Data & Analytics

cas-bigdatalab Bundle

数值关联规则校验工具。读取被检验表，根据用户自定义的条件表达式（类似Hive SQL规则）进行数据校验， 具有关联关系的数据项需满足特定约束条件。不满足条件的数据会标记质控标识并输出异常数据。 当用户提到关联规则校验、数据约束校验、自定义规则校验、条件表达式校验等需求时使用此skill。 即使用户没有说出"关联规则"，只要任务涉及根据自定义条件表达式进行数据校验，就应该使用此skill。

cas-bigdatalab Bundle

字段分布校验工具。读取结构化数据文件（CSV、TSV、Excel等），按模式检查数值字段统计特征或分类字段频率分布是否合理。 数值模式用于检查均值、标准差、中位数、分位数等统计量；分类模式用于检查类别数上限和单类占比是否异常。 当用户提到分布校验、统计特征验证、类别频率检查、类别倾斜检测等需求时使用此skill。 即使用户没有明确说出"分布校验"，只要任务涉及验证字段整体分布是否偏移或失衡，就应该使用此skill。

cas-bigdatalab Bundle

跨字段比较校验工具。读取结构化数据文件（CSV、TSV、Excel等），检查两个字段之间的逻辑约束关系 是否满足（如 start < end、min ≤ max、price >= cost），支持六种比较运算符，多约束可组合使用。 当用户提到跨字段校验、字段间比较、逻辑约束检查、大小关系验证等需求时使用此skill。 即使用户没有明确说出"跨字段"，只要任务涉及验证两个字段值之间的逻辑关系，就应该使用此skill。

cas-bigdatalab Bundle

数值数据阈值检验工具。读取结构化数据文件（CSV、TSV、Excel等），检查数值字段是否在指定的门限范围内，不允许超出门限值之外，最后输出为同格式的文件。当用户需要对数据进行阈值检验、数值范围检查、数据质量控制等操作时使用此skill。

microwind Bundle

当生成SQL查询、验证SQL、优化查询或调试SQL错误时，在执行到生产数据库之前验证SQL。

davekilleen Bundle

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

quantumquirkxyz Skill

Design analytical warehouse schemas — star / snowflake / OBT — with dimension, fact, and bridge tables; partitioning; indexing; and query optimization.

quantumquirkxyz Skill

Analyse experimental physics data with ROOT, pandas, uproot, NumPy — calibration, systematic errors, statistical inference, result archival — with reproducible scripts.

daemon-blockint-tech Bundle

Formulate and implement operations research optimization models—LP, MIP/QP, constraint programming, network flows, assignment, VRP, scheduling, resource allocation, inventory/production planning; heuristics and metaheuristics; sensitivity and infeasibility diagnosis; solver integration (OR-Tools, Gurobi, CPLEX, HiGHS, PuLP, Pyomo); production OR APIs (timeouts, warm starts). Use for operations research, OR engineer, optimization model, linear programming, mixed integer programming, MIP, VRP, vehicle routing, scheduling optimization, OR-Tools, Gurobi, constraint programming, resource allocation optimization, infeasible model, metaheuristic—not ML prediction (data-scientist), SCM strategy without optimization math (supply-chain-manager), WMS features (wms-developer), simulation platforms (simulation-software-engineer), generic backend (senior-software-engineer), dbt/warehouse (analytics-data-engineer).

daemon-blockint-tech Bundle

Guides advanced short-term actuarial mathematics aligned with SOA ASTAM and P&C/health-adjacent modeling—severity and frequency distributions, aggregate and compound loss models, Bühlmann and Bühlmann-Straub credibility, ratemaking and experience rating, short-term reserving at the math level, MLE and goodness-of-fit, and risk measures (VaR, TVaR). Tool-agnostic and concept-first. Use when the user mentions advanced short-term actuarial mathematics, ASTAM, severity model, frequency model, aggregate loss, compound distribution, Bühlmann credibility, experience rating, ratemaking, pure premium, negative binomial frequency, tail factor, TVaR, or short-term actuarial models—not life contingencies (life-health-insurance), Excel workpapers only (actuarial-analyst), appointed actuary sign-off (actuary, appointed-chief-actuary), assumption governance (assumption-setting), P&C legal/operations depth (property-casualty-insurance), or general ML (data-scientist, quantitative-researcher).

