Data & Analytics

flux-point-studios Bundle

Use this skill when the user asks about Indigo Protocol stats, TVL, APR, governance, or DEX yields. Triggers on: "Indigo TVL", "Indigo stats", "iUSD APR", "Indigo governance", "Indigo polls", "DEX yields for iAssets".

flux-point-studios Bundle

Use this skill when the user asks about SaturnSwap DEX statistics, total volume, TVL, number of pools/tokens, or top pools by volume. Triggers on: "SaturnSwap stats", "total TVL", "total volume", "how many pools", "top pools by volume", "DEX analytics", "SaturnSwap overview".

prof-ramos Bundle

Audits Supabase security on authorized bug bounty and pentest targets, focusing on misconfigurations common in vibe-coded and production apps: missing/broken RLS, USING(true)/WITH CHECK(true), JWT user_metadata privilege escalation, anon write policies, SECURITY DEFINER RPCs, storage buckets, exposed service_role keys, and PostgREST surface. Guides running the bundled SQL audit scripts, interpreting red flags, validating client-side exposure, and writing severity-ranked findings with PoC steps and remediations. Use when the user runs /supabase-security, or asks to audit Supabase, check RLS, review Supabase policies, hunt Supabase misconfigs, test anon key access, or secure a Supabase backend on a bug bounty target. Requires written authorization before any active testing.

prof-ramos Bundle

Run, test, and drive the edital-verticalizado tool. Processes Brazilian public exam announcements (editais) into structured study tables. Use to verticalizar an edital, generate CSV/JSON output, or verify the driver works.

rami-maalouf Bundle

Reads the Letterly CSV export in the unprocessed folder, extracts "magic" notes, preserves Letterly tags, and converts them into Markdown notes with frontmatter.

rynhardt-potgieter Skill

Code quality and formatting standards — C# naming conventions, TypeScript strict mode, SQL formatting, git commit style, code review checklist, error handling patterns, and logging conventions. Use this skill when writing new code, reviewing code quality, establishing naming conventions, setting up linting, or ensuring consistency across the codebase. Also use when subagents need a reference for coding style.

rynhardt-potgieter Skill

DynamoDB single-table design and data-access standards — partition/sort key modelling, GSIs, a generic Repository<T> base-class access pattern, org-scoped partitioning for tenant isolation, cursor pagination, and idempotency. Use this skill when designing DynamoDB tables, writing repositories, or persisting any model to DynamoDB. Replaces the postgresql-data skill on a DynamoDB stack — there is no SQL, no EF Core, and no migrations.

benchflow-ai Bundle

SkillsBench task authoring — walk a contributor from idea to submission-ready task following CONTRIBUTING.md and the task-implementation rubric. Use when the user wants to create a new SkillsBench task, scaffold a task from an existing workflow (notebook, Excel workbook, document, dataset), convert a prompt or a benchmark item into a SkillsBench task, write skills for a task, or prepare a SkillsBench PR. Pairs with `task-review` (run that as a self-check before submitting).

databricks Bundle

Build apps on Databricks Apps platform. Use when asked to create dashboards, data apps, analytics tools, or visualizations. Invoke BEFORE starting implementation.

databricks Bundle

Develop Lakeflow Spark Declarative Pipelines (formerly Delta Live Tables) on Databricks. Use when building batch or streaming data pipelines with Python or SQL. Invoke BEFORE starting implementation.

databricks Bundle

Use Databricks built-in AI Functions (ai_classify, ai_extract, ai_summarize, ai_mask, ai_translate, ai_fix_grammar, ai_gen, ai_analyze_sentiment, ai_similarity, ai_parse_document, ai_query, ai_forecast) to add AI capabilities directly to SQL and PySpark pipelines without managing model endpoints. Also covers document parsing and building custom RAG pipelines (parse → chunk → index → query).

databricks Bundle

Unity Catalog metric views: define, create, query, and manage governed business metrics in YAML. Use when building standardized KPIs, revenue metrics, order analytics, or any reusable business metrics that need consistent definitions across teams and tools.

databricks Bundle

Create Databricks AI/BI dashboards. Must use when creating, updating, or deploying Lakeview dashboards as Databricks Dashboard have a unique json structure. CRITICAL: You MUST test ALL SQL queries via CLI BEFORE deploying. Follow guidelines strictly.

