Data & Analytics

googlecloudplatform Bundle

Guides the agent to execute an evaluation of a ContextSet against a golden NLQ+SQL dataset using the Evalbench framework.

googlecloudplatform Bundle

Generate or expand a golden evaluation dataset of SQL/Question (NLQ+SQL) pairs for evaluating NL-to-SQL translation accuracy on a target database.

gravitational Bundle

Use when reviewing who can access which resources in a Teleport cluster, or whether that access is actually used — access list / ACL recertification, "who can reach this database/server", "what can this user access", attesting access for audit/compliance, and finding dormant or unused standing privileges. Covers `tctl access-review`, the `access_path` SQL query language, output semantics, and combining it with `tctl investigate`.

aeonfun Skill

Fleet skill observability with two views - health audits per-skill metrics and files/resolves issues in memory/issues/; analytics ranks the fleet by 7d runs, success rates, and anomaly flags.

pugyy Skill

数仓 ETL 开发流程，适用于生成 ODPS/MaxCompute 建表 DDL、INSERT SQL 和 SR 建表语句，并配合 hooks 自动校验 SQL 规范。直接调用命令：/dw-etl。

pugyy Skill

数仓性能优化流程，适用于分析 ETL SQL 执行计划、分区裁剪、JOIN 策略、数据倾斜和资源瓶颈。直接调用命令：/dw-performance-optimization。

qingtiandamowang Skill

MySQL 建表规约、索引规约、SQL 语句与 ORM 映射（阿里巴巴Java开发手册第五章）。Use when designing database tables, choosing column types, naming indexes, writing DDL or SQL queries, or reviewing a database schema — in ANY language (Go, Rust, Python, Java), since these are schema-level constraints independent of the application language.

qingtiandamowang Skill

Web 应用安全规约：越权校验、敏感数据脱敏、SQL 注入防护、输入有效性验证（SSRF/ReDoS/注入）、XSS 转义、CSRF 校验、重定向白名单、防重放机制、文件上传校验、配置文件密码加密（源自阿里巴巴Java开发手册第四章）。Use when implementing authentication, authorization, input validation, or reviewing security — in ANY language (Go, Rust, Python, Java), since these are application-level security constraints independent of language.

revosai Skill

Inspect the RevOS BigQuery lakehouse: list datasets and tables, introspect table schemas and column types, preview sample rows, assess data layers (bronze/silver/gold), and check data completeness and null rates. Required companion skill for create-dbt-transformations and create-cubes — load before generating dbt models or cube definitions to introspect warehouse columns and types. Use when asked to: explore the lakehouse, list BigQuery tables, inspect a table schema, preview data, check raw source tables, assess data quality, check null rates, understand available data, or perform BigQuery schema introspection.

revosai Bundle

Create a RevOS Connection YAML that syncs data from a Source into the org's data warehouse. Use whenever the user asks to: add a connection, set up a sync, ingest a table, pipe data from a source, configure streams, pick which tables to ingest, or wire up a Source. The skill picks a sensible stream subset (especially important for databases — most projects don't want every table) and confirms the choice before writing YAML.

revosai Bundle

Create new dbt transformations (silver/gold models) in the RevOS dbt project. Use when asked to create a dbt model, build a transformation, add a new layer model, declare a raw source, or register a new raw table. Bronze is source-declarations only — no SQL files. Covers dbt project conventions, sources, materialization, schema.yml, and validation commands.

romainsimon Bundle

Prices research, tests, surveys, dashboards and experiments before running them, by computing how much the result would raise expected utility - which is zero whenever no outcome would change the decision. Use when someone proposes an A/B test, user survey, market study, competitor analysis, analytics build, consultant, pilot, or "let's gather more data", and when deciding how large a study needs to be.

cognitedata Skill

Full best-practices audit of a CDF (Cognite Data Fusion) project. Scans all Cognite Toolkit YAML, SQL, and Python files and produces a structured AUDIT_REPORT.md covering naming conventions, data modeling, transformations, functions, workflows, and DMS query patterns. Use this skill whenever the user says "audit this project", "run best practices audit", "check best practices", "full audit", "validate CDF project", "compliance check", "run the auditor", "cog-vd-audit", "audit everything", or asks to review a project against Cognite best practices or production readiness. Also trigger when the user shares a project directory and asks if it follows the right patterns, is ready for production, or is ready for go-live.

