Data & Analytics

mister2d Bundle

Expert skill for document intelligence tasks powered by a self-hosted Apache Tika instance. Use this skill whenever the agent needs to: extract text from any file (PDF, DOCX, PPTX, XLSX, email, EPUB, archive, image, video, audio, geospatial, or any other format); detect MIME types or file metadata; recursively unpack compound documents like ZIP archives, EML emails with attachments, or embedded Office OLE objects; run OCR on scanned PDFs or images; detect document language; audit documents for embedded macros; or extract raw embedded assets such as images and charts from Word docs or PDFs. Also trigger for any workflow that needs to triage unknown file types before deciding how to process them, or that needs to feed clean text into a downstream LLM. Always prefer this skill over ad-hoc file parsing — Tika handles 1,400+ MIME types deterministically and Tesseract OCR is included in the deployed full container.

clickzetta Bundle

Singdata Lakehouse official documentation knowledge base (English). Consult references/ when writing SQL or answering questions about query syntax, functions, data types, DDL/DML, dynamic tables, permissions, vclusters, data lake, AI functions, and other Lakehouse topics.

clickzetta Bundle

Use the ZettaPark Python library to work with ClickZetta Lakehouse data through a pandas-like DataFrame API that translates Python transformations into distributed SQL — no manual SQL needed. Covers Session creation, DataFrame construction and transformation (filter/select/join/groupBy), result collection (collect/to_pandas/show), writing tables (save_as_table), file operations (PUT/GET), and executing SQL. Trigger when the user says: "ZettaPark", "zettapark", "DataFrame API", "Python Lakehouse", "save_as_table", "session.table", "session.sql", "collect()", "to_pandas", "Python data engineering", "Python write to Lakehouse", "Python read from Lakehouse", "clickzetta_zettapark_python", "Python ETL", "Python ML on Lakehouse", "feature engineering Python", "Python DataFrame Lakehouse". Keywords: ZettaPark, DataFrame, pandas-like, Python, SQL translation, distributed compute

clickzetta Bundle

dbt-clickzetta data modeling wizard: discovers Lakehouse data sources, infers modeling strategies, generates sources.yml and model files, and runs the full test suite. Presents choices rather than blank forms — explores data first, then proposes a justified plan for user confirmation. Trigger when the user wants to turn raw Lakehouse data into usable analytical tables — mentions dbt (dbt modeling, dbt model, sources.yml, incremental, dbt run, dbt test), wants ETL transformation, dimension/fact tables, or asks "how do I turn these tables into a queryable dataset". Keywords: dbt, dbt modeling, sources.yml, incremental, dbt run, dbt test, dimension table, fact table, ETL

clickzetta Bundle

ClickZetta Dynamic Table usage guide and routing hub, covering consultation (best practices, performance, incremental config), creation, and modification (ALTER, suspend/resume, columns). SQL conversion requests are delegated to the sql-to-dt sub-skill. Trigger when the user says: "dynamic table", "DT introduction", "dynamic table best practices", "dynamic table performance", "incremental computation", "REFRESH INTERVAL", "create dynamic table", "dynamic table scheduling", "dynamic table alerts", "ALTER DYNAMIC TABLE". Keywords: dynamic table, DT, REFRESH INTERVAL, incremental, suspend, resume, sql-to-dt

clickzetta Bundle

Migration guide for SQL workloads moving to ClickZetta Lakehouse from Snowflake, Databricks, or Spark SQL. Covers object concept mapping, syntax differences, function mapping tables, MERGE INTO limitations, strict implicit type conversion, and migration pitfalls. For native ClickZetta SQL syntax reference the Lakehouse documentation. Triggered when the user mentions migration source platforms (Snowflake, Databricks, Spark SQL) together with ClickZetta, asks about specific functions/syntax (IFF, LISTAGG, FLATTEN, TARGET_LAG, APPLY CHANGES INTO, ZORDER, WITH RECURSIVE, WHEN NOT MATCHED BY SOURCE), or asks about compatibility/differences. Keywords: Snowflake migration, Databricks migration, Spark SQL migration, vs Snowflake, vs Spark, vs Databricks, syntax differences, function mapping, implicit type conversion

