[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EX6ETAEX8ZD1VJR4TYDF6P":3,"skill-same:01M7EX6ETAEX8ZD1VJR4TYDF6P":65},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M7EX6ETAEX8ZD1VJR4TYDF6P","data-analysis",null,"Analyses tabular or experimental data rigorously - profiles the data first, checks for leakage between train and test splits, chooses statistical tests whose assumptions hold, reports effect sizes and confidence intervals rather than bare p-values, corrects for multiple comparisons, and keeps notebooks reproducible. Use for exploratory analysis, statistics, A\u002FB or experiment analysis, dataset checks, data leakage, p-values, or cleaning and validating datasets.","paulsagar7796-cmyk\u002FUniversal-agent-skills","paulsagar7796-cmyk","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F236126668?v=4","01M7EX5ZBFWM7WN5Y4Z691QQC3","01M7EX5ZCK8MW9651JQJKMBZ1M",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fpaulsagar7796-cmyk\u002FUniversal-agent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fdata\u002Fdata-analysis\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: data-analysis\ndescription: Analyses tabular or experimental data rigorously - profiles the data first, checks for leakage between train and test splits, chooses statistical tests whose assumptions hold, reports effect sizes and confidence intervals rather than bare p-values, corrects for multiple comparisons, and keeps notebooks reproducible. Use for exploratory analysis, statistics, A\u002FB or experiment analysis, dataset checks, data leakage, p-values, or cleaning and validating datasets.\nlicense: Apache-2.0\nmetadata:\n  version: \"0.1.0\"\n  category: data\n  maturity: draft\n  risk: low\n---\n\n# Data analysis\n\nNumbers you report must be reproducible from the data and code, and the uncertainty around them must be stated.\n\n## Workflow\n\n1. **Understand the question** and the unit of analysis (row = patient? sample? event?). Ask if unclear.\n2. **Profile before modelling**: shape, column types, units, missing values per column, duplicates, value ranges,\n   class balance, time span. Note anything odd (mixed units, sentinel values like -999, impossible values).\n3. **Leakage check** whenever there are train\u002Fvalidation\u002Ftest files or a split column:\n   `python3 scripts\u002Fleakage_check.py train.csv test.csv --id \u003Cid column> --target \u003Clabel column>`\n   (standard library only; reads local files, sends nothing anywhere). It reports exact duplicate rows across splits,\n   overlapping IDs, and features that are near-copies of the target. Also think about leakage it cannot see: future\n   information, preprocessing fitted on all data, group leakage (same patient\u002Fsubject in both splits).\n4. **Choose the analysis to fit the question and data**: state assumptions (independence, normality, equal variance)\n   and check them; prefer robust or non-parametric alternatives when they fail; for paired data use paired tests.\n5. **Report effect sizes with confidence intervals** (difference in means, odds ratio, Cohen's d …) alongside p-values.\n   A p-value alone is not a finding.\n6. **Multiple comparisons**: when testing many hypotheses, say how many and correct (Holm, Benjamini–Hochberg).\n   Never search through tests until something is significant; if exploration was open-ended, label results\n   exploratory.\n7. **Reproducibility**: fixed seeds, notebooks that run top to bottom (restart-and-run-all), relative paths, pinned\n   environment, raw data never modified in place (write cleaned data to a new file). `brain init` flags notebooks\n   run out of order, missing seeds and absolute paths.\n8. **Record** key findings in the brain with evidence (`brain remember … --evidence file:\u003Cnotebook or results file>`),\n   and analysis runs with `brain exp` when they produce metrics.\n\n## Stop and ask when\n\n- The request is to \"find something significant\" — explain why that invalidates the result and propose a\n  pre-specified analysis instead.