All categories
Data & Analytics
Data analysis, BI, visualization, datasets, statistics, and ML workflows
- 13,012
- 543
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse data & analytics skills
Showing 2,041–2,064 of 13,012 skills
- Aisbench Dataset Compression Herding当用户直接要求进行数据集压缩测评，或在量化调优过程中需要使用 AISBench 评测工具输出数据集精度等场景时使用。 本 Skill 负责：使用 AISBench 数据集压缩代码、用 RBF Kernel Herding 算法生成压缩后的数据子集（coreset），并按用户目标交付两种产物之一： ① 接入量化调优主流程：产出独立的 coreset 数据集配置（不覆盖原始数据），回传「全集 config_name + coreset config_name」给编排层，供 evaluation.yaml 切换； ② 仅数据集压缩测评（不做量化调优）：基于 example 模板生成「全集测试脚本」和「子集测试脚本」两份 shell 脚本。 暂时支持 AIME 2025 和 GPQA，其他数据集需要再结合 aisbench tools目录下 herding_coreset_selector 源码进行分析。Votes: 0GitHub stars: 31
- Spike Root Cause Analysis分布式训练梯度尖刺 (Gradient Spike) 根因定位。基于梯度监控数据 (trend.db/CSV)、 msprobe dump 统计数据，三阶段渐进式从异常坐标定位逐层深入到算子级根因。 当用户明确指明分析梯度尖刺问题时使用此 skill。 即便用户提供以上数据，但未指明分析梯度尖刺问题时，不可使用此skill。Votes: 0GitHub stars: 31
- Nan Overflow Detection多卡分布式训练中的 loss/gnorm 精度溢出检测与根因追溯。基于 MSProbe dump 数据，先跨 rank 定位首次出现 NaN 的源卡，再在源卡上追溯具体的溢出根因算子。 当用户需要：(1) 多卡分布式训练场景下的 NaN/Inf 溢出检测 (2) 找出首先出现 NaN 的源卡 (3) 追溯根因计算算子 (4) loss/gnorm NaN 问题定位 时使用此 skill。Votes: 0GitHub stars: 31
- Deterministic Calculation Analysis执行msProbe数据比对并分析比对结果，定位确定性计算问题首个输入一致输出不一致的API。Votes: 0GitHub stars: 31
- Compare Result Analyzer分析 msProbe compare 精度比对结果文件（CSV/XLSX），定位整网精度问题与数值差异。支持统计量模式，输出分析报告。支持辅助信息协助定位：辅助信息（历史结论/已知根因/已排除算子/嫌疑区域等）建议在请求中附带（不依赖交互工具）。若请求中未附带且运行环境无 AskUserQuestion，则跳过辅助信息收集、照常完成分析，报告中省略辅助信息章节并注明原因。Votes: 0GitHub stars: 31
- Reversa Highcharts VisualizerCria visualizações de dados interativas com Highcharts.js, gerando HTML standalone com gráficos animados, responsivos e acessíveis a partir de dados inline, CSV ou JSON.Votes: 0GitHub stars: 31
- Youtube Growth Playbook 2026Turn YouTube growth advice videos into an evidence-checked, executable 90-day channel operating plan. Use when the user asks how to grow a small YouTube channel, how to survive the early no-views phase, how to design titles and thumbnails, whether an algorithm claim is true, or how to run packaging experiments with YouTube Studio only. Also triggers on: 떡상, 유튜브 성장, 죽음의 계곡, 알고리즘 미신, 채널 일관성, 제목 썸네일 A/B 테스트.Votes: 0GitHub stars: 47
- Multi Source Wasserstein Distributionally Robust Graph LearningMS-WDRO for brain connectivity with heterogeneous data.Votes: 0GitHub stars: 3
- Arxiv 2609 24386v1 Machine Learning Based Prediction Of Childhood Stu**arXiv ID:** 2609.24386v1 **Authors:** Md Ahshanul Haque, Muhammad Ashad Kabir **URL:** http://arxiv.org/abs/2609.24386v1 **Utility Score:** 1.00Votes: 0GitHub stars: 3
- Prediction Market Oracle ResearchResearch prediction markets as data sources or oracle signals for products, agents, dashboards, and corporate decision intelligence. Use for source-grounded analysis of market-implied probabilities, caveats, and integration patterns without investment advice.Votes: 0GitHub stars: 17
- Differential Gene Analysis Rna SeqOpenCLAW Skill for bioinformatics data analysis.Votes: 0GitHub stars: 12
- Data Quality AuditorAudit datasets for completeness, consistency, accuracy, and validity. Profile data distributions, detect anomalies and outliers, surface structural issues, and produce an actionable remediation plan.Votes: 0GitHub stars: 12
- Huggingface DatasetsUse this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.Votes: 0GitHub stars: 12
- Baoyu Article IllustratorArticle illustrations: type × style × palette consistency.Votes: 0GitHub stars: 17
- StatusReport git state, ready work, blocked items, and PR health. Use when the user runs /status or wants a workspace snapshot.Votes: 0GitHub stars: 2
- Metainformant Archive Scripts ReorganizeMETAINFORMANT rules for directory archive/scripts_reorganize. Use when editing, adding tests, or reviewing code under this path. Read the linked AGENTS.md first; use uv only, write outputs to output/, real implementations.Votes: 0GitHub stars: 8
- Healthcare Data ReconciliationInvestigate disagreements between healthcare source records and downstream outputs. Use for claims/RCM totals, HL7/FHIR record pulls, mappings, clinical-result routing or patient-operations state. Produce an evidence trace and discriminating checks without assuming a root cause or authorizing data changes.Votes: 0GitHub stars: 3
- Healthcare Data Readiness DebriefDebrief one healthcare data project where preparation took more work than expected. Use a project summary or short interview to identify evidence gaps, trace their effect on the intended use, and produce a practical next-check brief. Works without patient records or database access.Votes: 0GitHub stars: 3
- Healthcare Cohort DesignTurn a healthcare population question into a reviewable cohort specification and acceptance cases. Use for claims or EHR cohorts, OMOP studies, quality-reporting denominators or trial-feasibility counts. Does not determine clinical trial eligibility or supply licensed measure logic.Votes: 0GitHub stars: 3
- Duckdb Data ProfilingProfile approved CSV or Parquet files with DuckDB and produce reproducible quality and join checks. Use for local exploratory analysis, schema drift, identifier preservation or source reconciliation. Does not authorize sensitive-data downloads or arbitrary SQL execution.Votes: 0GitHub stars: 3
- Databricks Data Product ReviewReview a Databricks data product or proposed release using approved metadata and query evidence. Use for Unity Catalog scope, Delta change handling, reconciliation, or a release handoff. Does not provision infrastructure or authorize production writes.Votes: 0GitHub stars: 3
- Data Product OperatorHelp a data leader or data product manager choose the next decision, coordinate delivery and review outcomes across one product or a portfolio. Use to establish or improve a data-product operating rhythm, connect existing skills and preserve decision context. Domain agnostic; does not replace the team's tools or grant execution authority.Votes: 0GitHub stars: 3
- AnalystBuild or update an evidence graph for a data analysis by linking the question, definitions, source versions, checks, findings and decisions. Use when an analysis spans multiple skills or someone asks what supports a conclusion, what changed, or what to check next. Does not grant data access or approve release.Votes: 0GitHub stars: 3
- Metamask Official InstrumentationCreate and update Sentry spans, MetaMetrics events, and Segment events — methodology, policies, common pitfallsVotes: 0GitHub stars: 76