Data & Analytics

ihkreddy Skill

Data analysis workflows and patterns for exploring, transforming, and visualizing data. Use when working with data, creating reports, or when users mention "data analysis", "analyze data", "data exploration", or "reporting".

senior-sigan Bundle

Comprehensive database design tool creating complete schemas with tables, fields, indexes, and ER diagrams. Use when users request database design for any system. Generates Markdown docs, SQL scripts, and DrawDB-compatible JSON/DBML files. Supports MySQL, PostgreSQL, SQL Server. Triggers: database design, schema, ER diagram, SQL, data model.

barefootford Skill

Help a user handle a one-off production related task that doesn't match perfectly to an existing skill. Examples, pull a clip's audio, extract a frame, transcribe a stray recording, draft notes, create a spreadsheet, convert a file from one type to another, etc. Use when the request doesn't map to other more obvious skills.

block Skill

Use when editing `server/sqlc/queries/**/*.sql`, `server/sqlc.yaml`, or creating a new `server/migrations/*.sql` file. sqlc query and schema source changes require running `just gen` so `server/generated/sqlc/` stays in sync. Edits to *existing* migration files are owned by the `migration-immutability` skill instead.

block Skill

Use when modifying an existing `server/migrations/*.sql` file already on `main`. Deployed migrations are immutable — `golang-migrate` skips already-applied versions, so editing one in place silently desyncs schemas across environments. Corrective changes must go in a new migration.

blogic-cz Skill

LOAD THIS SKILL when: running SQL queries, inspecting database schema, listing tables or columns, or working with database environments. Contains all db-tool commands.

alexeykrol Skill

Миграция схемы базы данных: SQLite → PostgreSQL/Supabase. Генерация SQL, проверка совместимости.

pskoett Skill

Analytics synthesis with visualizations from engineering and product data sources

marazii Bundle

End-to-end quantitative data work — cleaning, exploration, statistical testing, modeling, visualization, and reproducible scripting in Python or R. Handles messy CSVs, survey data, time series, panel data, and small-to-medium datasets. Produces analysis scripts and a written interpretation. Trigger when: user mentions "clean this data", "analyze", "statistics", "regression", "EDA", "explore the data", "fit a model", "visualize", "summary stats", "hypothesis test", "ANOVA", "t-test", "correlation", "Python script", "R script", "pandas", "tidyverse", or runs /analyze.

perdolique Bundle

Drizzle ORM v1 beta query patterns for TypeScript. Use when writing, reviewing, or debugging Drizzle queries on `drizzle-orm@1.0.0-beta.1+`, especially with Relations v2, Relational Query Builder v2 (`db.query.*`), dynamic filters, SQL builder fallbacks, relation loading, and query-shape type mismatches. Also apply during code review when code contains non-trivial `drizzle-orm` usage.

relewise Bundle

Analyze Relewise revenue and product-search performance. Use for KPI summaries, popular or trending searches, low-click searches, searches without results, and comparisons across periods or Datasets.

relewise Bundle

Compare two or more Relewise Datasets using consistent metadata, analytics, or consumption measures. Use when a user asks to compare stores, markets, environments, or other Dataset-backed properties.

relewise Skill

Build, review, and troubleshoot Relewise integrations using the Relewise Developer MCP. Use for implementation work involving Relewise Search, Recommendations, behavioral tracking, data integration, SDKs, or API usage in C#, TypeScript/JavaScript, PHP, or Java. Do not use for business analytics or My Relewise configuration tasks.

safetymp Bundle

HR ERP database migrations and packaging: Prisma/SQL surfaces, expand-migrate-contract, RLS-safe seeds, db:verify, distroless/GHCR supply chain. Use for DDL, backfills, dual-write cutovers, Dockerfile, or publish-ghcr workflows.

wix Skill

Use when adding tracking code, advertising pixels, third-party integrations, popups, banners, or client-side JavaScript to sites. Triggers include embed, inject, script, third-party integration, DOM injection, Google Analytics, Facebook Pixel, tracking pixel, chat widget, popup, coupon popup, custom JavaScript, site script.