clickzetta Bundle

Manage ClickZetta Lakehouse Volume objects for mounting object storage (OSS/COS/S3), querying files, and importing/exporting data. Covers creating External Volumes (OSS/COS/S3), User Volume file operations (PUT/GET/REMOVE), SELECT FROM VOLUME direct file queries, COPY INTO TABLE imports, COPY INTO VOLUME exports, and more. Triggered when users say "create Volume", "mount OSS", "mount S3", "mount COS", "Volume management", "query OSS files", "query S3 files", "upload files to Volume", "PUT files", "GET files", "import data from Volume", "export to Volume", "COPY INTO VOLUME", "SELECT FROM VOLUME", "User Volume", "data lake files", "data export", "export data", "export CSV", "export Parquet", "COPY OVERWRITE INTO". Keywords: Volume, OSS, COS, S3, mount, file query, COPY INTO, external storage

clickzetta Bundle

Complete guide for managing ClickZetta Analytics Agent domains via cz-cli: domain CRUD, table registration, column semantics (types/descriptions/aliases), metrics (simple & compound), Answer Builders, Knowledge Bases, and QA testing. Wizard-driven workflows with intent classification, routing tables, and troubleshooting references. Trigger when the user says: "analytics agent", "分析域", "语义层", "指标", "answer builder", "知识库", "多别名", "column semantics", "domain prompt", "metric create", "AB create", "session run", "domain table add", "semantics set", "knowledge space". Keywords: analytics agent, domain, semantics, metric, answer builder, knowledge base, alias, cz-cli, data analysis, AI agent, semantic layer

clickzetta Bundle

dbt-clickzetta project initialization wizard: builds a dbt project connected to ClickZetta Lakehouse, covering installation checks, profiles.yml, layering standards, and dbt_project.yml generation. Hands off to clickzetta-dbt-modeling after completion. Trigger when the user wants to build a data warehouse or start a dbt project in ClickZetta — "I want to build a data warehouse with dbt", "dbt beginner guide", "dbt project init", "dbt from scratch", "how to connect dbt to ClickZetta", "dbt profiles configuration", "how do I write profiles.yml". Keywords: dbt, project setup, profiles.yml, dbt-clickzetta, initialization, ELT, data warehouse setup

clickzetta Bundle

Write data to ClickZetta Lakehouse using the Spark Connector or Flink Write Connector. Covers Spark DataFrame read/write configuration (Maven dependencies, connection parameters, read/write code), Flink Table API writes (CDC mode igs-dynamic-table, append-only mode igs-dynamic-table-append-only), checkpoint configuration, buffer/flush tuning, and key constraints such as primary-key table limitations. Trigger when the user says "Spark Connector", "Flink Connector", "Spark writes to Lakehouse", "Flink writes to Lakehouse", "spark-clickzetta", "igs-flink-connector", "Spark DataFrame write", "Flink CDC write", "Flink sink", or "spark.read.format clickzetta". Keywords: Spark, Flink, DataFrame, connector, read, write, CDC, igs-dynamic-table

clickzetta Bundle

Automatically converts CREATE TABLE DDL + INSERT OVERWRITE SQL from Hive/Spark or any batch processing system into Dynamic Table DDL and companion files (refresh, prev_refresh, backfill). Trigger when the user provides DDL and INSERT OVERWRITE and requests conversion, or says "convert to DT", "sql to dt", "convert to dynamic table", "INSERT OVERWRITE to DT", "DDL conversion", "create dynamic table". Keywords: sql-to-dt, convert to DT, INSERT OVERWRITE, DDL conversion, dynamic table

clickzetta Bundle

Reference index for creating Dynamic Tables. Covers SQL patterns supported by incremental computation and incremental refresh configuration options. Keywords: dynamic table, DT creator, incremental, SQL patterns, refresh configuration

