Data & Analytics

davidcastagnetoa Bundle

Web Application Firewall para detectar y bloquear ataques SQL injection, XSS y otros OWASP Top 10

ascend-ai-coding Bundle

面向 Ascend PyTorch Profiler / msprof DB（如 ascend_pytorch_profiler*.db、msprof_*.db）的 SQL 分析技能。将自然语言问题（算子耗时、通信、下发、调度、schema/table 查询）转为安全可执行 SQL，并按需从官方文档提取表结构详情。

ascend-ai-coding Skill

ATB CSV 测试用例生成技能。当用户需要为 ATB 算子创建 CSV 格式的泛化测试用例时调用此技能。 覆盖：正例设计、反例设计、性能测试用例、CSV 格式规范。

ascend-ai-coding Bundle

读取昇腾社区论坛（Hiascend Community Forum）的帖子内容，支持按时间范围筛选并导出为Excel。支持时间快捷选项（今年、本月、本周、今天）和自定义区间，自动剔除置顶贴（top>0），智能终止查询，时区自动转换（+8小时），并发分页获取提升效率，并将topicId转换为可点击的论坛链接。当用户需要获取昇腾论坛帖子、筛选特定时间范围的论坛内容、导出论坛数据到Excel时触发使用。

ascend-ai-coding Bundle

在 ascend-kernel 的 csrc/ops/<op>/test 下维护仅含 JSONL 的 profiler 性能用例，使用 torch_npu.profiler（固定 warmup=5、active=5）采集，汇总 ASCEND_PROFILER_OUTPUT/op_statistic.csv 的 Total Time(us)，输出含 DType 列的统一 Markdown 对比报告（自定义算子 vs 标杆）。不生成 perf_cases.json 与 *_profiler_results.json。参考实现见 examples/layer_norm_profiler_reference/。

ascend-ai-coding Bundle

昇腾社区论坛问题分析工具，读取Excel格式的论坛帖子数据，自动筛选问题、故障、报错类帖子，获取帖子详细内容，并根据关键词进行多维度筛选分析，最终导出结构化的问题数据Excel报告。用于分析昇腾论坛中的技术问题、故障排查和报错处理相关帖子。

ascend-ai-coding Bundle

ATB OPS→ACLNN 迁移标准化工作流主模板。整合前置学习、设计文档生成、CSV用例设计、 实际迁移、编译验证、测试验证全流程，提供明确的阶段 Gates 和用户确认机制。

ferroxlabs Skill

Applies cohort analysis to a described dataset by defining the cohort grouping variable, time horizon, measured behavior, and producing the cohort table structure with retention calculation formulas. Outputs a populated cohort matrix, not a description of cohort analysis theory. Use when the user asks to analyze retention, track user behavior over time by signup date, compare customer groups by acquisition period, or measure how engagement changes as users age. Do NOT use for funnel conversion analysis (use funnel-analysis), customer segmentation by attributes (use segmentation-design), or A/B test design comparing two groups (use ab-test-design).

ferroxlabs Skill

Produces a funnel analysis with defined conversion stages, step-by-step conversion rates, biggest drop-off identification, and diagnostic questions for each stage. Outputs a populated funnel table with actionable insights, not a description of funnel methodology. Use when the user asks to analyze conversion rates, identify where users drop off in a process, optimize a signup or purchase flow, or measure step-by-step completion rates. Do NOT use for cohort-based retention over time (use cohort-analysis), customer segmentation by attributes (use segmentation-design), or KPI definition (use kpi-definition).

ferroxlabs Skill

Past the fake-door stage. Demand signal exists. The question now: does the actual product produce the outcome customers expected. Load when someone says "people signed up — what do we ship to the first cohort," or "we need to know if this works before we scale."

ferroxlabs Skill

E-commerce strategy covering platform selection, product listing optimization, conversion rate optimization, cart abandonment strategies, payment processing, shipping, inventory management, customer retention, and analytics KPIs. Use when the user asks about ecommerce advisor or needs help with related topics. Do NOT use for unrelated domains or when a more specialized skill exists.