aaddrick Skill

Use when analyzing structured data exports containing multiple CSV files, reconstructing user activity timelines from metadata headers, calculating account lifespan or content creation baselines, or cross-referencing schemas across export files to identify data gaps and quality issues

hyperfx-ai Skill

Manage Instagram professional accounts via the Hyper MCP — publish photos, Reels, Stories, and carousels; moderate comments and mentions; send Direct Messages; pull account and media insights. Uses the Instagram API with Instagram Login (Business Login). Use when the user mentions Instagram posts, Reels, Stories, carousels, IG DMs, Instagram comments, mentions, profile, or analytics. For paid Instagram advertising, use `meta-ads`.

hyperfx-ai Skill

Safe workflow for reading, mapping, and writing Google Sheets without shifting columns or overwriting the wrong ranges. Use when the user wants to read, update, or append spreadsheet data, fix sheet structure, or sync data into Google Sheets.

multiplex-ai Bundle

Unified social media skill — create, adapt, distribute, and schedule content across LinkedIn, Twitter/X, Instagram, TikTok, YouTube, Threads, Bluesky, Facebook, and newsletters. Covers platform-native content creation, cross-platform distribution (never identical cross-posts), content calendars, repurposing systems, engagement strategy, and analytics. Use when the user mentions 'LinkedIn post,' 'Twitter thread,' 'social media,' 'content calendar,' 'social scheduling,' 'engagement,' 'viral content,' 'what should I post,' 'repurpose this content,' 'tweet ideas,' 'LinkedIn carousel,' 'social media strategy,' 'grow my following,' 'crosspost,' 'post everywhere,' 'distribute this,' or 'content engine.' For broader content strategy, see content-strategy.

bingx-api Bundle

Use when the user asks for BingX perpetual futures technical analysis, indicator values, candlestick pattern recognition, multi-timeframe scoring, support/resistance levels, divergence detection, or trend analysis. Depends on bingx-swap-market for K-line data and computes 78 indicators plus 62 candlestick patterns locally via pandas-ta-classic.

snaplogic Skill

Creates Robot Framework test cases for uploading files to SnapLogic SLDB. Use when the user wants to upload files (JSON, CSV, expression libraries, pipelines, JAR files, etc.), needs to know which destination path to use, or wants to see file upload test case examples.

snaplogic Skill

Guides setting up database containers for testing in the SnapLogic project. Use when the user wants to start/stop databases (Oracle, PostgreSQL, MySQL, SQL Server, DB2, Teradata, Snowflake), load test data, or troubleshoot database connections.

snaplogic Skill

Creates Robot Framework test cases for exporting database table data to CSV files. Use when the user wants to export Oracle, Snowflake, PostgreSQL, or other database data to CSV for verification or comparison purposes.

svy04 Bundle

랜딩 페이지·상세페이지·문의 폼의 전환이 안 나올 때 진단하고 고칠 때 사용한다. 사용자가 '전환율', '이 페이지 왜 전환이 안 되나', '랜딩 페이지 개선', '폼 이탈', '문의가 안 온다', '장바구니 이탈', '팝업', 'A/B 테스트'라고 말하거나 URL만 던져도 이 스킬을 쓴다. 한국 폼에만 있는 마찰(동의 체크박스·본인인증·간편로그인)과 팝업 관행을 함께 다룬다. 가입 흐름 자체는 signup-kr, 문구는 copy-kr, 측정은 analytics-kr 을 쓴다.

svy04 Bundle

앱 스토어 등록 정보를 점검하고 고칠 때 사용한다. 사용자가 'ASO', '앱스토어 최적화', '앱 제목', '앱 키워드', '스토어 등록', '원스토어', '갤럭시 스토어', '앱 심사 반려', '사전예약'이라고 말하면 이 스킬을 쓴다. 애플의 키워드 필드는 100자이고 구글 플레이에는 키워드 필드가 없으며, 한국에는 구글·애플 외의 마켓이 있고, 위치정보를 다루면 신고 의무가 붙는다. 앱 설치 광고는 global-ads-kr, 측정은 analytics-kr 을 쓴다.