\n- Data looks personal or sensitive (health, genetics, identifiers): confirm it may be analysed here; never upload it\n  to an external service without explicit approval (`upload-sensitive-data`).\n\n## Never\n\n- Report results from data you did not load, invent values, or silently drop rows\u002Foutliers (say what was removed and why).\n- Copy raw data rows into the brain, reports or chat beyond small illustrative examples without personal data.\n\n## Output contract\n\n```\nData: \u003Cfiles, rows, columns, period>   Quality issues: \u003Cmissing, duplicates, units>\nLeakage check: \u003Cresult or \"not applicable\">\nMethod: \u003Ctest\u002Fmodel and why; assumptions checked>\nResults: \u003Cestimate, 95% CI, p (corrected if applicable), n>\nLimitations: \u003Cwhat this analysis cannot show>\n```\n","# Data analysis\n\nNumbers you report must be reproducible from the data and code, and the uncertainty around them must be stated.\n\n## Workflow\n\n1. **Understand the question** and the unit of analysis (row = patient? sample? event?). Ask if unclear.\n2. **Profile before modelling**: shape, column types, units, missing values per column, duplicates, value ranges,\n   class balance, time span. Note anything odd (mixed units, sentinel values like -999, impossible values).\n3. **Leakage check** whenever there are train\u002Fvalidation\u002Ftest files or a split column:\n   `python3 scripts\u002Fleakage_check.py train.csv test.csv --id \u003Cid column> --target \u003Clabel column>`\n   (standard library only; reads local files, sends nothing anywhere). It reports exact duplicate rows across splits,\n   overlapping IDs, and features that are near-copies of the target. Also think about leakage it cannot see: future\n   information, preprocessing fitted on all data, group leakage (same patient\u002Fsubject in both splits).\n4. **Choose the analysis to fit the question and data**: state assumptions (independence, normality, equal variance)\n   and check them; prefer robust or non-parametric alternatives when they fail; for paired data use paired tests.\n5. **Report effect sizes with confidence intervals** (difference in means, odds ratio, Cohen's d …) alongside p-values.\n   A p-value alone is not a finding.\n6. **Multiple comparisons**: when testing many hypotheses, say how many and correct (Holm, Benjamini–Hochberg).\n   Never search through tests until something is significant; if exploration was open-ended, label results\n   exploratory.\n7. **Reproducibility**: fixed seeds, notebooks that run top to bottom (restart-and-run-all), relative paths, pinned\n   environment, raw data never modified in place (write cleaned data to a new file). `brain init` flags notebooks\n   run out of order, missing seeds and absolute paths.\n8. **Record** key findings in the brain with evidence (`brain remember … --evidence file:\u003Cnotebook or results file>`),\n   and analysis runs with `brain exp` when they produce metrics.\n\n## Stop and ask when\n\n- The request is to \"find something significant\" — explain why that invalidates the result and propose a\n  pre-specified analysis instead.\n- Data looks personal or sensitive (health, genetics, identifiers): confirm it may be analysed here; never upload it\n  to an external service without explicit approval (`upload-sensitive-data`).\n\n## Never\n\n- Report results from data you did not load, invent values, or silently drop rows\u002Foutliers (say what was removed and why).\n- Copy raw data rows into the brain, reports or chat beyond small illustrative examples without personal data.