Data & Analytics

nledford Skill

Database-neutral SQL engineering guidance. Use when reading, writing, refactoring, reviewing, testing, or optimizing SQL queries, schemas, migrations, tables, views, functions, triggers, constraints, indexes, transactions, reporting queries, or data behavior before choosing a database-specific skill. Use api-design when SQL changes affect published contracts, observability-engineering for database telemetry, and PostgreSQL, MySQL/MariaDB, or SQLite skills for engine-specific behavior.

nledford Skill

Review Rust code with Rust-specific rigor. Use with code-review when changes touch Rust ownership, lifetimes, traits, error contracts, crate boundaries, feature flags, tests, Rustdoc, async, Tokio, Axum, Leptos, SQLx, SeaQuery, SeaORM, Diesel, SQLite, unsafe code, macros, FFI, public APIs, design patterns, anti-patterns, or performance-sensitive behavior. Use sql-engineering, postgresql-sql-engineering, mysql-mariadb-sql-engineering, or sqlite-sql-engineering too for database-native schema, SQL, migrations, privileges, or query plans.

nledford Skill

Rust anti-pattern detection and correction guidance. Use when reviewing or refactoring Rust code for generated-code smells, borrow-checker workarounds, unnecessary clones, Arc<Mutex> misuse, boxed indirection, deref polymorphism, deny-warnings misuse, panic/unwrap at boundaries, async overuse, leaky framework or SQL types, brittle tests, or architecture boundary violations. Do not use for ordinary Rust implementation; use rust-engineering instead.

nledford Skill

Rust persistence, SQLx, SeaQuery, and SQL-library guidance. Use when adding, changing, reviewing, or testing SQLx queries/macros, SeaQuery builders, SeaORM, Diesel, raw SQL choices, Rust database adapters, pools, transactions, offline query metadata, migrations invoked from Rust, SQLite support, database-backed Rust tests, dynamic SQL construction, or persistence boundaries. Use sql-engineering, postgresql-sql-engineering, mysql-mariadb-sql-engineering, or sqlite-sql-engineering for database-native design.

nledford Skill

SQLite and SQL engineering guidance. Use with sql-engineering when adding, changing, reviewing, testing, or optimizing SQLite schemas, migrations, constraints, indexes, transactions, query behavior, local/embedded database workflows, SQLite-backed tests, or SQLite-specific adapter boundaries in any language stack. Do not use for unchanged-SQL ORM or generic adapter mechanics. Use api-design when SQLite schemas or exports affect published contracts and observability-engineering for durable SQLite diagnostics.

nledford Bundle

Data-platform engineering guidance for implementing, changing, reviewing, or testing source-to-landing ingestion, post-landing lakehouse or warehouse transformations, analytical semantic contracts, Power BI semantic models and DAX, and Microsoft Fabric or Power BI operations. Use for CDC, watermarks, replay, Delta tables, medallion layers, analytical grain, governed metrics, TMDL, RLS or OLS, refresh, promotion, gateways, capacity, recovery, and runbooks. Do not use for application domain modeling, physical OLTP database design, generic distributed protocols, generic UX, or final release decisions.

nledford Skill

PostgreSQL and SQL engineering guidance. Use with sql-engineering when adding, changing, reviewing, testing, or optimizing PostgreSQL schemas, SQL queries, migrations, transactions, constraints, indexes, views, functions, row-level security, privileges, data behavior, or database performance in any language stack. Do not use for unchanged-SQL ORM or adapter mechanics. Use api-design when migrations or query outputs affect published contracts and observability-engineering for PostgreSQL telemetry signals.

nledford Skill

MySQL and MariaDB SQL engineering guidance. Use with sql-engineering when adding, changing, reviewing, testing, or optimizing MySQL or MariaDB schemas, SQL queries, migrations, transactions, constraints, indexes, views, stored routines, replication, privileges, storage engines, connection pooling, or query performance in any language stack. Explicitly name which engine and version a change targets when MySQL and MariaDB diverge. Do not use for unchanged-SQL ORM or adapter mechanics. Use api-design when migrations or query outputs affect published contracts and observability-engineering for MySQL/MariaDB telemetry signals.

