Data & Analytics

1398281322-a11y Skill

Use when writing or reviewing APIs that touch authz, 越权, SQL injection, third-party callback signatures, 核销 merchant ownership, or sensitive fields. Use on almost every write API; skip only for internal read prototypes with no user input.

1398281322-a11y Skill

Use when diagnosing slow SQL, creating or changing secondary indexes, EXPLAIN, 最左前缀, covering index, or implicit conversion. Do not use for sharding or table status-machine design.

1398281322-a11y Skill

Use when defining API 接口规范, REST methods, HTTP status, 错误码, 版本, pagination, 金额单位分, 时区, Idempotency-Key, or request_id. Do not use for HMAC/replay (backend-api-security) or SQL 越权 (backend-safe-check).

1398281322-a11y Skill

Use when deciding 下单扣库存 vs 支付扣库存 vs 预占/锁定库存, 可售库存, 锁定库存, occupy TTL. Do not replace the SQL condition stock>=n (backend-concurrency-sell). Do not use for 秒杀分层 (backend-seckill).

1398281322-a11y Skill

Use when cluster login state, 分布式 Session, JWT, SSO, Redis session, sticky sessions, or gateway auth is in play. Do not use for SQL 越权 resource checks (backend-safe-check).

anthonyalcaraz Bundle

Budget a specialist model fleet against the two production bottlenecks: KV-cache-bound concurrency and end-to-end latency. Computes how many concurrent users a GPU can host (peak KV per active user, not model size, is the binding constraint), proves that quantizing weights does not move that ceiling while KV compression (MEMENTO) does, estimates GPU speedups for graph analytics (cuGraph / nx-cugraph), and checks a multi-node workflow against the book's latency budget and the sub-2s target. Use when scaling a multi-model agent to real-time latency. NOT for model selection (that is model-routing-selector), NOT for cost/quality scoring (that is cost-performance-scorer), NOT for defining GPU terms (that is gpu-glossary-anchor).

ardurai Bundle

God-level backend engineering: Node.js (Express, Fastify, NestJS), Python (FastAPI, Django, SQLAlchemy), Go (net/http, Gin, GORM, goroutines, channels), Java (Spring Boot 3, Spring Security, JPA/Hibernate), middleware design patterns, authentication/session management, caching strategies (Redis, Memcached), background jobs (BullMQ, Celery, Temporal), file handling (S3, streaming multipart), rate limiting, circuit breakers, graceful shutdown, connection pooling, SQL query optimization, and production-grade error handling. Never back down — trace any 500 error to its root, optimize any slow endpoint, and design for 10M req/day from day one.

ardurai Bundle

God-level database mastery covering SQL (PostgreSQL deep dive, MySQL differences), NoSQL (MongoDB, Cassandra, DynamoDB), NewSQL (CockroachDB, Spanner), caching (Redis deep dive — data structures, persistence, clustering, pub/sub), message streaming (Apache Kafka — architecture, partitioning, consumer groups, exactly-once semantics), Elasticsearch/OpenSearch (indexing, mapping, search relevance, aggregations), time-series (InfluxDB, TimescaleDB), graph databases (Neo4j), schema design, query optimization, indexing strategies, ACID vs BASE, CAP theorem, replication, sharding, and connection pooling. A developer who does not understand their database is a developer who will eventually bring it to its knees.

reagin Bundle

Implement or review Go relational-database code using database/sql, pgx, sqlx, or an existing data layer. Use for query safety, scanning and nullability, transactions, pools, migrations, performance, and database tests while preserving the project's selected datastore and library.

ryanduguid Bundle

Use when pulling, specifying, or validating the source exports the contracting pack runs on: job or tracking-dimension P&L, contract and claim registers, plant registers and hire dockets, payroll by employee and by job, and subcontractor payment listings, including file conventions, completeness checks and CSV parsing traps. Reference skill for the other skills in this pack.

incidentfox Bundle

Google BigQuery data warehouse queries and schema inspection. Use when running SQL queries, listing datasets/tables, or inspecting table schemas in BigQuery.

incidentfox Bundle

Snowflake data warehouse queries and schema inspection. Use when running SQL queries against Snowflake, listing tables, or inspecting schemas.