unboundcompute Skill

Decide whether a whitebox lead is a real bug by tracing taint from an untrusted source to a dangerous sink and confirming every hop against live source. Use after a scanner, a candidate list, or your own reading surfaces a "this looks dangerous" sink (SQL exec, system/exec, file open, deserialize, template render, redirect target, memcpy) and you must decide whether attacker- controlled input actually reaches it - or kill the lead with evidence. Covers forward and reverse taint, witness paths, sanitizer analysis, and the evidence rules that separate a finding from a false positive.

unboundcompute Skill

Hunt injection into search and analytics engines such as Elasticsearch, OpenSearch, and Solr where untrusted input reaches a query DSL body, a query-string or Lucene query, a script field, or a stored scripting expression. Covers request data that becomes query structure (a filter clause, a field selector, an aggregation) rather than a bound term, a raw query-string parameter whose Lucene syntax the caller controls, and script injection through inline or stored scripts that run in the engine. Use when an application forwards user input into a search cluster as query JSON, a query string, or a script. The untrusted value that becomes query or script structure is the source, the search or script call is the sink, and the missing field allowlist or the enabled dynamic script is the bug.

cslawyer1985 Skill

主体合规追踪器——初始化、报告即将到来的截止日、更新状态、运行健康审计、 导出为 CSV。维护从主体清单构建的 compliance-tracker.yaml，按主体和 注册地计算申报截止日，呈现未来30/60/90天内的待办事项。当用户说"主体合规" "申报截止日""年报到期""主体追踪器""什么申报到期""主体健康"或"存续状态"时使用。

lamm-mit Bundle

Extract and preview data from Excel and CSV spreadsheets for scientific analysis

lamm-mit Bundle

Read a CSV or XLSX file and return columns, shape, dtypes, and first N rows as JSON.

lamm-mit Bundle

Execute arbitrary Python code and return stdout. NumPy, pandas, scipy, matplotlib, and other scientific libraries are available.

lamm-mit Bundle

Query and analyze structured CSV datasets on critical minerals production, trade, and supply chains

lamm-mit Bundle

3D tetrahedral FEM modal analysis of a membrane STL. Takes a binary STL (mm units) + material properties JSON, repairs surface mesh, generates tetrahedral volume mesh via TetGen, assembles 3D stiffness/mass matrices with jax-fem, solves the generalised eigenvalue problem, and reports eigenfrequencies + mode shapes. Returns artifact JSON with eigenfrequencies_hz, eigenfrequencies_khz, modes_in_range, target_range_pass, and paths to summary PNG and CSV.

inbharatai Skill

Create, read, edit, and fix spreadsheets — add columns, compute formulas, format cells, generate charts, and clean messy tabular data.

inbharatai Skill

Perform SQL-based data analysis — exploratory queries, aggregations, funnels, cohorts, and insight narratives.

inbharatai Skill

Write and optimize complex SQL queries — JOINs, CTEs, window functions, query plans, and dialect-specific syntax.

inbharatai Skill

Facilitate cohort-based learning — weekly prompts, peer challenges, group projects, and community engagement.

inbharatai Skill

Analyze, clean, transform, and summarize CSV files — detect anomalies, compute statistics, and produce actionable insights.

inbharatai Skill

Master pandas operations — DataFrames, Series, groupby, merge, time-series resampling, and memory optimization.

inbharatai Skill

Write PySpark and Spark SQL jobs — RDDs, DataFrames, streaming, MLlib, and cluster configuration.