jinshuju Bundle

通过金数据（Jinshuju，jinshuju.net）MCP 操作用户托管在金数据平台上的在线表单与表格：创建 / 复制 / 编辑表单与主题，含自动判分的考试表单、选项计分的测评表单；创建 / 编辑多维表格；查询、新增（单条或批量）、更新、删除、批量修改数据，或把本地上传的 Excel / CSV 批量导入；建表格 / 看板视图筛选数据，建对外查询页供访客自助查询；用上传凭证上传本地图片或文件；在服务端统计数据（条数、分组、按天 / 周 / 月的趋势、整表字段分布画像），跨表单搜关键字；查询账户套餐额度与团队成员。仅在用户操作其金数据平台数据时使用——触发信号：提到 金数据 / Jinshuju / jinshuju.net、给出 form_token，或要操作一张已托管在金数据上的表单、表格或数据。不要用于：用代码开发表单 / 问卷系统、把本地文件当普通文档分析（与导入到金数据表单无关时）、图片 / 票据 OCR、物流或监控等与平台无关的自动化，以及与金数据平台无关的通用数据处理。

jinshuju Bundle

通过金数据（Jinshuju，jinshuju.net）MCP 操作用户托管在金数据平台上的在线表单：创建 / 复制 / 编辑表单与主题，含自动判分的考试表单、选项计分的测评表单；查询、新增（单条或批量）、更新、删除、批量修改数据，或把本地上传的 Excel / CSV 批量导入表单；建表格 / 看板视图筛选数据，建对外查询页供访客自助查询；用上传凭证上传本地图片或文件；在服务端统计数据（条数、分组、按天 / 周 / 月的趋势、整表字段分布画像），跨表单搜关键字；查询账户套餐额度与团队成员。仅在用户操作其金数据平台数据时使用——触发信号：提到 金数据 / Jinshuju / jinshuju.net、给出 form_token，或要操作一张已托管在金数据上的表单或数据。不要用于：用代码开发表单 / 问卷系统、把本地文件当普通文档分析（与导入到金数据表单无关时）、图片 / 票据 OCR、物流或监控等与平台无关的自动化，以及与金数据平台无关的通用数据处理。

jinshuju Bundle

通过金数据（Jinshuju，jinshuju.net）MCP 操作用户托管在金数据平台上的数据表格：创建 / 编辑 / 移动数据表与列（含自动计算的公式列）；查询、新增（单条或批量）、更新、批量更新、删除行数据，或把本地上传的 Excel / CSV 批量导入数据表；用上传凭证把本地文件写入附件列；在服务端统计行数据（条数、分组、按天 / 周 / 月的趋势、整表列分布画像），跨表搜关键字；查询账户套餐额度与团队成员。仅在用户操作其金数据数据表时使用——触发信号：提到 金数据表格 / Jinshuju 表格 / 数据表，或要在金数据上建表、加改列、批量维护行数据。不要用于：用代码开发表格系统、把本地文件当普通文档分析（与导入到金数据数据表无关时）、搭建对外收集的表单 / 问卷、图片 / 票据 OCR，以及与金数据平台无关的通用数据处理。

jinshuju Skill

金数据（Jinshuju，jinshuju.net）操作技能 —— 创建/复制/编辑表单与主题，增删改查与批量修改表单数据，把本地上传的 Excel/CSV 导入表单，建视图筛选与对外查询页，在服务端统计数据（条数/分组/趋势/分布画像）与跨表单搜关键字，上传图片附件，查询账户套餐与团队成员。触发词：金数据、Jinshuju、jinshuju.net、form_token、表单、报名表、问卷、数据录入、数据查询、批量修改、数据导入、数据统计、数据分析、跨表单搜索。

zhaolong666520 Bundle

Create publication-grade scientific figures and drive desktop Origin/OriginPro from Codex or Claude Code. Use for SCI, Nature/Science/Cell/IEEE/Elsevier, and thesis figures; automatic data inspection and chart recommendation; journal-style inference from PDFs, websites, or DOIs; Origin template automation; editable OPJU projects; batch export; redraw, beautification, export, or critique from CSV/TSV/TXT/XLSX/XLS, Python/Matlab/Origin outputs, screenshots, diagrams, or draft manuscript figures.