incidentfox Bundle

Amplitude product analytics. Use when querying user events, funnels, retention, or product usage data. Provides event segmentation, user activity lookup, and annotation queries.

incidentfox Bundle

Incident.io incident management and analytics. Use for listing, searching, and analyzing incidents. Supports MTTR calculations, severity analysis, and alert fatigue detection via alert route analytics.

ersinkoc Skill

SQL Injection detection across all variants — classic, blind, time-based, second-order, and UNION-based

rweisssieker-xp Skill

TOPdesk Asset Management design, schema, analytics, and workflow support. Use for asset templates, dynamic asset fields, asset relations, owner/branch/location mapping, lifecycle, incident/change links, CMDB-like reporting, asset data quality, and asset KPIs.

rweisssieker-xp Skill

Expert guidance for TOPdesk helpdesk/service-management functionality, the database schema of a custom Topdesk app, Power BI reporting/analytics, and AI/KI features for TOPdesk data and workflows. Use when answering questions about TOPdesk modules, incidents, changes, assets, knowledge base, self-service portal, operators/persons, API behavior, integrations, reporting, OData/database tables, entity relationships, migrations, Power BI dashboards, semantic models, DAX, Power Query, KPI definitions, AI-assisted ticket classification, routing, summaries, response suggestions, knowledge article generation, semantic search, predictive insights, or when designing, querying, documenting, or validating the Topdesk app schema.

rweisssieker-xp Skill

Advanced Python automation for TOPdesk data, APIs, OData, reporting, migration, testing, and delivery tooling. Use for writing, reviewing, hardening, testing, or packaging Python scripts that parse TOPdesk OData metadata, profile CSV/Excel exports, call TOPdesk REST APIs, generate field catalogs, create data-quality findings, build Power BI/reporting artifacts, run migration checks, or provide CLI utilities.

rweisssieker-xp Skill

Advanced PowerShell automation for TOPdesk delivery and operations. Use for writing, reviewing, hardening, testing, or packaging PowerShell scripts that work with TOPdesk APIs, OData exports, CSV/JSON artifacts, tenant mapping, Power BI refresh operations, migration batches, runbooks, Windows scheduled tasks, CI scripts, validation gates, and safe local automation.

rweisssieker-xp Skill

Translate TOPdesk business questions into tenant-safe OData filters, SQL/reporting-view queries, Power Query extraction plans, DAX measure definitions, validation checks, and Power BI report requirements. Use when combining TOPdesk queries with Power BI modelling, KPI semantics, reconciliation, data-quality checks, or report implementation tasks.

rweisssieker-xp Bundle

Tenant-specific TOPdesk field and model mapping. Use for OData metadata, API samples, CSV exports, UI labels, category/status/priority exports, entity inventories, field catalogs, local schema mapping, Power BI fact/dimension mapping, RLS/security mapping, and tenant-specific data-quality gaps.

rweisssieker-xp Bundle

Generate decision-ready TOPdesk findings from analysis CSV files, SLA findings, data-quality findings, process-debt outputs, AI governance rows, or manual finding drafts using a standard evidence, impact, risk, action, owner, and validation metric format.

wonderslife Bundle

MySQL数据库专家提供SQL优化、索引设计和表结构分析服务。当用户需要SQL优化或数据库设计时调用此技能。支持中文触发：SQL优化、数据库设计、索引优化、慢查询分析。

wonderslife Bundle

性能优化专家，提供瓶颈识别、SQL调优、缓存策略设计、压测指导。触发：性能优化、瓶颈定位、JVM调优、压测、慢接口优化、performance optimization。

deagentic Bundle

Use when data models, queries, migrations, schema design, ORM usage, indexing, or storage architecture decisions need review. Invoke for any SQL, NoSQL, time-series, or search database work.

penghang1223 Bundle

DuckDB数据分析工具集 — 内存管理/ClickBench基准/结果导出。$700 MacBook也能跑大数据。

thinkingaiagenticengine Bundle

Inspect Trino metadata, table schemas, query plans, EXPLAIN ANALYZE output, and existing query records through the mcp-trino MCP tools. Use when Codex needs to navigate Trino catalogs or schemas, inspect a table before writing or reviewing SQL, analyze a query plan, diagnose a Trino query ID from query-info, or explain the inspection-only limits and query visibility behavior of mcp-trino.