fabioc-aloha Skill

Creates native Word, PowerPoint, or Excel artifacts through available Scout Co-create capabilities, using approved source material as a semantic brief rather than converting Markdown.

iwanalq 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、管理文档评论/权限、订阅评论变更、修改标题；也负责把本地 Word/Markdown/Excel/CSV/PPTX 和 Base 快照（.base）导入为飞书在线文档、电子表格、多维表格/Base 或幻灯片（docx、sheet、bitable、slides）。用户需要整理云盘目录、查看文件详情、处理评论/权限/标题/订阅，或导入本地文件时使用。"云空间"、"云盘"、"云存储"、"网盘"、"我的空间"都路由到本 skill。给出 doubao.com 云空间资源 URL/token，或提到豆包里的 file/folder/docx/sheet/bitable/wiki 资源时，也直接使用本 skill；按资源类型、URL 路径和 token 路由，不因域名不是飞书而回退到 WebFetch。

iwanalq Bundle

表格全场景处理：覆盖本地 Excel/CSV 与在线表格（含 doubao.com 的 /sheets/ 链接）的创建、读写、分析、计算、建模、文本语义处理、可视化、图表/透视表、表格美化等所有表格任务。用户上传 Excel/CSV、或给出feishu/doubao.com 表格链接（/sheets/ URL/token）作为附件时使用；用户口述数据要整理成表时使用；用户要求计算、统计、建模、预测、分类、挖掘、可视化、透视、美化、公式计算时使用。一切与 excel 相关的任务必须加载本技能。本技能不负责获取外部信息，如需补充数据须先通过其他途径获得。

mz038197 Skill

Operates the facenet-cli Click tool (fnet) for face embeddings and 1:1 or 1:N matching via facenet-pytorch, with optional JSON output for automation. Use when the user works in the facenet-cli repo, runs fnet / embedding commands, needs camera capture or CSV face databases, or mentions facenet-pytorch CLI harness.

ominou5 Skill

Sets up analytics and tracking for funnel pages. Covers GA4, Meta Pixel, Google Tag Manager, conversion tracking, and UTM parameter handling.

heymegabyte Bundle

PDF/DOCX/XLSX/PPTX generation and parsing on Cloudflare Workers. Covers CF Browser Rendering → PDF, pdf-lib Worker-native generation, docx/exceljs output, pptxgenjs slides, and RAG-ready text extraction. Use cases: donor annual reports, SaaS invoices, tax receipts, financial reports, grant applications. Source: anthropics/skills pdf/docx/pptx/xlsx patterns.

arnavpuri Skill

Data dashboard and admin panel design patterns for information-dense interfaces. Trigger: user asks to "build a dashboard", "create an admin panel", "design analytics", "make a data view", "build a settings page", "create a table view", "design a CRM", "build an internal tool", or any data-heavy interface work.

coval-ai Bundle

Turn a large dataset (an existing oversized Coval test set, an export of past conversations, or a CSV/JSON of cases) into a small, high-signal Coval test set by removing duplicates, identifying unique scenarios, and selecting a representative, failure-weighted subset — then bulk-loading it with no row cap. Use when the user says "I have thousands of cases", "dedupe my test set", "my test set is too big", "turn this dataset into a test set", "pick representative scenarios", or "my CSV import only kept 10 / uploaded everything".

datus-ai Skill

Guided workflow for SQL data analysis using db_tools

datus-ai Skill

Build the project's vector-indexed knowledge base from files plus database metadata — optionally scoped to specific files / tables / datasources / domains. Scan the in-scope material, classify it into business domains, explore each domain's tables and docs in parallel with explore subagents (the validated-query SQL corpus is enumerated directly, no explore needed), then (after the user confirms a generation manifest — or directly, in the same turn, when the user has waived confirmation) route every artifact to its store via storage-classify, generating semantic_models / metrics / reference_sql (and mining any extra knowledge), and refresh AGENTS.md's KB index. The lightweight /init handles the AGENTS.md inventory plus file-based knowledge/memory; this skill owns the heavy vector-store generation.

datus-ai Skill

Create database tables from SQL (CTAS) or natural language descriptions

datus-ai Bundle

Generate formatted data reports from SQL query results

datus-ai Skill

SQL query optimization techniques and best practices