whisper-money Skill

Query the local or production database from the CLI via the `agent:db` artisan command. Activates when the user asks to inspect, count, look up, or run a query against the database; asks 'how many X', 'what's in prod', 'check the prod DB', 'query the database'; or mentions production data, the prod database, or running SQL.

charlesxjyang Skill

Use when the user is working with cheminformatics: SMILES, SMARTS, SDF/MOL files, molecular graphs, substructure search, fingerprints, descriptors, similarity, reactions, standardization, stereochemistry, conformers, or molecule drawing. Prefer RDKit over generic NetworkX, regexes, pandas string parsing, or ad hoc chemistry code when molecular graph semantics matter.

charlesxjyang Skill

Use when the user is working with multidimensional microscopy or spectroscopy data, HyperSpy Signal objects, navigation vs signal axes, lazy signals, HSPY/ZSpy/DM3/DM4/EMD/TIFF/BCF/SER file loading, dimensionality reduction, model fitting, ROIs, EELS/EDS data through the eXSpy extension, or preserving microscope metadata during analysis. Prefer HyperSpy over raw NumPy/Pandas when signal axes, navigation axes, metadata, lazy loading, and microscopy signal semantics matter.

charlesxjyang Skill

Use when the user is working with materials structures, compositions, crystallography, Materials Project data, phase diagrams, Pourbaix diagrams, VASP input/output, computed entries, symmetry analysis, oxidation states, diffusion analysis, electronic structures, or conversions between materials data formats. Prefer pymatgen over generic NumPy/Pandas or ASE when the task is materials analysis rather than running a calculator.

ruc-nlpir Bundle

Create, inspect, and edit Microsoft Excel workbooks and XLSX files with reliable formulas, dates, types, formatting, recalculation, and template preservation.

alexxiang2008 Bundle

发票自动归档 - 识别增值税发票图片/PDF，自动分类汇总生成Excel报表。支持 /invoice 或 /发票 命令启动。

morzecrew Bundle

Build backend services with Forze — specs, deps modules, handlers, governed aggregates, FastAPI routes, identity and tenancy, encryption, messaging, realtime, durable execution, analytics, and deterministic simulation testing. Use when writing or wiring an application that depends on forze and its integration packages.

allthingsida Bundle

Complete idasql SQL function reference catalog. Use when looking up function signatures, parameters, or usage examples.

allthingsida Bundle

Execute IDAPython via idasql. Use when SQL surfaces are insufficient and direct IDA SDK access is needed via Python snippets or scripts.

andreab67 Bundle

Magnific generative-media API (api.magnific.com, part of Freepik) — image generation, upscaling, video, audio, and stock content through one async task API. Use when calling Magnific or working with any of its models — Mystic; Flux (2 Pro / 2 Turbo / 2 Klein / Dev / Kontext Pro / Pro v1.1 / HyperFlux); Seedream 4 / 4.5 / 4.5 Edit; Z-Image; the Creative & Precision Upscalers; Relight; Style Transfer; Remove Background; Image Expand; Kling 2.1/2.5/2.6/O1/Motion-Control; MiniMax Hailuo & Video-01-Live; WAN 2.5/2.6; Runway Gen4 Turbo & Act-Two; LTX 2.0 Pro; Seedance; PixVerse; OmniHuman; VFX; music generation; sound effects; audio isolation; or the team analytics + stock (icons / videos / templates) endpoints. Triggers — "Magnific API", "x-magnific-api-key", "upscale an image", "image to video", "generate an image/video/music", "poll a task_id", "Magnific webhook signature", "Magnific MCP". Covers the submit→poll-or-webhook task model, auth, webhook HMAC verification, rate limits, pricing, and the full per-endpoi