thinkingaiagenticengine Bundle

Predict internet product user lifetime value (LTV) and lifecycle (LT) from retention and revenue data. Use when the user asks about LTV, user lifetime value, LT, user lifecycle, lifecycle forecast, payback period, retention fitting, retention decay, retention curve, channel quality assessment, per-user or per-cohort value estimation, cohort revenue projection, active days forecast, LTV segmentation — for games, tools, social, e-commerce, or any internet product. Supports both directly provided data and automated ae-cli data retrieval from a TE project, including RFM / pay-tier / VIP stratified LTV. For macro calendar-time total-revenue forecasting and acquisition-budget / DNU-ARPU target-solving, use revenue-forecast-model-cli.

thinkingaiagenticengine Bundle

Write Trino SQL statements based on requirements and system data specifications. Triggered only under the following conditions >> 1. When users need SQL code, such as "help me write a SQL", "generate SQL statement", "how to write this SQL", "give me a query statement". 2. When users need to query a list of players meeting certain conditions or query a player's behavior list, used to generate SQL and then initiate query requests through `ae-cli analysis adhoc run` with `--model-type sql`. 3. If the data users need can be obtained through ae-analysis (such as dashboards, reports), prioritize using the ae-analysis skill to complete the full query execution process, do not use this skill

thinkingaiagenticengine Bundle

Recommend the most suitable AE (AgenticEngine) analysis model from 12 models and generate its configuration. Use when users are unsure which analysis model to choose, ask "which model to use / which one should I choose", ask whether a model fits a scenario (e.g. "can retention analysis do this"), ask which model to use for LTV / ROI / revenue, or want configuration guidance for a chosen model — with precise field mapping when a project is available, or a generic-example configuration for consultation when no project is provided. Do not use for simple data queries, executing a specific investigation, writing SQL/code, or configuring a model whose name is already known (route those to ae-analysis).

thinkingaiagenticengine Bundle

Analyze puzzle IAA game post-launch version data covering retention, levels, monetization, segmentation, and churn. Trigger when reviewing casual/puzzle game retention, level experience, ad placements, user segmentation, or churn attribution. Not for ad-hoc single-metric queries or non-game analytics.

thinkingaiagenticengine Bundle

Identifies slow SQL queries, unreasonable indexes, and inefficient writing patterns, providing actionable rewrite solutions and tuning suggestions based on execution plans and database optimization rules. Special support for Trino SQL optimization, including partition field usage and field naming conventions. Use when users need to optimize slow SQL queries, identify inefficient writing patterns, or get tuning suggestions based on execution plans.

thinkingaiagenticengine Bundle

Diagnoses APP performance issues by automatically matching core performance analysis fields from TE system tables, covering device compatibility, frame rate & lag, page loading, and crash & exceptions analysis, with field matching confirmation, professional report output, and compliant SQL generation. Use when users need to diagnose APP performance issues such as device compatibility problems, frame rate drops or lag, slow page loading, or crash and exception analysis.

thinkingaiagenticengine Bundle

Aligns and explains analytical scope for dashboards, reports, queries, SQL, tags, cohorts, virtual attributes, dimension-table attributes, and related analysis objects. Use when users ask about the scope, definition, or coverage of any of these analysis objects.

thinkingaiagenticengine Bundle

Trigger when a Feishu spreadsheet defines account-to-platform data permissions that must be compared with, added to, or synchronized into one explicitly selected AE/TE project. Resolve accounts and existing access, build a deterministic change plan, preserve project roles, require approval before permission mutations, and verify every result. Do not use for organization-wide access, unspecified projects, arbitrary role changes, or sheets without an unambiguous account and permission mapping.

wecode-ai Bundle

飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、评论/权限/订阅、标题、版本和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token 也按资源路径和 token 路由，不回退 WebFetch。不负责：文档内容编辑（走 lark-doc）、表格/Base 表内数据操作（走 lark-sheets/lark-base）、知识空间节点/成员管理（走 lark-wiki）、原生 Markdown 文件读写/patch/diff（走 lark-markdown）。