fatih-developer Bundle

Expert SQLite guidance for modern full-stack and AI projects. Use when user mentions sqlite, sqlite3, bun:sqlite, better-sqlite3, aiosqlite, libsql, Turso, Cloudflare D1, WAL mode, FTS5, sqlite-vec, or asks about local/embedded databases, schema design, SQLite migrations with Drizzle or raw SQL, performance tuning, backup/restore, and building stateful CLI with SQLite.

vanducng Bundle

Operate the Braze platform through braze-cli category commands for campaigns, Canvas, catalogs, analytics, messaging, SMS, subscriptions, users, templates, and content blocks. Use when the user asks to inspect Braze data, diagnose permissions, change opt-in or opt-out state, or validate and ship the Braze CLI.

vanducng Skill

Query, inspect, and manage saved database connections through the Go `miudb` CLI. Use when the user asks to run SQL, list schemas, add native connections, smoke-test connections, inspect tunnel-backed databases, or produce agent-readable JSON from SQLite, Postgres, MySQL, Snowflake, or BigQuery.

vanducng Bundle

Design and review production database schemas, data models, ERDs, migration plans, and storage patterns. Use for OLTP schema design, OLAP/star-schema modeling, fact/dimension tables, indexes, constraints, partitioning, multi-tenant data models, CSV/JSON-to-table design, schema review, migration risk review, and database design documents across PostgreSQL, MySQL, SQLite/D1, BigQuery, and MongoDB. Does not execute DDL by default.

aradotso Skill

Monitor Claude AI token usage in real-time with ML predictions, cost analytics, and session limit warnings

zju-real Bundle

飞书云空间：管理云空间中的文件和文件夹。上传和下载文件、创建文件夹、复制/移动/删除文件、查看文件元数据、管理文档评论、管理文档权限、订阅用户评论变更事件、修改文件标题（docx、sheet、bitable、file、folder、wiki）；也负责把本地 Word/Markdown/Excel/CSV 以及 Base 快照（.base）导入为飞书在线云文档（docx、sheet、bitable）。当用户需要上传或下载文件、整理云空间目录、查看文件详情、管理评论、管理文档权限、修改文件标题、订阅用户评论变更事件，或要把本地文件导入成新版文档、电子表格、多维表格/Base 时使用。

aaronjmars Bundle

Build a weekly token-consumption recap image from memory/token-usage.csv - this week + all-time totals, top skills, rendered as a shareable SVG card.

hajibabaie Skill

When the user wants to version-control optimization research code - small commits per experiment change, tags for paper result snapshots, .gitignore for solver logs, linking result tables to commit hashes, and branch strategy for risky refactors. Also use when the user mentions "git workflow," "version control research," "tag results," "reproducible experiments git," "gitignore solver," or when a paper number must trace to an exact code state. For repository layout, see optimization-project-structure; for tidy result tables, see pandas-experiment-management.

mahdtech Bundle

Expert guidance, CLI commands, architecture reference, file server & share management, SMB/NFS protocols, directory services, smart tiering, disaster recovery, analytics, performance tuning, and troubleshooting for Nutanix Files (v5.0). Use when working with Nutanix Files, SMB/NFS file shares, file analytics, Smart Tiering, Metro Availability, Files REST APIs, or file server performance optimization.

fatih-developer Bundle

Traces the data source (Data Lineage) of any column or table. Identifies views, triggers, stored procedures, and ETL pipelines involved.

fatih-developer Bundle

Plan end-to-end push notification strategies using APNs and FCM. Design payloads, define permission request timing, architect silent pushes vs. rich notifications, and structure analytics tracking.

gannonh 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.

asdc163 Bundle

Turn a product outcome or AI product goal into an evidence-bounded metric contract with a primary measure, denominator, window, guardrails, instrumentation gaps, and a decision rule. Use before an experiment, rollout, or evaluation when a PM needs to define what success means without inventing baselines or analytics evidence.