ferroxlabs Skill

Designs a customer or user segmentation by selecting variables, defining the segmentation method (RFM, behavioral, demographic, needs-based), producing segment definitions with names, and specifying the analysis output format. Use when the user asks to segment customers, create audience groups, build user personas from data, define target segments, or cluster users by behavior or attributes. Do NOT use for cohort analysis by time period (use cohort-analysis), funnel conversion between steps (use funnel-analysis), or individual KPI definition (use kpi-definition).

ferroxlabs Skill

Search infrastructure design expert covering full-text search architecture, Elasticsearch/OpenSearch cluster design, relevance tuning (BM25, TF-IDF, custom scoring), faceted search, autocomplete, query understanding, search analytics, and search quality measurement. Use when the user asks about search system architect, search system architect best practices, or needs guidance on search system architect implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

ferroxlabs Skill

As of: 2026-05-16

aws-samples Bundle

Use this skill to investigate and troubleshoot Amazon Managed Service for Apache Flink (formerly Kinesis Data Analytics) problems by analyzing application creation, startup, Flink job failures, checkpointing, source/sink connectors, scaling, parallelism, state management, watermarks, VPC connectivity, IAM permissions, Studio notebooks, and following structured runbooks. Activate when: application creation failures, start errors, Flink job failures, checkpoint issues, connector errors, scaling problems, state management issues, watermark problems, VPC connectivity failures, IAM errors, Studio notebook issues, or the user says something is wrong with Managed Flink or Kinesis Data Analytics.

aws-samples Bundle

Use this skill to investigate and troubleshoot Amazon RDS for SQL Server problems by analyzing instance configurations, performance metrics, connectivity, parameter groups, and following structured runbooks. Activate when: launch failures, instance class issues, storage problems, high CPU or SQL Server wait statistics, memory pressure, I/O bottlenecks, tempdb contention, connection failures, Windows Authentication/Kerberos issues, SSL/TLS problems, parameter group issues, SQL Server configuration, max memory/workers tuning, native backup to S3, snapshot restore, point-in-time recovery, read replica issues, Multi-AZ failover, native backup restore migration, DMS issues, collation problems, TDE encryption, SQL Server audit, login/user issues, version upgrades, patching, or the user says something is wrong with RDS SQL Server without naming specific symptoms.

aws-samples Bundle

Use this skill to investigate and troubleshoot Amazon Connect Contact Lens and Wisdom problems by analyzing real-time analytics, sentiment analysis, transcription, category rules, custom vocabulary, knowledge bases, search, evaluation forms, screen recording, data lake export, S3 output, third-party integrations, and following structured runbooks. Activate when: Contact Lens enablement issues, real-time analytics errors, sentiment analysis problems, transcript failures, category rule errors, custom vocabulary issues, Wisdom knowledge base problems, search failures, evaluation form issues, screen recording errors, data export problems, or the user says something is wrong with Contact Lens or Wisdom.

builderio Bundle

Turn visible project context, a proven thread, skill, or workflow into a runnable Agent-Native app with simple buttons, visible agent steps, preview, and deployment handoff. Use when a user invokes `/turn-into-app` or asks to make a workflow into an app, including from Claude or ChatGPT on the web, including when the source is a spreadsheet link or upload.

builderio Skill

Server-side analytics tracking with pluggable providers. Use when adding analytics events, registering custom tracking providers, or configuring built-in providers (PostHog, Mixpanel, Amplitude, Webhook).

builderio Skill

How to keep template code PostgreSQL-specific and hosting-agnostic. Use when defining schemas, writing raw SQL, or creating server routes.

builderio Skill

How to store application data in agent-native apps. All data lives in SQL. Use when adding data models, deciding where to store data, or reading/writing application data.

builderio Skill

Search Gong call metadata and transcript excerpts for sales-call analysis, customer conversations, objections, risks, and next steps.

builderio Skill

dbt (data build tool) project structure, SQL patterns, and best practices for the analytics warehouse. Use this skill when working with dbt models, testing SQL queries, or creating new analytical tables.

builderio Skill

Search and analyze Jira tickets, sprints, and project analytics. Use this skill when the user asks about tickets, bugs, sprint tracking, or engineering work.

builderio Skill

Extract key learnings from the current chat thread and save them to docs/learnings.md. Use this skill when the user types "/learn" or asks to save learnings from the conversation.

