[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EWPRJ653P95K86MJS1BZ2P":3,"skill-same:01M7EWPRJ653P95K86MJS1BZ2P":69},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":36,"updatedAt":37,"install":38,"resources":50},"01M7EWPRJ653P95K86MJS1BZ2P","dataframe-code-agents",null,"Use ai-data-science-team single-agent pandas code generators for cleaning, wrangling, visualization, and feature engineering workflows.","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\u002Fai-data-science-team\u002Fsub-skills\u002Fdataframe-code-agents\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dataframe-code-agents\ndescription: \"Use ai-data-science-team single-agent pandas code generators for\n  cleaning, wrangling, visualization, and feature engineering workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\n  package: ai-data-science-team\n  import: ai_data_science_team\n  version: 0.0.0.9017\nlicense: MIT\n---\n\n# dataframe-code-agents\n\nUse this sub-skill when the task is to run or explain **one ai-data-science-team pandas code-generation agent** over already-loaded pandas data: cleaning, wrangling, Plotly visualization, or feature engineering.\n\nThe package agents call the caller-provided LangChain-compatible model when invoked. This operating skill does not provide or configure that model and its bundled inspection script performs no model calls.\n\n## Route first\n\n| User intent | Use here? | Target |\n|---|---:|---|\n| Load local CSV\u002FExcel\u002FJSON\u002FParquet\u002FPickle files, discover files, or summarize a DataFrame without code generation | No | `..\u002Fdata-access-and-eda\u002FSKILL.md` |\n| Clean one DataFrame with generated pandas code | Yes | `DataCleaningAgent` |\n| Wrangle, join, reshape, aggregate, or transform one or more DataFrames with generated pandas code | Yes | `DataWranglingAgent` |\n| Generate a Plotly chart from one DataFrame with generated code | Yes | `DataVisualizationAgent` |\n| Produce a model-ready feature table with generic encodings and optional target preservation | Yes | `FeatureEngineeringAgent` |\n| Query a SQL database or reason about SQL safety | No | `..\u002Fsql-analysis\u002FSKILL.md` |\n| Compose multiple agents, use analyst teams, supervisors, or Streamlit apps | No | `..\u002Fmultiagent-and-app-workflows\u002FSKILL.md` |\n| Train H2O models or inspect MLflow tools | No | `..\u002Fmodeling-and-mlflow\u002FSKILL.md` |\n\n## Minimum runtime assumptions\n\n- `ai_data_science_team` imports successfully in the current Python environment.\n- The caller already has data in memory as a pandas `DataFrame`, a dict convertible to a DataFrame, or for wrangling a list of DataFrames\u002Fdicts.\n- The caller supplies a LangChain-compatible chat model object as `model=llm` before invoking an agent.\n- Data loading, EDA-only reporting, SQL access, app launching, model training, and service orchestration are delegated to sibling sub-skills.\n\n## Operating checklist\n\n1. Identify the single-agent task: cleaning, wrangling, visualization, or feature engineering.\n2. Verify the data shape is compatible with the selected agent.\n3. Choose conservative execution settings:\n   - `n_samples` low enough for wide data.\n   - `max_retries` bounded, usually `1` to `3`.\n   - `log=True` only when the user wants generated code\u002Ferror files, with a user-selected relative `log_path`.\n   - `human_in_the_loop=True` only when a review\u002Fresume interaction is acceptable.\n4. Invoke through the class wrapper (`DataCleaningAgent`, `DataWranglingAgent`, `DataVisualizationAgent`, or `FeatureEngineeringAgent`) unless the caller specifically needs the lower-level `make_*_agent` graph.\n5. Retrieve results through getters or `get_response()`; inspect generated code before reusing it outside the package workflow.\n6. If generated code fails, use the returned error key, bounded retries, logs, and the troubleshooting table rather than rerunning blindly.\n\n## Fast reference map\n\n- API signatures, response keys, getters, and shared graph behavior: [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md)\n- End-to-end cleaning, wrangling, visualization, and feature engineering patterns: [`references\u002Fworkflows.md`](references\u002Fworkflows.md)\n- Human review, checkpointers, resume commands, and generated-code logging: [`references\u002Fhuman-in-the-loop-and-logging.md`](references\u002Fhuman-in-the-loop-and-logging.md)\n- Symptom-based fixes for token pressure, sandbox errors, malformed outputs, and Plotly warnings: [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md)\n- Safe import\u002Fsignature\u002Fsandbox probe with no model call: [`scripts\u002Finspect_dataframe_agents.py`](scripts\u002Finspect_dataframe_agents.py)\n\n## Key safety facts\n\n- Generated pandas\u002FPlotly code is executed by the package through a subprocess sandbox with a timeout, a memory limit, and blocked imports for common filesystem, process, and network modules.