envoydev Bundle

PostgreSQL engine specialist - the Postgres-specific delta on top of the cross-engine database-conventions hub: identifier folding and idempotent DDL, index-type selection (B-tree/GIN/GiST/BRIN/hash), JSONB and full-text indexing, SARGable predicate rewrites, the planner (EXPLAIN ANALYZE, pg_stat_statements, autovacuum/ANALYZE, work_mem), connection pooling modes, and array-batching/ON CONFLICT/COPY. Load for any hand-written Postgres SQL, an .sql file on a Postgres project, an EXPLAIN plan, a slow query, or an index/pooling decision. Not the cross-engine schema/transaction rules (-> database-conventions), the ORM side (-> dotnet-data-access), or another engine's SQL. Companions: database-conventions (cross-engine hub - load first), database-security (RLS/privileges), dotnet-data-access (the EF Core / ORM side).

envoydev Skill

SQL / data-layer security-hardening reference, organized by the persistence threat surface: SQL injection closed at every sink, least-privilege database accounts, row-level security and tenant isolation (the data-layer IDOR), secrets kept out of connection strings, encryption at rest and in transit, sensitive-data exposure and masking, and audit logging that never records the secret. Load when hardening or reviewing a SQL / data-persistence feature, when the security-auditor sweeps the data stack, or on asks like 'is this query injectable' or 'can one tenant read another's rows'. Points at dotnet-security for the app-layer EF and injection surface, dotnet-cryptography for crypto primitives, and dotnet-migrate for safe migration mechanics. Do NOT load for non-security work.

envoydev Bundle

The .NET ORM / data-access layer (.NET 8 floor) - ORM-agnostic access principles here, per-ORM mechanics in references/: session or context lifetime and thread-safety, change tracking, loading strategy and N+1, projection to read models, bounded results and no-generic-repository, and the full-ORM-for-writes + micro-ORM-for-reads split. Load when you configure a DbContext or ISession, write or review an ORM query, pick a loading strategy, or design a read/write store; then use references/efcore.md for EF Core or references/nhibernate.md for NHibernate. Not the engine side (raw SQL, index, planner -> postgres / sqlite) nor the migration playbook (-> dotnet-migrate). Companions: csharp (async, mapping), dotnet-testing (integration tests).

envoydev Bundle

Choose and hold a .NET application architecture - the decision layer here, each style's depth in references/. Two axes plus one additive: topology (single deployable -> modular-monolith -> microservices), internal organization (clean-architecture vs vertical-slice), and DDD tactical patterns layered on when the domain has real invariants. Load when deciding where code belongs, structuring a new app or module, picking a layering/slicing style, drawing a service or module boundary, reviewing architecture drift, or when the user says clean architecture, vertical slice, DDD, modular monolith, microservices, or bounded context. Companions: dotnet-architecture-tests, dotnet-web-backend, dotnet-messaging, csharp. Do NOT load for encoding the boundaries as build-failing tests (dotnet-architecture-tests) or raw SQL / query tuning (postgres).

envoydev Bundle

database conventions across Postgres, SQL Server/T-SQL, SQLite, and MongoDB - the engine-neutral rules for schema design, migrations, indexes, foreign keys, transactions, connection management, query safety, N+1 prevention, and secret handling, plus the per-engine pitfalls that bite. Load before designing or modifying a schema, writing SQL raw or through an ORM, modeling a document store, or creating a migration, view, procedure, or index. Deeper work routes out: engine tuning to `postgres` / `sqlite`, .NET data access to `dotnet-data-access`, migration mechanics to `dotnet-migrate`, security posture to `database-security`. Do NOT load for app-only in-memory data structures or a project with no persistence layer.

hajibabaie Skill

When the user wants to choose facility sites and assign customers to them — UFLP, CFLP, p-median, or p-center — with strong MIP formulations, Benders or Lagrangian solution paths, and greedy, interchange, or VNS heuristics. Also use when the user mentions "facility location," "p-median," "p-center," "open facilities," "location-allocation," "UFLP," "warehouse location," or when fixed opening costs trade off against assignment or transport costs. For optimality-cut decomposition at scale, see benders-decomposition; for demand uncertainty, see stochastic-optimization.