cognitedata Skill

Expert guidance on CDF Transformations. Use when the user is writing, reviewing, or troubleshooting a CDF Transformation SQL query running on the Spark SQL backend, configuring Transformation YAML files for the Cognite Toolkit, working with transformation destinations (nodes, edges, instances, raw, etc.), or auditing an existing transformation for performance, memory, incremental-load, JOIN, DM/delete, or formatting issues.

huiliyi37 Skill

Excel 电子表格读写与编辑最佳实践 — 用 xlsx_read/xlsx_write/xlsx_edit 处理 .xlsx 时遵守的公式、数字格式与可维护性纪律

igniteui Bundle

All Ignite UI for Blazor data grids — Grid Lite, Flat Grid, Tree Grid, Hierarchical Grid, Pivot Grid: setup, columns and templates, sorting, filtering, selection, cell and row editing, grouping, summaries, toolbar, Excel/CSV export, paging, remote and server-side data, virtualization, sizing, state persistence, and migrating Grid Lite to IgbGrid. Use for grids, tables, tabular data, cell editing, row selection, column pinning or hiding, grouped rows, pivot tables, tree or hierarchical data, master-detail views, and grid export. For non-grid components use igniteui-blazor-components; for theming use igniteui-blazor-theming.

dwani-ai Skill

Cross-chunk executive synthesis for warehouse and CCTV video job summaries — observations, security, logistics, attendance counts only.

dwani-ai Skill

Safety and security risk triage from aggregated chunk-level CCTV and warehouse analysis JSON.

dwani-ai Skill

Privacy and re-identification risk review for structured video analytics JSON (scenes, events, counts).

edtechre Bundle

Write, register, and debug PyBroker indicators using the bundled PyBroker wiki references generated from the local docs. Use when an agent needs to write custom indicator functions with pybroker.indicator, vectorize indicator logic with NumPy and Numba @njit kernels, wrap third-party technical analysis libraries such as TA-Lib, pandas-ta, ta, tulipy, or finta, use the built-in indicator factories and vector helpers, compute indicators standalone with IndicatorSet, parameterize indicators with hyperparams for optimization, compute indicators on multiple time intervals, feed custom data columns into indicators, cache indicator computations, or debug Numba compilation errors and parallel indicator failures.

egoisutolabs Skill

Design multi-tab app screens (fitness / analytics / productivity / social) so each tab uses a distinct structural layout instead of just rotating accent colors. Use when the designer asks to "design a tab bar app", "make 4 screens for a fitness app", "Home / Insights / Profile screens", or any multi-screen app where the screens share chrome but serve different content kinds. Prevents the "four templated screens that feel fake" trap.

fastfold-ai Bundle

Run molecular dynamics (MD) simulations via the FastFold Workflows API. Today supports the CALVADOS+OpenMM workflow (calvados_openmm_v1) from either an existing fold job (AF structure + PAE auto-resolved) or manual PDB+PAE upload, then waits for completion, fetches metrics/plots/CSV artifacts, and extracts trajectory frames as PDB files. Use when running an MD simulation with FastFold, CALVADOS + OpenMM, reading MD metrics/plots, extracting frames, or scripting submit → wait → results for an MD run.

firetiger-oss Skill

Use when the user mentions Firetiger or wants to work with their observability data — setting up Firetiger, instrumenting an app with OpenTelemetry, querying traces/logs/metrics with SQL, investigating an incident, monitoring a PR or deployment, or creating a monitoring agent. Always use this skill when the user says "Firetiger", even for simple asks — it routes to the specialized skill that carries the critical gotchas (Basic-auth ingest, DuckDB SQL over per-service tables, the @firetiger comment flow) that prevent common mistakes.

imraywang Bundle

X(Twitter)账号数据周报:通过 xapi 拉近 7 天(可选 30 天对比)推文与指标,算周环比、挑出 top/bottom 推,把表现归因到声部/话题/hook 形式/发布时段这些可复现的规律,再给下周 2-3 条可执行的内容动作(加什么、停什么、测什么)。当用户要做 X/Twitter 数据周报或内容复盘、想知道哪条推表现好以及为什么、要基于数据(而不是拍脑袋)定下周内容方向、或说「看看我这周推文数据」「帮我复盘账号」时使用。触发:/ray-metrics 或 /ray-metrics 「@handle 或 时间范围」。xapi 拉不到数据时必须诚实报告并给替代路径(X Analytics 导出 csv / 浏览器读 analytics 页),绝不编造数据充数。不用于:替作者撰写推文成品(只给方向和骨架,不代笔)、拆解别人账号做对标(用 ray-benchmark)。

jeromwolf Skill

Generate a modern admin dashboard with charts, tables, and KPI cards. Supports admin, analytics, monitoring, and CRM styles. Uses glassmorphism design with dark theme.