\n- The sandbox is a guardrail, not a proof of correctness. Tell the user to review generated functions, especially before copying them into production notebooks or pipelines.\n- The default report node is deterministic: it packages selected state keys into an `AIMessage` without another model explanation call.\n- Human-in-the-loop review pauses after code execution when enabled, so use a checkpointer and stable `thread_id` if the run must be resumed.\n","# dataframe-code-agents\n\nUse this sub-skill when the task is to run or explain **one ai-data-science-team pandas code-generation agent** over already-loaded pandas data: cleaning, wrangling, Plotly visualization, or feature engineering.\n\nThe package agents call the caller-provided LangChain-compatible model when invoked. This operating skill does not provide or configure that model and its bundled inspection script performs no model calls.\n\n## Route first\n\n| User intent | Use here? | Target |\n|---|---:|---|\n| Load local CSV\u002FExcel\u002FJSON\u002FParquet\u002FPickle files, discover files, or summarize a DataFrame without code generation | No | `..\u002Fdata-access-and-eda\u002FSKILL.md` |\n| Clean one DataFrame with generated pandas code | Yes | `DataCleaningAgent` |\n| Wrangle, join, reshape, aggregate, or transform one or more DataFrames with generated pandas code | Yes | `DataWranglingAgent` |\n| Generate a Plotly chart from one DataFrame with generated code | Yes | `DataVisualizationAgent` |\n| Produce a model-ready feature table with generic encodings and optional target preservation | Yes | `FeatureEngineeringAgent` |\n| Query a SQL database or reason about SQL safety | No | `..\u002Fsql-analysis\u002FSKILL.md` |\n| Compose multiple agents, use analyst teams, supervisors, or Streamlit apps | No | `..\u002Fmultiagent-and-app-workflows\u002FSKILL.md` |\n| Train H2O models or inspect MLflow tools | No | `..\u002Fmodeling-and-mlflow\u002FSKILL.md` |\n\n## Minimum runtime assumptions\n\n- `ai_data_science_team` imports successfully in the current Python environment.\n- The caller already has data in memory as a pandas `DataFrame`, a dict convertible to a DataFrame, or for wrangling a list of DataFrames\u002Fdicts.\n- The caller supplies a LangChain-compatible chat model object as `model=llm` before invoking an agent.\n- Data loading, EDA-only reporting, SQL access, app launching, model training, and service orchestration are delegated to sibling sub-skills.\n\n## Operating checklist\n\n1. Identify the single-agent task: cleaning, wrangling, visualization, or feature engineering.\n2. Verify the data shape is compatible with the selected agent.\n3. Choose conservative execution settings:\n   - `n_samples` low enough for wide data.\n   - `max_retries` bounded, usually `1` to `3`.\n   - `log=True` only when the user wants generated code\u002Ferror files, with a user-selected relative `log_path`.\n   - `human_in_the_loop=True` only when a review\u002Fresume interaction is acceptable.\n4. Invoke through the class wrapper (`DataCleaningAgent`, `DataWranglingAgent`, `DataVisualizationAgent`, or `FeatureEngineeringAgent`) unless the caller specifically needs the lower-level `make_*_agent` graph.\n5. Retrieve results through getters or `get_response()`; inspect generated code before reusing it outside the package workflow.\n6. If generated code fails, use the returned error key, bounded retries, logs, and the troubleshooting table rather than rerunning blindly.\n\n## Fast reference map\n\n- API signatures, response keys, getters, and shared graph behavior: [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md)\n- End-to-end cleaning, wrangling, visualization, and feature engineering patterns: [`references\u002Fworkflows.md`](references\u002Fworkflows.md)\n- Human review, checkpointers, resume commands, and generated-code logging: [`references\u002Fhuman-in-the-loop-and-logging.md`](references\u002Fhuman-in-the-loop-and-logging.md)\n- Symptom-based fixes for token pressure, sandbox errors, malformed outputs, and Plotly warnings: [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md)\n- Safe import\u002Fsignature\u002Fsandbox probe with no model call: [`scripts\u002Finspect_dataframe_agents.py`](scripts\u002Finspect_dataframe_agents.py)\n\n## Key safety facts\n\n- Generated pandas\u002FPlotly code is executed by the package through a subprocess sandbox with a timeout, a memory limit, and blocked imports for common filesystem, process, and network modules.\n- The sandbox is a guardrail, not a proof of correctness. Tell the user to review generated functions, especially before copying them into production notebooks or pipelines.