daemon-blockint-tech Bundle

Guides design, implementation, and operation of B2B electronic data interchange—X12 and EDIFACT, transaction mapping (850/855/856/810/997, ORDERS/DESADV/INVOIC/APERAK), canonical-to-segment translation, partner implementation guides, syntax and SNIP validation, functional acks and exceptions, transport (AS2, SFTP, VAN), healthcare variants (834/835/837) without PHI in outputs, certification testing, production monitoring, idempotency and reconciliation. Use when the user mentions EDI engineer, electronic data interchange, X12, EDIFACT, 850 purchase order, 856 ASN, 810 invoice, 997 acknowledgment, EDI mapping, AS2, partner onboarding, implementation guide, EDI validation, or VAN—not generic API integration without EDI (senior-software-engineer), WMS warehouse workflows (wms-developer), supply chain strategy without EDI build (supply-chain-manager), healthcare compliance program only (compliance-engineer), or OR routing and solver math (operations-research-algorithm-developer).

daemon-blockint-tech Bundle

Guides cybersecurity detection engineering using MITRE D3FEND—file analysis, identifier reputation, network traffic analysis, physical access monitoring, and platform monitoring. Covers dynamic/emulated analysis, traffic signature detection, behavior analytics, and integrity monitoring. Use when building detection rules, analyzing malware, monitoring networks, or designing SOC workflows—not for hardening (d3fend-harden), isolation (d3fend-isolate), or deception (d3fend-deceive).

daemon-blockint-tech Bundle

Guides design, build, customization, and integration of warehouse management systems—receiving, putaway, inventory, allocation, picking (wave/batch/zone), packing, shipping, cycle counts; slotting; lot/serial/expiry; RF/mobile and barcode; WMS–ERP–TMS–OMS integration; EDI/API; WCS/automation handoffs; peak scaling; multi-warehouse and 3PL models. Use when the user mentions WMS developer, warehouse management system, pick path, wave planning, putaway, cycle count, WMS integration, RF scanning, slotting, 3PL WMS, fulfillment system, inventory allocation, or WMS customization—not supply chain strategy without WMS (supply-chain-manager), generic ERP consulting, logistics routing without WMS, OT/ICS plant (scada-ics-cyber-security-specialist, control-software-developer), analytics warehouse marts (data-warehouse-engineer), or generic app/platform work without warehouse domain (senior-software-engineer, platform-engineer).

daemon-blockint-tech Bundle

Design data architecture at enterprise and solution levels. Cover data mesh, lakehouse, governance, domain-driven design, conceptual/logical/physical data modeling, platform selection, and compliance frameworks. Produce ADRs, data model diagrams, platform comparison matrices, and governance policy templates. Triggers on "design data platform", "choose data warehouse", "data mesh", "lakehouse architecture", "data governance", "data modeling", "platform selection", "data architecture decision", "compliance framework", or "data strategy". For applied AI solution architecture (RAG data plane, embeddings, vector stores in commercial or enterprise products), use applied-ai-architect-commercial-enterprise. For dbt analytics layers and mart delivery, use analytics-data-engineer—not data-architect.

daemon-blockint-tech Bundle

Guides cleaning and standardizing tabular datasets before analysis, modeling, or reporting—profiling, quality rules, missing values, duplicates, outliers, type coercion, encoding fixes, record linkage, deduplication, high-level PII handling (not legal advice), actuarial/insurance field scrubbing, reproducible scrub pipelines, validation checks, and sign-off. Distinct from warehouse ETL or statistical modeling. Use when the user asks for "data scrubbing", "clean this dataset", "scrub the data", "data cleaning", "dedupe records", "handle missing values", "outlier treatment", "standardize columns", "data quality rules", "profile this table", or "prepare data for modeling". Not warehouse pipelines (data-warehouse-engineer), ML modeling (data-scientist, actuary), privacy programs (compliance-engineer), FinOps only (finops-analyst), or assumption governance (assumption-setting).

daemon-blockint-tech Bundle

Guides hands-on actuarial analyst work for insurance, reinsurance, and pension—reserving and loss development (IBNR, triangles, chain-ladder diagnostics), pricing and rate indication support (experience, trend, credibility, basic GLM at spec level), data validation and model I/O review, reporting packs and workpapers, assumption application under actuary direction, and statutory tie-outs at analyst depth. Use when the user mentions actuarial analyst, loss development, IBNR, reserve analysis, rate indication, pricing support, actuarial workpaper, triangle analysis, credibility, experience study, actuarial reporting, or reserve roll-forward—not actuary sign-off (actuary), consulting engagements (actuarial-consulting), assumption governance (assumption-setting), ALM strategy (asset-liability-management), P&C legal depth (property-casualty-insurance), charts only (data-visualization), or ETL-only pipelines (data-scrubbing).