mozilla-platform-ops Bundle

Query Mozilla's Redash (sql.telemetry.mozilla.org) for telemetry data from BigQuery. Use when querying Firefox user telemetry, OS distribution, architecture breakdown, FXCI task data, or running custom SQL against Mozilla's data warehouse. Triggers on "redash", "telemetry query", "sql.telemetry", "BigQuery query", "Firefox data", "client counts", "user population", "DAU", "MAU", "macOS version", "macOS distribution", "Apple Silicon", "aarch64", "x86_64", "architecture distribution", "Windows version", "Windows distribution", "how many users", "what share of users", "what percentage of Firefox users", "worker pool", "queue time", "Taskcluster queue", "FXCI task data".

nvidia Bundle

Use AFTER a Search has completed and BEFORE claiming any speedup or shipping an ACF. Loads the dump_results CSV, extracts top-K candidates (single-objective) or the Pareto front (multi-objective), re-measures each against the no-ACF baseline with 100+ trials on fresh caches, runs Welch's t-test plus Cohen's d, rejects three classic false-positive patterns (lucky-min / higher-variance / multiple-comparisons-of-N), and saves the validated winner as best.acf. Triggers on "validate result", "extract best config", "Welch's t-test", "is my speedup real", "save best ACF", "pareto front", "claim speedup", "ship config".

onlyfansapi Bundle

Build, use, and troubleshoot integrations with OnlyFansAPI.com. Use for OnlyFans API requests, account and fan management, chats, posts, media, analytics, tracking links, webhooks, automations, and OnlyFansAPI MCP setup.

osovv Bundle

Use when the user asks about token usage, cache hit rate, cache efficiency, model or provider consumption, session costs, or whether a vvoc release or OpenCode upgrade changed caching behavior. Runs read-only analysis over vvoc analytics (CLI and JSONL) and historical opencode.db data, then reports findings without modifying anything.

pluginagentmarketplace Bundle

Production-grade database design skill for SQL/NoSQL selection, schema design, indexing, and query optimization

posit-dev Bundle

Validate DataFrames and database tables with Pointblank. Covers the Validate workflow (plan, interrogate, report), column selectors, data backends (Polars, Pandas, DuckDB, databases via Ibis), threshold levels, actions, and result extraction. Use when building, running, or troubleshooting data-validation pipelines.

kehwar Bundle

Expert guidance for creating, implementing, and troubleshooting AC (Access Control) Rules in Frappe Tweaks - an advanced rule-based permission system. Use when working with AC Rules, Query Filters, AC Resources, AC Actions, implementing fine-grained access control, debugging permission issues, creating principal/resource filters, integrating with DocTypes or Reports, or understanding rule evaluation and SQL generation.

kehwar Bundle

Expert guidance for connecting Power Query (Power BI, Excel) to Frappe apps and reports. Use when building Power Query M code for Frappe data access, integrating Frappe reports with Power BI/Excel, implementing authentication for Power Query connections, handling heavy/long-running reports with report_long_polling API to avoid timeouts, applying column types and transformations, or troubleshooting Power Query caching and connection issues.

kimlawtech Skill

세무용 재무제표(재무상태표·손익계산서) 자동 생성 스킬. 국세청 표준계정과목 매핑, 일반기업회계기준(K-GAAP) 간소화 버전. 분류 완료된 거래내역을 기간 지정해 BS·PL로 집계하고 JSON·CSV 파일로 출력.

kimlawtech Skill

원본 재무 데이터(엑셀·은행 CSV·카드 내역 CSV·영수증 이미지·세금계산서 PDF·카드명세서 PDF)를 표준 거래내역 13개 필드로 변환하는 스킬. PaddleOCR 로컬 처리로 영수증·세금계산서·카드명세서에서 거래 자동 추출, Level 2 민감정보 마스킹 적용.

kimlawtech Skill

한국 스타트업·1인 법인 대표·프리랜서·개인사업자를 위한 장부 자동 생성 진입점 스킬. 호출 시 5개 하위 스킬(jangbu-import·jangbu-tag·jangbu-tax·jangbu-dash·jangbu-jongso)을 번호·문자 메뉴로 제시하고, 입력 즉시 해당 스킬 인터뷰로 직행한다. 엑셀·5대 은행 CSV·7대 카드사 명세서 PDF·영수증·세금계산서 지원, macOS Vision/PaddleOCR 로컬 처리, Level 2 민감정보 마스킹.