serialexperimentslainnnn Skill

Use when writing or reviewing the SQL language itself — .sql files, SELECT/JOIN/CTE/window function queries, GROUP BY and aggregation, NULL and three-valued logic, MERGE and UPSERT, DDL and CREATE TABLE, ALTER TABLE migrations and expand/contract, transactions, BEGIN/COMMIT, isolation levels, SELECT FOR UPDATE and deadlocks, parameterized queries and SQL injection in query construction, dynamic identifier quoting, SARGable predicates, EXPLAIN and query plans, ANSI SQL versus PostgreSQL/MySQL/MariaDB/SQL Server T-SQL/Oracle PL-SQL/SQLite dialect differences, .sqlfluff and sqlfluff, shandy-sqlfmt, or hand-written SQL versus ORM- and dbt-generated SQL.

serialexperimentslainnnn Skill

Use when a graph engine or a graph query is on the table — proving the traversal is variable-depth before adding an engine (friend-of-a-friend, shortest path, cycle detection, propagation) instead of a two-hop JOIN or a recursive CTE, Neo4j (cypher-shell, neo4j.conf, Bolt, 5.26 LTS versus CalVer releases, Community versus Enterprise, GDS algorithms), Memgraph, MemGQL, FalkorDB, ArangoDB, JanusGraph, TigerGraph GSQL, Amazon Neptune or Neptune Analytics, Apache AGE and SQL/PGQ GRAPH_TABLE on Postgres, DuckPGQ, writing Cypher or openCypher MATCH patterns and reading their PROFILE/EXPLAIN plan, GQL as ISO/IEC 39075 and how little of it is really implemented, Gremlin and TinkerPop traversals, RDF triplestores with SPARQL, OWL ontologies, Fuseki, GraphDB or Virtuoso, deciding what is a node versus a relationship, supernodes and dense relationships, anchoring a traversal on a starting index, graph partitioning and single-machine limits, or knowledge graphs built to feed an LLM.

serialexperimentslainnnn Skill

IBM i (AS/400, iSeries, System i) application engineering on Power. Use when working with RPG sources (.rpgle, .sqlrpgle, RPG III/RPGLE, **FREE fully free-form, /COPY and /INCLUDE prototypes), CL programs (.clle, CRTBNDCL, CL commands like WRKACTJOB, WRKSPLF, DSPFFD), DDS physical and logical files and display files (.pf, .lf, .dspf, .prtf), ILE modules, service programs, binding directories and activation groups (CRTRPGMOD, CRTSRVPGM, CRTPGM, ACTGRP), IFS and QSYS.LIB objects, library lists and *LIBL, Db2 for i with embedded SQL, SQL stored procedures, Run SQL Scripts, ACS, and IBM i Services SQL views (QSYS2, SYSTOOLS), record-level access opcodes (CHAIN, SETLL, READE, WRITE, UPDATE), journaling and commitment control, extracting business rules from RPG/CL/DDS for a characterization or modernization gate (DSPPGMREF, DSPDBR, QSYS2.PROGRAM_INFO, BOUND_MODULE_INFO, exit points via WRKREGINF or QSYS2.EXIT_POINT_INFO, Query/400 *QRYDFN, DDS validity-checking keywords, ADDPFTRG/ADDPFCST triggers and constraints),

serialexperimentslainnnn Skill

The Lisp family except Clojure - Common Lisp and Scheme. Use when working with .lisp, .lsp, .cl, .asd, .scm, .ss, .sls, .sld, .rkt or .el files, ASDF defsystem forms, Quicklisp (ql:quickload, quicklisp.lisp, dists, qlfile/qlfile.lock with Qlot, ocicl and ocicl.csv), SBCL, Clozure CL, ECL, ABCL, CLASP, CLISP, CMUCL, LispWorks or Allegro CL images, save-lisp-and-die and dumped Lisp images, SLIME or Sly and swank/slynk REPL sessions, defmacro and macroexpand-1, CLOS defclass/defgeneric/defmethod and the MOP, the condition system (handler-bind, handler-case, restart-case, invoke-restart, signal, cerror), declaim/declare optimize speed safety, fiveam/parachute/rove test systems, Racket raco and

