Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Map Delphi classes to a relational database using TMS Aurelius ORM attributes. Use when the user asks to create entity classes, add Aurelius mapping to existing classes, fix or review mapping attributes, explain how a class is mapped, or work with associations, inheritance, automapping, nullable fields, blobs, or composite identifiers. Triggers on requests like "create Aurelius entities for...", "map this class to Aurelius", "add ORM mapping", "fix the mapping on this class", "how do I map a one-to-many in Aurelius".
Save, load, update, delete, merge, and navigate entity objects using TMS Aurelius ORM (TObjectManager). Use when the user asks how to persist or retrieve data with Aurelius, manage object lifetime, work with associations or collections at runtime, handle transactions, use cached updates, or control concurrency. Does NOT cover query DSL or criteria/projections (those are in a separate skill). Triggers on requests like "save an entity with Aurelius", "load a customer from the database", "add items to a collection", "how do I update an object", "flush changes", "delete a record with Aurelius", "merge a transient object", "how do transactions work in Aurelius", "batch updates Aurelius".
Use when setting up an autonomous ML experimentation harness (an “autoresearch” loop): a fixed harness that owns data and metrics plus a hackable training script an LLM iterates on under a fixed time budget. Use when scaffolding harness.py/train.py/program.md, designing structured training-dynamics logging for agents to read, or enforcing that experiments cannot game the metric
Calculate and analyze Customer Acquisition Cost (CAC) and Customer Lifetime Value (LTV) to evaluate unit economics and marketing efficiency. Use this skill when the user needs to assess whether their customer acquisition is profitable, optimize marketing spend allocation, or evaluate business model viability — even if they say 'are we spending too much on ads', 'what's each customer worth', or 'is our growth sustainable'.
Technical enforcement of GDPR Article 5(1)(b) purpose limitation principle. Covers purpose-tagged data stores, access control per purpose, Article 6(4) compatibility assessment factors, and system design for preventing purpose creep. Includes purpose binding architecture and compatibility test implementation.
HTML-rendered version of /cc-canary — produces a long-form nerf-detection report as a standalone dark-theme HTML file and auto-opens it in the browser. Same analysis as /cc-canary (forensic markdown writeup), same narrative placeholders, but the output is a styled HTML page suitable for viewing, sharing, or printing. Writes `./cc-canary-<YYYY-MM-DD>.html` to the current directory.
Extracts HTTP/HTTPS request and response data from Charles Proxy session files (.chlsj format), including URLs, methods, status codes, headers, request bodies, and response bodies. Use when analyzing captured network traffic from Charles Proxy debug sessions, inspecting API calls, debugging HTTP requests, or examining proxy logs.
When writing reports in Feishu Docs, create, edit, and deliver chart-assistant editable chart cards. Covers 30+ built-in chart types, including columns/bars (stacked, grouped, percentage, and overlapping comparisons), line, area, scatter/bubble, dual-axis, pie/doughnut, rose, radar, funnel, word cloud, Sankey, heatmap, Treemap/Sunburst, as well as business charts such as waterfall/bridge, Mekko, bullet, dumbbell, butterfly, and small-multiple panels. Chart types, annotations, and editing capabilities are broadly aligned with ThinkCell. By default, follows MBB (McKinsey/BCG/Bain) consulting-style charting standards and provides report-grade analytical annotations such as variance annotations (total variance, hierarchical variance, compound growth rate), trendlines, reference lines/regions, and highlight coloring. Supports connecting Feishu Sheet/Base/Fengshen data sources and keeping them in sync, recreating charts from reference images, creating Feishu Docx files, and inserting/replacing chart-assistant cards in existing documents; it can also explain and validate chart-assistant configurations. Use when the user explicitly mentions Chart Assistant, editable charts or configurations, built-in Chart Assistant templates, Chart Assistant cards, data-source sync, turning Fengshen or Feishu Sheet/Base links into editable charts, or requests MBB/consulting-style charts or recreation from reference images, even if they don't name the skill. Do not take over ordinary requests like "make this a chart" or "draw a trend chart" unless they require the product capabilities above; if the user only wants a text explanation and no chart, don't trigger the chart-creation flow.
Implements strict data minimization and retention limits for children's personal data under GDPR Art. 5(1)(c), Recital 38, UK AADC Standard 8, and COPPA Section 312.7. Covers strict necessity testing, shorter retention periods, limited profiling, parental dashboard design, and automated deletion. Keywords: data minimization, children, retention, necessity test, parental dashboard.
Produce a structured churn analysis that separates avoidable from unavoidable churn. Use when investigating why customers are leaving, identifying at-risk segments, calculating net revenue retention, or building a retention intervention plan. Produces a churn report with rate calculations, categorised reasons by avoidability, segment breakdown, timing analysis, early warning signals, and prioritised interventions ranked by estimated impact.