\n- The default report node is deterministic: it packages selected state keys into an `AIMessage` without another model explanation call.\n- Human-in-the-loop review pauses after code execution when enabled, so use a checkpointer and stable `thread_id` if the run must be resumed.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":29},{"import":25,"package":26,"version":27,"disco-role":28},"ai_data_science_team","ai-data-science-team","0.0.0.9017","operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fai-data-science-team\u002Fsub-skills\u002Fdataframe-code-agents",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":39,"prompt":49,"zipAvailable":29},[40,43,46],{"tool":41,"command":42},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill dataframe-code-agents",{"tool":44,"command":45},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill dataframe-code-agents",{"tool":47,"command":48},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill dataframe-code-agents","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\u002Fai-data-science-team\u002Fsub-skills\u002Fdataframe-code-agents\u002FSKILL.md",[51,57,61,65],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fapi-reference.md","REFERENCE","参考文档",11493,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fai-data-science-team\u002Fsub-skills\u002Fdataframe-code-agents\u002Freferences\u002Fapi-reference.md",{"path":58,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fhuman-in-the-loop-and-logging.md",6649,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fai-data-science-team\u002Fsub-skills\u002Fdataframe-code-agents\u002Freferences\u002Fhuman-in-the-loop-and-logging.md",{"path":62,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",8406,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fai-data-science-team\u002Fsub-skills\u002Fdataframe-code-agents\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fworkflows.md",9062,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fai-data-science-team\u002Fsub-skills\u002Fdataframe-code-agents\u002Freferences\u002Fworkflows.md",[70,77,84,91,99,106],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7EXRM12046G0GM1WGMMFXCN","ci-cd-and-automation","Automates CI\u002FCD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fci-cd-and-automation\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7EXRFYYSJ3Y15AGPDDEWWQD","chrome-devtools","Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to `--slim` mode (MCP configuration).","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fchrome-devtools\u002FSKILL.md",[],[],{"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":19},"01M7EXR6EYPE4X5X1BTAE6QJRV","chrome-cdp","Drive a real Chrome via the Chrome DevTools Protocol (CDP). Ensures a\ndebuggable Chrome is running (launching it if needed) so the agent can\nnavigate, read page content, inspect the DOM, run JavaScript, and take\nscreenshots — without the user typing any launch command. Includes a\nfirst-class \"review a live running app\" flow: point Chrome at the app under\ndevelopment and inspect\u002Fscreenshot the REAL page (what a static-artifact tool\ncannot do). Backed by Glimpse and the chrome-devtools MCP server. Use when\nasked to \"use chrome\", \"open chrome\", \"drive my browser\", \"read the page in\nchrome\", \"review the running app\", \"screenshot the app\", or \"\u002Fchrome-cdp\".","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fchrome-cdp\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":95,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7EXR1Y7E79KQKG4J798XGH6","check-identity-pack","Run an AFP 100-point or AUSTRAC safe-harbour identity check over a set of documents, and report exactly what's missing. Use when the user asks to check identity documents, verify someone's ID for onboarding, or assess whether a document pack satisfies Australian identity requirements.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fcheck-identity-pack\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M7EXQXW7C7PGREJW9ZZTZ16H","changelog","Auto-generates a changelog from git commits, sprint data, and design documents. Produces both internal and player-facing versions.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fchangelog\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M7EXQMH2ZME3ANN8Q8MEWPFB","cellxgene-census","Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs\u002Fdownloads, embeddings, spatial Census data, or reference atlas comparisons across organisms, tissues, diseases, assays, and cell types. For analyzing your own local single-cell data use scanpy, anndata, or scvi-tools.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fcellxgene-census\u002FSKILL.md",[],[]]