serialexperimentslainnnn Skill

Use when operating Oracle Database — sqlplus, RMAN, dgmgrl and Data Guard, srvctl/crsctl/asmcmd and ASM disk groups, lsnrctl with listener.ora/tnsnames.ora/sqlnet.ora, CDB/PDB multitenant and MAX_PDBS, Real Application Clusters, AWR/ASH/ADDM and awrrpt.sql, v$session/v$active_session_history wait events, SQL plan baselines and DBMS_SPM, DBMS_STATS, Flashback Database, unified auditing, TDE wallets and Advanced Security, DBA_FEATURE_USAGE_STATISTICS and CONTROL_MANAGEMENT_PACK_ACCESS as audit exposure, processor core factor and Named User Plus metrics, Standard Edition 2 socket and thread caps, Oracle AI Database 26ai / 23ai / 19c upgrades and Release Updates, quarterly Critical Patch Updates, or ora2pg / orafce / oracle_fdw migration off Oracle to PostgreSQL.

serialexperimentslainnnn Skill

PL/SQL as a program language and Oracle Forms/Reports as a legacy application layer - two things with different futures. Use when writing or reviewing .pks/.pkb/.plb sources, CREATE OR REPLACE PACKAGE / PACKAGE BODY / PROCEDURE / FUNCTION / TRIGGER, anonymous PL/SQL blocks, %TYPE and %ROWTYPE declarations, ref cursors and cursor FOR loops, BULK COLLECT and FORALL with SAVE EXCEPTIONS and LIMIT, EXECUTE IMMEDIATE and DBMS_SQL dynamic SQL, DBMS_ASSERT input validation, bind variables versus literal concatenation, WHEN OTHERS exception handlers, RAISE_APPLICATION_ERROR, PRAGMA AUTONOMOUS_TRANSACTION, AUTHID DEFINER versus CURRENT_USER, package state and ORA-04068, invalid objects and recompilation, DBMS_PROFILER / DBMS_HPROF / PL/Scope, utPLSQL test suites, SQL Developer and SQLcl, and when working with Oracle Forms .fmb/.fmx/.pll/.olb/.mmb modules, Forms Builder, frmcmp and frmweb, WebUtil, Oracle Reports .rdf/.rep, Forms and Reports 12c or 14c, or planning a Forms-to-APEX / Forms-to-Java migration with ORDS.

skotalexsander Bundle

Aplica o método do System Design Primer a um projeto REAL, na escala verdadeira dele: levanta casos de uso, o que fica fora e as suposições; estima carga com contas à vista (usuários → requisições/s → armazenamento → banda); desenha em alto nível; detalha fluxos, dados e API; e só então decide banco, cache, fila, consistência e ponto único de falha, cada decisão com critério, trade-off e o que faria mudar. Entrega um documento de design. Use quando disser 'como eu estruturo esse sistema', 'qual arquitetura', 'isso aguenta X usuários?', 'preciso de fila/cache/Redis?', 'SQL ou NoSQL', 'vou pôr no ar, o que pode cair?', 'um servidor dá conta?', 'desenha a arquitetura do app', ou antes de começar backend, API, realtime, bot com servidor ou app com banco. NÃO use para layout de tela e UX (front_god, ux-audit), para decisão já tomada que só precisa ser registrada (documentation-and-adrs) nem para schema de tabela isolado (database-schema-designer).

skotalexsander Bundle

Acha e conserta custo algorítmico ruim em código REAL — laço dentro de laço, includes/indexOf/find/filter dentro de laço, shift() ou pop(0) em fila, cópia de array a cada iteração, ordenação repetida, recursão que recalcula, uma consulta ao banco por item (N+1), estrutura de dados errada — MEDINDO antes e depois com tamanhos crescentes e provando que o resultado não mudou. Também treina resolução de problemas de algoritmo com o método de 6 passos e dica graduada, sem entregar a resposta pronta. Use quando disser 'isso tá lento', 'trava com muitos itens', 'demora quando a lista cresce', 'otimiza esse loop', 'qual a complexidade disso', 'Big-O', 'Map ou objeto', 'Set ou array', 'qual estrutura de dados usar', 'quero treinar algoritmo', 'exercício de lógica', 'leetcode'. NÃO use para renderização lenta, rede ou Core Web Vitals (performance-optimization), animação travando (optimize-web-animations) nem consulta SQL lenta por falta de índice (sql-database-assistant).

