR","https:\u002F\u002Fruc-nlpir.github.io\u002F","2026-11-12 11:33:15",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add RUC-NLPIR\u002FFlashRSI --skill dataset-domain-token-counts-via-metadata-config",{"tool":43,"command":44},"bunx","bunx skills add RUC-NLPIR\u002FFlashRSI --skill dataset-domain-token-counts-via-metadata-config",{"tool":46,"command":47},"pnpm","pnpm dlx skills add RUC-NLPIR\u002FFlashRSI --skill dataset-domain-token-counts-via-metadata-config","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FRUC-NLPIR\u002FFlashRSI\u002Fblob\u002Fmain\u002Fexports\u002Fharnesses\u002Fevoharness-miniagent-terminalbench\u002Fskills\u002Fdataset-domain-token-counts-via-metadata-config\u002FSKILL.md",true,[],[52,59,67,74,81,88],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M7CRXMNEFS1SET0Q6DGX94K9","dynamic-resources","Example skill loaded from resources_discover","https:\u002F\u002Fgithub.com\u002FRUC-NLPIR\u002FFlashRSI\u002Fblob\u002Fmain\u002Fflashrsi\u002Fagents\u002Fpi_agent\u002Fruntime\u002Fpi_native\u002Freference\u002Fexamples\u002Fextensions\u002Fdynamic-resources\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":63,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M7CRXJDRSCK61F563B0Z5STZ","hermes-agent","Use the FlashRSI Hermes Snapshot's headless Python runtime, tools, sessions, and compression paths.","MIT","https:\u002F\u002Fgithub.com\u002FRUC-NLPIR\u002FFlashRSI\u002Fblob\u002Fmain\u002Fflashrsi\u002Fagents\u002Fhermes\u002Fskills\u002Fautonomous-ai-agents\u002Fhermes-agent\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M7CRXF7GB79VXXMK71F5EN45","skill-installer","Install Codex skills into $CODEX_HOME\u002Fskills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).","https:\u002F\u002Fgithub.com\u002FRUC-NLPIR\u002FFlashRSI\u002Fblob\u002Fmain\u002Fflashrsi\u002Fagents\u002Fcodex\u002Fpython_core\u002Fresource_assets\u002Fsystem_skills\u002Fskill-installer\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M7CRXA6107K9ENE8RDGR76N5","skill-creator","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.","https:\u002F\u002Fgithub.com\u002FRUC-NLPIR\u002FFlashRSI\u002Fblob\u002Fmain\u002Fflashrsi\u002Fagents\u002Fcodex\u002Fpython_core\u002Fresource_assets\u002Fsystem_skills\u002Fskill-creator\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M7CRX78G60TK2917V62T5ZZF","review-agent","Perform a read-only, defect-first review of a specified code change and return every actionable finding. Use when another agent delegates review of uncommitted changes, a base-branch diff, a commit, or custom review instructions.","https:\u002F\u002Fgithub.com\u002FRUC-NLPIR\u002FFlashRSI\u002Fblob\u002Fmain\u002Fflashrsi\u002Fagents\u002Fcodex\u002Fpython_core\u002Fresource_assets\u002Fsystem_skills\u002Freview-agent\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M7CRX2M7GC2714H3GVQERXKF","plugin-creator","Create and scaffold plugin directories for Codex with a required `.codex-plugin\u002Fplugin.json`, optional plugin folders\u002Ffiles, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries for plugin ordering and availability metadata, or update an existing local plugin during development with the CLI-driven cachebuster and reinstall flow.","https:\u002F\u002Fgithub.com\u002FRUC-NLPIR\u002FFlashRSI\u002Fblob\u002Fmain\u002Fflashrsi\u002Fagents\u002Fcodex\u002Fpython_core\u002Fresource_assets\u002Fsystem_skills\u002Fplugin-creator\u002FSKILL.md",[],[]]