hajibabaie Skill

When the user wants to record, store, and aggregate computational-experiment results for optimization algorithms with pandas - tidy one-row-per-run tables, run metadata (instance, seed, algorithm, parameters, runtime, objective), atomic CSV/parquet writing, aggregation across instances and seeds, and pivot tables for papers. Also use when the user mentions "experiment results," "results dataframe," "aggregate runs," "experiment tracking," "results CSV," "results parquet," or when thousands of raw runs must become one defensible paper table. For statistical comparison of algorithms, see algorithm-benchmarking-statistics; for turning result tables into figures, see matplotlib-optimization-visualization.

hajibabaie Skill

When the user wants to organize optimization research code into a reproducible project — separating the src package, scripts, configs, and results; JSON/YAML config systems; factory registration of algorithms and problems; seed discipline; atomic result writing; and light testing. Also use when the user mentions "project structure," "research code organization," "config file," "factory pattern," "reproducible runs," or "random seed," or when results can no longer be traced to the exact code and parameters that produced them. For result tables and aggregation, see pandas-experiment-management; for commit and tag discipline, see git-for-research-code.

hajibabaie Skill

When the user wants to compare optimization algorithms with a sound empirical protocol — instance and seed design, time limits, best/mean/gap reporting, nonparametric hypothesis tests, effect sizes, and the plots that summarize them. Also use when the user mentions "compare algorithms," "statistical test," "Wilcoxon," "Friedman test," "performance profile," "time-to-target," or asks "is my algorithm better" than a baseline. For benchmark instance sets and parsers, see instance-generation-and-benchmarks; for tidy run tables and aggregation, see pandas-experiment-management.

jperezduerto Skill

Operate sqlmap for automatic SQL injection detection and database takeover. Use when the user needs to test for SQL injection, enumerate database contents, extract tables and data, obtain OS shells or file read/write access, bypass WAFs with tamper scripts, or integrate with Burp Suite saved requests. Covers detection techniques, injection types (boolean, time, error, union, stacked), all enumeration flags, second-order injection, tamper scripting, request customization, and advanced evasion. Source: https://github.com/sqlmapproject/sqlmap

jperezduerto Skill

Operate Chainsaw — a fast Windows event log (EVTX) analysis tool with Sigma rule integration for rapid threat hunting and incident response. Use when analyzing Windows event logs for lateral movement, credential access, persistence, execution, or defense evasion artifacts. Covers installation (cargo, releases), hunt mode with Sigma rules, search mode, dump mode, supported formats (EVTX, JSON), output formats (ASCII table, CSV, JSON), writing custom detection rules, key detection categories, and incident response triage workflows.

jperezduerto Skill

Use and weaponize the PayloadsAllTheThings payload library for web application penetration testing and CTF engagements. Use when the user needs injection payloads, bypass techniques, or exploitation strings for SQL injection, XSS, command injection, SSRF, XXE, SSTI, CSRF, LFI/RFI, directory traversal, authentication bypass, or deserialization attacks. Covers payload selection, real-world delivery with Burp Suite and curl, WAF bypass, chaining vulnerabilities, and reporting. Source: https://github.com/swisskyrepo/PayloadsAllTheThings

drmoisan Skill

Admit one new item into a running parallel run — preparation via a preparation-mode child orchestrator run, conflict-edge computation against all items including in-flight ones, and the admission decision that either places the item in the current cohort or defers it and recolors the unstarted subgraph. Appends exactly one mutations[] entry. In-flight items are never moved.

drmoisan Skill

Prepare a set of thematically unrelated items for concurrent execution before any execution begins - item intake over issue numbers and potential-entry paths, concurrent preparation-mode child orchestrator delegations, blast-radius computation and V1-V3 validation, cohort seeding with a recomputation-parity check, run-manifest and planner-checkpoint authoring, and the parallel-orchestrator kickoff artifact.

drmoisan Skill

Execute a prepared parallel run for the parallel-orchestrator agent — cohort scheduling under a max_concurrency cap, per-item fan-out onto isolated worktrees branched from origin/main, per-item merge to main after durably confirming CI green, worktree cleanup, and the generated parallel-status.md projection. There is no integration branch and no final integration pull request.