serialexperimentslainnnn Skill

Use when data reaches a human for a decision — deciding whether a dashboard changes any decision at all and retiring dead ones, choosing or operating a BI tool (Power BI and Fabric F-SKU capacity versus Pro/PPU per-user licensing, Tableau Creator/Explorer/Viewer seats, Looker platform fee and LookML, Metabase, Apache Superset, Lightdash, Evidence, Preset), .pbix/.pbip/.twb/.twbx/.lkml/model.lkml/explore.lkml files, dashboard and report design driven by audience and decision, self-service tiers and certified versus exploratory content, extracts and imports versus direct/live query, pre-aggregates, caching and refresh schedules as a cost pattern, report certification, per-report ownership and periodic pruning, row-level and column-level security and whether to enforce it in the warehouse or in the tool, spreadsheet export as a governance leak, scheduled report delivery, data alerts, embedded analytics, and showing data freshness or staleness inside the report itself.

serialexperimentslainnnn Skill

Use when changes must be captured from a database or processed in motion — deciding whether streaming is warranted at all versus an incremental batch every 15 minutes, capturing from the transaction log (PostgreSQL pgoutput/wal2json logical decoding and replication slots, MySQL/MariaDB binlog and GTID, Oracle LogMiner, SQL Server CDC, MongoDB change streams) versus triggers or timestamp polling, running Debezium (Debezium Server, Debezium Engine, Kafka Connect connectors, signals, tombstone records, snapshot.mode and incremental snapshots) or Flink CDC, initial snapshot cost and resume after a crash, an inactive slot retaining WAL until pg_wal fills the disk (max_slot_wal_keep_size, idle_replication_slot_timeout, safe_wal_size, wal_status), why table-change events are not domain events and must not become a public contract, at-least-once versus at-most-once versus exactly-once and consumer idempotency, ordering guaranteed only per partition and choosing the partition key, schema evolution when the source adds

serialexperimentslainnnn Skill

IBM Z mainframe engineering and the COBOL application estate on z/OS. Use when working with .cbl/.cob/.cpy COBOL sources and copybooks, JCL jobs (//STEP EXEC PGM=, SYSIN DD, IEBGENER, IDCAMS, SORT/DFSORT), CICS command-level EXEC CICS programs and BMS maps, IMS DB/TM and PSB/DBD, Db2 for z/OS with EXEC SQL and DCLGEN and BIND PACKAGE/PLAN, VSAM KSDS/ESDS/RRDS clusters, QSAM datasets and PDS/PDSE members, IBM MQ for z/OS, TSO/ISPF, SDSF, RACF ACF2 or Top Secret profiles, SMF records, WLM service classes, MSU MIPS and rolling four-hour average capacity billing, Tailored Fit Pricing and sub-capacity SCRT reporting, Enterprise COBOL for z/OS or GnuCOBOL compilation, EBCDIC to ASCII conversion, COMP-3 packed decimal and REDEFINES layouts, Rocket Git for z/OS and IBM Dependency Based Build with zAppBuild, Zowe and z/OSMF, z/OS Connect REST APIs over CICS, Wazi and zD&T emulation, or deciding whether to rehost, recompile, auto-translate or rewrite a COBOL application off the mainframe.

serialexperimentslainnnn Skill

Security detection engineering — building and governing SIEM detections as code. Use when writing or tuning Sigma rules (sigma-cli, pySigma, sigma correlations), YARA or YARA-X rules, Elastic detection-rules TOML, KQL, SPL, EQL or YARA-L analytics, Suricata and Zeek signatures, Wazuh decoders and rules, ATT&CK Navigator coverage layers, DeTT&CT, Chainsaw or Hayabusa triage, alert runbooks and false-positive rates, detection unit tests in CI, OCSF or ECS log normalization, or onboarding a new log source into a SIEM.

