[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F3TVW42H14HCNNWS698F46":3,"skill-same:01M7F3TVW42H14HCNNWS698F46":55},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":48},"01M7F3TVW42H14HCNNWS698F46","competition-data-science",null,"Prepare datasets and operate RD-Agent data-science\u002FKaggle workflows with reproducible debug, validation, submission, and grading artifacts.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Frd-agent\u002Fsub-skills\u002Fcompetition-data-science\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: competition-data-science\ndescription: \"Prepare datasets and operate RD-Agent data-science\u002FKaggle\n  workflows with reproducible debug, validation, submission, and grading\n  artifacts.\"\nmetadata:\n  disco-role: operating\n  parent-skill: rd-agent\nlicense: MIT\ndisable-model-invocation: true\n---\n\n# RD-Agent competition and data science\n\nUse this sub-skill for `rdagent data_science`, Kaggle-style tasks, custom datasets, data preparation, generated modeling code, local evaluation, and submission artifacts.\n\n## Input contract\n\nA custom task should be organized around a task directory and a `source_data` root. The repository's example documents the following shape:\n\n```text\nsource_data\u002F\u003Ctask>\u002Fprepare.py\n\u003Ctask>\u002F\u003Ctask>\u002Fdescription.md\n\u003Ctask>\u002F\u003Ctask>\u002Fsample.py        # optional debug sampler\n\u003Ctask>\u002Feval\u002Fgrade.py           # optional test grader\n\u003Ctask>\u002Feval\u002Fvalid.py           # optional submission validator\n```\n\nThe task description should state the objective, data fields, split\u002Fuse restrictions, modeling constraints, metric, and submission format. Run [check_dataset_layout.py](scripts\u002Fcheck_dataset_layout.py) before asking an agent to write modeling code.\n\n## Safe workflow\n\n1. Inspect `rdagent data_science --help` and the scenario config.\n2. Run `prepare.py` or the dataset preparation step in a disposable output location; verify row counts, columns, labels, and train\u002Ftest separation.\n3. Create a tiny debug sample using the task's `sample.py` when present. The default sampler in `rdagent.scenarios.data_science.debug.data` is a fallback, not a guarantee of semantic correctness.\n4. Launch the smallest agent loop that exercises code generation and evaluation.\n5. Validate the generated submission with `valid.py` when available, then grade with `grade.py` or the configured evaluator.\n6. Preserve the description, resolved paths, generated source, submission, validation output, metric, and seed.\n\n## Competition hygiene\n\n- Do not use test labels, competition metadata, or future information in feature engineering.\n- Check that local validation matches the competition's target and that a generated submission has the exact required columns\u002Forder.\n- Treat external Kaggle credentials and downloads as prerequisites; do not include them in a reusable skill or test fixture.\n- A successful code-generation iteration is not a score. Report the evaluator command and the data split that produced the score.\n- For time-series or patient data, preserve group\u002Fentity boundaries and temporal ordering while sampling.\n\nRead [dataset-contract.md](references\u002Fdataset-contract.md) for required files and artifact semantics. For Qlib-backed finance tasks use [quant-finance](..\u002Fquant-finance\u002FSKILL.md) instead.\n","# RD-Agent competition and data science\n\nUse this sub-skill for `rdagent data_science`, Kaggle-style tasks, custom datasets, data preparation, generated modeling code, local evaluation, and submission artifacts.\n\n## Input contract\n\nA custom task should be organized around a task directory and a `source_data` root. The repository's example documents the following shape:\n\n```text\nsource_data\u002F\u003Ctask>\u002Fprepare.py\n\u003Ctask>\u002F\u003Ctask>\u002Fdescription.md\n\u003Ctask>\u002F\u003Ctask>\u002Fsample.py        # optional debug sampler\n\u003Ctask>\u002Feval\u002Fgrade.py           # optional test grader\n\u003Ctask>\u002Feval\u002Fvalid.py           # optional submission validator\n```\n\nThe task description should state the objective, data fields, split\u002Fuse restrictions, modeling constraints, metric, and submission format. Run [check_dataset_layout.py](scripts\u002Fcheck_dataset_layout.py) before asking an agent to write modeling code.\n\n## Safe workflow\n\n1. Inspect `rdagent data_science --help` and the scenario config.\n2. Run `prepare.py` or the dataset preparation step in a disposable output location; verify row counts, columns, labels, and train\u002Ftest separation.\n3. Create a tiny debug sample using the task's `sample.py` when present. The default sampler in `rdagent.scenarios.data_science.debug.data` is a fallback, not a guarantee of semantic correctness.\n4. Launch the smallest agent loop that exercises code generation and evaluation.\n5. Validate the generated submission with `valid.py` when available, then grade with `grade.py` or the configured evaluator.\n6. Preserve the description, resolved paths, generated source, submission, validation output, metric, and seed.\n\n## Competition hygiene\n\n- Do not use test labels, competition metadata, or future information in feature engineering.\n- Check that local validation matches the competition's target and that a generated submission has the exact required columns\u002Forder.\n- Treat external Kaggle credentials and downloads as prerequisites; do not include them in a reusable skill or test fixture.\n- A successful code-generation iteration is not a score. Report the evaluator command and the data split that produced the score.\n- For time-series or patient data, preserve group\u002Fentity boundaries and temporal ordering while sampling.\n\nRead [dataset-contract.md](references\u002Fdataset-contract.md) for required files and artifact semantics. For Qlib-backed finance tasks use [quant-finance](..\u002Fquant-finance\u002FSKILL.md) instead.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":27},{"disco-role":25,"parent-skill":26},"operating","rd-agent",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Frd-agent\u002Fsub-skills\u002Fcompetition-data-science",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":27},[38,41,44],{"tool":39,"command":40},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill competition-data-science",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill competition-data-science",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill competition-data-science","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Frd-agent\u002Fsub-skills\u002Fcompetition-data-science\u002FSKILL.md",[49],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fdataset-contract.md","REFERENCE","参考文档",1267,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Frd-agent\u002Fsub-skills\u002Fcompetition-data-science\u002Freferences\u002Fdataset-contract.md",[56,63,68,75,82,89],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":64,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]