builderio Skill

Look up customer support tickets and account history via Pylon. Use this skill when the user asks about support tickets, customer issues, or support history.

builderio Skill

Search Slack messages and read channel history across your workspaces. Use this skill when the user asks about Slack conversations, channel messages, or internal communications.

builderio Skill

Query HubSpot CRM for deals, companies, contacts, tickets, owners, and account/deal context. Use when the user asks for HubSpot data or connection status.

builderio Skill

Enrich contacts and companies via Apollo.io for prospecting and sales intelligence. Use this skill when the user asks about contact details, company research, or finding decision-makers.

builderio Skill

Generate inline chart images (PNG) for embedding in chat responses. Use this skill when you need to create bar, line, or area charts for data visualization in chat.

builderio Skill

Search and read GitHub PRs, issues, and code across a configured GitHub org or repo. Use this skill when the user asks about pull requests, code reviews, or GitHub issues.

builderio Skill

Access the Notion content calendar and page data for editorial planning. Use this skill when the user asks about the content calendar, blog planning, or editorial schedule.

modu-ai Bundle

나에게 맞는 정부·공공기관 지원사업을 찾아주고, 심사 기준에 맞춘 사업계획서·신청서 초안을 만들어 드립니다(Word·한글·Excel 파일까지). 창업자·소상공인·중소기업·연구자·비영리단체·개인 누구나 쓸 수 있습니다. 다음과 같은 요청 시 사용하세요: - "정부 지원사업 찾아줘" - "우리 상황에 맞는 지원금 있어?" - "사업계획서 초안 써줘" - "지원서 작성 도와줘" - "이 신청서 심사 기준으로 검토해줘" - "마감 전에 뭐 준비해야 해?" - "예비창업패키지 신청서 만들어줘" - "지원금 어떻게 쓰는지 모르겠어" 지원사업 탐색·신청서 작성·서류 검토·일정 관리까지 도와주며, 마지막에 AI 표현 다듬기로 이어집니다. [책임 경계] vs moai-tutor:education-grant-writer: 이 스킬=범용 정부 지원사업(창업·소상공인·중기·공모전), 저 스킬=학술/R&D 연구비 특화(NRF·IITP·KIAT).

modu-ai Skill

[책임 경계] 재구매 타이밍 엔진 — 구매주기 골든타임 3구간(리마인드 80% / 데드라인 110-120% / 휴면 진입 150%) + 구간별 메시지 톤 + 리드 스코어링 룰 + 리텐션 차트 cohort 분석 가이드 전담. 페어 스킬 commerce-ltv-cac-architect(고객 수익 구조)와 명확히 구분 — 본 스킬은 재구매 타이밍 트리거 전용, 페어는 LTV/CAC 전체 모델. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: "재구매 시점 알려줘", "골든타임 3구간", "리마인드 메시지 시점", "데드라인 메시지", "휴면 진입 90일", "리드 스코어링", "리텐션 차트 cohort", "정기 구매 카테고리", "화장품 재구매 60일", "면도기 30일 재구매", "구매주기 기반 CRM". 3구간 골든타임: ① 평균 주기 80% 시점 = 리마인드 (감성·정체성) ② 110-120% = 데드라인 (긴급성·할인) ③ 150% = 휴면 진입 (윈백·강한 인센티브). 화장품·식품·반려동물·렌즈·면도기 등 정기 구매 카테고리 한국 D2C 표준 적용. ai-slop-reviewer 자동 체이닝 (텍스트 메시지 산출물).

acaprino Bundle

X-ray method: mechanical structure extraction fused with semantic reading into a ground-truth account of WHAT, WHY, HOW and CONSEQUENCES. Python, Java, JavaScript, TypeScript, SQL, PL/SQL, Rust. TRIGGER WHEN: encountering an unfamiliar codebase, needing pre-review technical context, before a major refactor, or when documentation is stale or missing. DO NOT TRIGGER WHEN: the user wants human-readable narrative docs (use /codebase-mapper:map-codebase), a public-facing README, or a review verdict (senior-review consumes this output instead).

builderio Skill

Track errors and issues across your projects via Sentry. Use this skill when the user asks about errors, exceptions, error trends, or application health.