boxlogodev Bundle

This skill handles all SAP IBP (Integrated Business Planning) tasks including Demand Sensing, S&OP, Supply Planning, Inventory Planning, Response & Supply, Control Tower, Excel UI integration, planning algorithms, time series forecasting, master data integration with S/4HANA, BTP environment provisioning, ATP (Available-to-Promise) checks, multi-level planning, snapshots, version management, key figures, planning levels, planning operators, and SAP IBP Excel UI. Use this skill whenever the user mentions IBP, demand planning, supply planning, S&OP, sales and operations planning, demand sensing, inventory optimization, statistical forecasting, planning area, planning level, key figure, time-series, IBP Excel, BTP planning, response planning, ATP, or any IBP module question.

yuyuliuliu Bundle

Use when processing user-provided spreadsheets that originated from handwritten/paper logs, screenshot OCR, or external imports—especially those with ambiguous dimension labels like color/date/category/status. This skill guards against misreading label literals as real business semantics by verifying true meaning, adding anti-misread annotations (cell comments + header note + header renaming), running numeric sanity sweeps, and handling Excel file locks.

akayashuu Bundle

Use when integrating Takt analytics into a web app, or authoring/maintaining a @vskstudio/takt-* wrapper — covers init/pageview/track, the excludeLocalhost gotcha, SPA pageviews, sendBeacon transport, and per-framework idioms.

serialexperimentslainnnn Skill

Use when deciding the shape of an analytical schema — star schema versus 3NF versus Data Vault (hubs, links, satellites, PIT and bridge tables), bronze/silver/gold or staging/intermediate/marts layering, declaring the grain of a fact table, additive versus semi-additive versus non-additive measures, factless facts, periodic and accumulating snapshots, surrogate versus natural keys, slowly changing dimensions (SCD type 0-7), conformed dimensions across marts, degenerate and junk dimensions, a date/calendar dimension with fiscal periods and business timezone versus UTC, One Big Table denormalization for a serving layer, the single definition of a metric and the semantic layer (MetricFlow, Cube, Apache Ossie/OSI semantic models), proving uniqueness and referential integrity on a model, or migrating a schema whose grain must change.

johnnylin2121 Bundle

亚马逊广告分析与经营分析工作流——基于CSV/Excel数据进行广告表现和产品表现的深度分析，找出问题并给出数据驱动的整改方案。Use when user uploads Amazon advertising data files (CSV/Excel), asks for "亚马逊分析", "广告分析", "ACOS优化", "产品表现分析", "经营分析", "广告数据分析", "广告报告", "帮我分析一下广告数据", or mentions Amazon ACoS/ROAS/CPC/CVR metrics. Covers full-store summary analysis, ASIN deep-dive, competitor comparison, action recommendations with expected goals, and operation tracking.

jameswh3 Skill

Build rich, company-specific and persona-specific Microsoft Copilot Cowork exercises for customer enablement: agentic workspace scenarios, robust multi-step anchor prompts, drop-in synthetic content packs, and executive handouts. Use when the user asks to "create a Cowork exercise", "build a Copilot Cowork demo", "make a Cowork workshop track", "build Cowork exercises for a CFO / plant manager / claims lead", "design a scheduled autonomous briefing demo", "build a Cowork exercise set for [company]", or "create Cowork exercises by persona". Do NOT use for non-Cowork Copilot surfaces (Chat, Researcher, Analyst, Notebook, Agent Builder, Outlook, Teams, Excel, Word, PowerPoint) - use copilot-se-demo-builder; do NOT use to perform the real work a scenario depicts.

vaibtan Bundle

Reconstruct why code or a product decision exists from source history, issues, documents, conversations, observability, and analytics. Use for $why, design rationale, regressions, postmortems, or data-backed thresholds. Use $how for execution behavior.