andreab67 Skill

Operational PostgreSQL workflows for production environments — diagnosing slow queries, lock contention, bloat, replication lag, and connection-pool exhaustion; designing and reviewing backups (pg_dump, pg_basebackup, PITR via WAL archiving); planning upgrades and major-version migrations; configuring pgBouncer/RDS Proxy/PgCat; tuning postgresql.conf for OLTP and analytics workloads; writing and reviewing schema migrations across EF Core, Alembic, Flyway, and raw SQL; setting up observability with postgres_exporter to Prometheus, log shipping to Loki, and slow-query alerting; hardening for DoD/federal use (STIG, role separation, RLS, pgaudit, TLS). Use this skill whenever the user mentions Postgres, PostgreSQL, pg_, EXPLAIN ANALYZE, autovacuum, pgBouncer, replication lag, schema migrations, or anything involving a Postgres incident, performance problem, upgrade, backup, or compliance audit — even if they don't say "Postgres" explicitly but the context is clearly a relational database on PostgreSQL. Do NOT use

apache Bundle

Apache Doris table design and cluster sizing best practices. MUST USE when writing, reviewing, or optimizing Doris CREATE TABLE statements, partition/bucket strategies, data models, or cluster configurations. ALSO MUST USE whenever the doris-architecture-advisor skill produces DDL — apply the Pre-Flight Checklist to every CREATE TABLE before output. Also triggers on any workload design involving: IoT, analytics, dashboard, CDC, time-series, log analysis, real-time warehouse, point query, data platform, or any scenario where table design decisions are being made. Also triggers on replacing or migrating from legacy analytics/search/serving stacks such as Impala, Kudu, Elasticsearch/ES, Greenplum, Presto, HBase, Hive, Hadoop, Redis, or Lambda-style multi-engine data platforms, even when Apache Doris is not named explicitly. Also use when user provides an Apache Doris connection string or asks to get started. Also triggers on slow query investigation, query profiling, runtime performance diagnosis, tablet skew an

aj-geddes Bundle

Guides secure development using defense-in-depth and attacker's mindset. ALWAYS trigger on "security review", "vulnerability", "authentication", "authorization", "input validation", "XSS", "SQL injection", "CSRF", "secrets management", "OWASP", "threat model", "security scan", "path traversal", "mass assignment", "privilege escalation", "security headers", "bandit", "dependency audit", "hardening". Use when implementing auth, handling user input, storing secrets, reviewing code for vulnerabilities, or preparing for production deployment. Different from devops skill which covers infrastructure; this covers application-level security patterns.

flydev-fr Bundle

Use for raw SQL via TSqlDB* providers, picking DB engines (SQLite, PostgreSQL, MSSQL, Oracle, Mongo, ZEOS, ODBC), pooling, BSON. Do NOT use for ORM (mormot2-orm) or REST (mormot2-rest-soa).

flydev-fr Bundle

Use when defining TOrm classes, building TOrmModel, mapping fields with attributes, configuring virtual tables, or ORM CRUD. Do NOT use for raw SQL (use mormot2-db) or REST (use mormot2-rest-soa).

blink-new Skill

Database CRUD with automatic camelCase conversion. Create, list, update, delete, upsert, count, exists. Raw SQL via CLI. Boolean handling for SQLite.

michael-denyer Bundle

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

eturkes Bundle

Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.

eturkes Bundle

Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.

caelaxie Bundle

Use when designing, reviewing, or writing SQL tables, schemas, and queries to detect and remediate SQL anti-patterns with PostgreSQL-first, constraint-backed designs and fail-closed migration guidance.

chanktb Bundle

Onboards a business into the claude-google-ads suite by producing account-context.yaml — the backbone every other skill reads. Detects the data source (Shopify/WooCommerce/BigCommerce/CSV via MCP), captures Google Ads account ids and conversion actions, GA4/GSC properties (shared vs per-site), brand and competitor terms, margins, and operator guardrails. Use when the user starts with Google Ads, has no context file yet, or says "set up", "onboard", "connect my store/account", "configure".