daemon-blockint-tech Bundle

Guides applied predictive analytics for business—target and leakage framing, tabular feature engineering, regression and classification models (baselines, boosting, regularized linear), validation splits and metrics, calibration and cost-sensitive thresholds, practitioner explainability (importance, SHAP), drift monitoring concepts, and uncertainty comms. Covers churn, demand, fraud, propensity, risk scores—not actuarial reserving. Use for "predictive analytics", "build a predictive model", "propensity model", "churn prediction", "demand forecast model", "classification model", "feature engineering", "model validation", "predict customer behavior", "risk score model", or "predictive modeling workflow". Not for MLOps (ml-infrastructure-engineer-safeguards), DL research (ml-research-engineer-safeguards), actuarial reserving (actuarial-analyst), BI only (data-visualization), warehouse/dbt only (data-warehouse-engineer, analytics-data-engineer), or A/B tests (ab-testing-engineer).

daemon-blockint-tech Bundle

Guides analytics engineering—dbt (or equivalent) project structure, staging/intermediate/mart models, dimensional and wide-mart patterns, incremental and CDC loads, data tests and contracts, documentation and lineage, CI for analytics code, and handoff to BI semantic layers. Use when building or refactoring analytics models, writing dbt SQL, defining tests and exposures, debugging mart freshness, or aligning warehouse tables to business metrics—not for leading product-embedded analytics teams or launch roadmaps (analytics-data-engineering-manager-product), enterprise data platform ADRs (data-architect), deep warehouse platform tuning only (data-warehouse-engineer), dashboard design (bi-analyst), or ML modeling (data-scientist).

daemon-blockint-tech Bundle

Guides developer education leadership—audience and skills-gap analysis, learning paths and curriculum design, workshops and cohort programs, hands-on labs, certification or badging, instructor enablement, feedback loops, and success metrics (completion, confidence, time-to-first-success). Use when building or scaling a developer training program, onboarding engineers to a platform, designing certification, planning launch enablement for developers, or aligning docs/tutorials with learning outcomes—not for writing single API pages (tech-writer-researcher), customer support macros (product-support-specialist), generic exec comms (communication-lead), or shipping product code (senior-software-engineer).

daemon-blockint-tech Bundle

Guides business model research—Business Model Canvas and Lean Canvas, value proposition and customer segments, revenue and pricing models, unit economics (CAC, LTV, payback), market sizing (TAM/SAM/SOM), competitive business-model benchmarking, and evidence-backed synthesis for startups and product strategy. Use when researching how a company or idea makes money, comparing competitor monetization, sizing a market, stress-testing unit economics, drafting a canvas for a pitch, or documenting monetization hypotheses—for shipping pricing/packaging PRDs and paywalls use product-management-monetization—not for delivery BRDs (business-analyst), steerCo consulting engagements (business-consultant), GAAP revenue recognition (senior-revenue-accountant), internal BI SQL (bi-analyst), or technical architecture (senior-system-architecture).

daemon-blockint-tech Bundle

Guides pre-credential actuarial foundations—probability and statistics for actuaries, financial math (interest, annuities, loans, duration intro), insurance risk concepts, spreadsheet/R/Python literacy, SOA/CAS/IAI path overview, and quantitative study discipline. Use for pre-actuarial, actuarial foundations, probability for actuaries, financial mathematics basics, interest theory, starting actuarial career, SOA exam path, actuarial science basics, learn actuarial math, or entry level actuary preparation—not ASTAM/ALTAM (advanced-short-term-actuarial-mathematics, advanced-long-term-actuarial-mathematics), workpapers (actuarial-analyst), signing/governance (associate-actuary, appointed-chief-actuary), generic calculus homework, or ML (data-scientist, quantitative-researcher).