Guide for building a consent record-keeping system to demonstrate valid consent per GDPR Article 7(1). Covers required fields including timestamp, version, purpose, mechanism, and identity. Implements audit-ready consent receipts per the Kantara Initiative Consent Receipt Specification and supervisory authority expectations.
Integrate or upgrade the Contentsquare Flutter SDK -- Session Replay, screen tracking, transactions, analytics, masking, privacy opt-in/out. Always starts with a mandatory Contentsquare project healthcheck (ask for the data source IDs or resolve the Android and iOS bundle ids, call the healthcheck endpoint, report project health) before any other work. Use when working with Contentsquare, CSQ, CSQ.start, StartConfig, AnalyticsOptions, ProductAnalyticsOptions, CSQNavigatorObserver, CSQNavigatorAutoRouteObserver, auto_route, AutoRoute, GoRouter, go_router, CSQWebViewWrapper, configureProductAnalytics, or migrating from the legacy `Contentsquare()` API to `CSQ()` (v3.x to v4.x) or from 4.1.x to 4.5.1.
Read and write large cuPyNumeric arrays to HDF5 with Legate's parallel, distributed HDF5 I/O (legate.io.hdf5: to_file, from_file, from_file_batched). Use when a developer needs to save a cuPyNumeric array to an .h5/.hdf5 file, load an HDF5 dataset into a distributed cuPyNumeric array, read a large HDF5 dataset in chunks, hand arrays to an HPC pipeline as a single file, or accelerate HDF5 disk I/O with GPUDirect Storage (GDS). Do not use it for Parquet/cuDF/raw-binary or other sharded/custom layouts (see the cupynumeric-parallel-data-load skill), Zarr or object-store/S3 output, .npz or pickled archives, plain h5py without cuPyNumeric, or pure array compute such as FFT, matmul, or reductions.
Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual partition + leaf @task launch with CPU/OMP/GPU variants. Use when no single-call loader fits, including when per-shard row counts differ across files. Prefer cupynumeric.load or legate.io.hdf5.from_file when they apply.
Analyze datasets using Python with pandas, numpy, and visualization libraries. Generates statistical summaries, identifies patterns, creates charts, and provides insights. Use when analyzing CSV/Excel files, exploring data, creating visualizations, or when users mention data analysis, statistics, charts, or datasets.
QA an analysis before sharing with stakeholders — methodology checks, accuracy verification, and bias detection. Use when reviewing an analysis for errors, checking for survivorship bias, validating aggregation logic, or preparing documentation for reproducibility
Design and audit data warehouse metrics layers, semantic models, KPI definitions, source lineage, grain, dimensions, ownership, freshness, quality tests, backfills, access, dashboards, finance/product reconciliation, and metric change control. Use when teams need trusted metrics instead of duplicated BI formulas.
Explore SQLite and PostgreSQL databases: list tables, inspect schemas (columns/types/constraints), preview data, generate Mermaid ER diagrams, and run safe read-only queries. Triggered by requests to explore a database, view table structures, describe tables, generate diagrams, or query data, and by keywords like database exploration, schema, ER diagram, or SQL query.
Work with MongoDB (document database, BSON documents, aggregation pipelines, Atlas cloud) and PostgreSQL (relational database, SQL queries, psql CLI, pgAdmin). Use when designing database schemas, writing queries and aggregations, optimizing indexes for performance, performing database migrations, configuring replication and sharding, implementing backup and restore strategies, managing database users and permissions, analyzing query performance, or administering production databases.
Use the DBX CLI to inspect DBX-managed database connections, explore schemas, run bounded read-only queries, generate DBML or schema documentation, and open tables in DBX Desktop. Use when the user asks to work with a database configured in DBX from a shell-capable AI agent. Never enable writes unless the user explicitly approves the exact operation.
NVIDIA DeepStream SDK 9.0 development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.
Architecture guide for GDPR-compliant federated learning systems. Covers horizontal and vertical FL, aggregation strategies (FedAvg, FedProx), communication efficiency, secure aggregation, and differential privacy integration. Includes privacy guarantees analysis and deployment patterns for cross-organizational ML without data sharing.
Deploy differential privacy in production systems including epsilon selection strategies, noise calibration with Laplace and Gaussian mechanisms, privacy budget tracking, composition theorems, and Python implementation patterns. Covers both central and local differential privacy models.
Maintain or migrate EF6-based applications with realistic guidance on what to keep, what to modernize, and when EF Core is or is not the right next step. USE FOR: EF6 codebases; runtime versus ORM migration decisions; EDMX, code-first, ObjectContext, and legacy data-access review. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.