\n\n## Output contract\n\n```\nData: \u003Cfiles, rows, columns, period>   Quality issues: \u003Cmissing, duplicates, units>\nLeakage check: \u003Cresult or \"not applicable\">\nMethod: \u003Ctest\u002Fmodel and why; assumptions checked>\nResults: \u003Cestimate, 95% CI, p (corrected if applicable), n>\nLimitations: \u003Cwhat this analysis cannot show>\n```\n",{"name":5,"license":14,"metadata":23,"description":7},{"risk":24,"version":25,"category":26,"maturity":27},"low","0.1.0","data","draft","main","3a32b58695554c34c977f4a8dbb868d2d93c91d0","skills\u002Fdata\u002Fdata-analysis",0,"https:\u002F\u002Fgithub.com\u002Fpaulsagar7796-cmyk\u002FUniversal-agent-skills","https:\u002F\u002Fgithub.com\u002Fpaulsagar7796-cmyk","2026-10-19 15:51:08",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add paulsagar7796-cmyk\u002FUniversal-agent-skills --skill data-analysis",{"tool":41,"command":42},"bunx","bunx skills add paulsagar7796-cmyk\u002FUniversal-agent-skills --skill data-analysis",{"tool":44,"command":45},"pnpm","pnpm dlx skills add paulsagar7796-cmyk\u002FUniversal-agent-skills --skill data-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpaulsagar7796-cmyk\u002FUniversal-agent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fdata\u002Fdata-analysis\u002FSKILL.md",true,[49,55,59],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"evals\u002Fcases.yaml","REFERENCE","参考文档",2999,"https:\u002F\u002Fgithub.com\u002Fpaulsagar7796-cmyk\u002FUniversal-agent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fdata\u002Fdata-analysis\u002Fevals\u002Fcases.yaml",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"manifest.yaml",832,"https:\u002F\u002Fgithub.com\u002Fpaulsagar7796-cmyk\u002FUniversal-agent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fdata\u002Fdata-analysis\u002Fmanifest.yaml",{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"scripts\u002Fleakage_check.py","SCRIPT","脚本",4807,"https:\u002F\u002Fgithub.com\u002Fpaulsagar7796-cmyk\u002FUniversal-agent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fdata\u002Fdata-analysis\u002Fscripts\u002Fleakage_check.py",[66,73,80,87,94,101],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M7EX9X6CQ1DZZ413VE5BE6DM","malicious-remote-exec","TEST FIXTURE ONLY - installs by piping a remote script to a shell and persists itself. Use when testing the scanner.","https:\u002F\u002Fgithub.com\u002Fpaulsagar7796-cmyk\u002FUniversal-agent-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fmalicious-remote-exec\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M7EX9S7WEKDJ39587ZM94D98","malicious-exfil","TEST FIXTURE ONLY - pretends to format code but exfiltrates environment variables. Use when testing the scanner.","https:\u002F\u002Fgithub.com\u002Fpaulsagar7796-cmyk\u002FUniversal-agent-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fmalicious-exfil\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M7EX9MM1Z011GG37VCT66YB4","malicious-concealment","TEST FIXTURE ONLY - instructions that try to override the agent and hide actions. Use when testing the scanner.","https:\u002F\u002Fgithub.com\u002Fpaulsagar7796-cmyk\u002FUniversal-agent-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fmalicious-concealment\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":18},"01M7EX9GY9Q8YZHBTPFQGJ7Q7M","clean-weather","TEST FIXTURE ONLY - a legitimate skill that reads a public weather API. Use when testing scanner false positives.","https:\u002F\u002Fgithub.com\u002Fpaulsagar7796-cmyk\u002FUniversal-agent-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fclean-weather\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":18},"01M7EX9E8DS554HCA3XA2D7K1H","skill-template","One sentence saying what this skill does. Use when \u003Cthe situations and words that should trigger it>.","https:\u002F\u002Fgithub.com\u002Fpaulsagar7796-cmyk\u002FUniversal-agent-skills\u002Fblob\u002Fmain\u002Ftemplates\u002Fskill-template\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":18},"01M7EX97HN9JHMJFN5AHT68X0E","skill-package-audit","Audits a third-party Agent Skill or skill repository before it is installed or used - checks provenance and license, scans instructions and scripts for prompt injection, hidden text, credential access, data exfiltration, destructive or persistent commands, and reports a risk verdict with evidence. Use before installing a skill, when asked whether a skill is safe, or when reviewing skill supply-chain risk.","https:\u002F\u002Fgithub.com\u002Fpaulsagar7796-cmyk\u002FUniversal-agent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsecurity\u002Fskill-package-audit\u002FSKILL.md",[],[]]