Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Manages Google Cloud Pub/Sub topics, subscriptions, schemas, and messages safely and efficiently. Use when building or managing event-driven, decoupled systems, streaming data pipelines, or integrating push/pull asynchronous message consumers. Don't use when writing or debugging Google Cloud client library code or raw REST/gRPC API interactions directly.
Runs differential expression analysis on bulk RNA-seq count data with PyDESeq2, the Python port of DESeq2. Covers formulaic single- and multi-factor designs, contrasts, Wald tests, Benjamini-Hochberg FDR correction, optional apeGLM LFC shrinkage, pandas and AnnData (H5AD) integration, CSV export, volcano and MA plots, and a command-line script. Use when comparing gene expression between conditions such as treated vs control, adjusting for batch or covariates, porting an R DESeq2 workflow to Python, or building a Python pipeline for differential expression from raw integer counts. Not for single-cell data or for R-based DESeq2 itself.
Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.
Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API, opentrons-integration may be simpler.
Complete mass spectrometry analysis platform. Use for proteomics workflows feature detection, peptide identification, protein quantification, and complex LC-MS/MS pipelines. Supports extensive file formats and algorithms. Best for proteomics, comprehensive MS data processing. For simple spectral comparison and metabolite ID use matchms.
Facilitates a top-down pyramid discussion that calibrates the user's topic depth, then starts at high-level goals and progressively descends to concrete actionables, sharpening gaps and assumptions at each layer. Use when the user wants to break down a goal, explore a vision, elicit requirements, or mentions pyramid discussion, top-down planning, or progressive breakdown.
Complete Python gotchas reference. PROACTIVELY activate for: (1) Mutable default arguments, (2) Mutating lists while iterating, (3) is vs == comparison, (4) Late binding in closures, (5) Variable scope (LEGB), (6) Floating point precision, (7) Exception handling pitfalls, (8) Dict mutation during iteration, (9) Circular imports, (10) Class vs instance attributes. Provides: Problem explanations, code examples, fixes for each gotcha. Ensures bug-free Python code.
Modern Python patterns for Modal.com serverless platform. PROACTIVELY activate for: (1) Modal function deployment, (2) Type-safe Modal with Pydantic, (3) Async patterns in Modal, (4) GPU workloads (ML inference, training), (5) FastAPI web endpoints on Modal, (6) Scheduled tasks and cron jobs, (7) Modal Volumes and storage, (8) Testing Modal functions with pytest, (9) Modal classes and lifecycle methods, (10) Parallel processing with map/starmap. Provides: Type hints patterns, Pydantic integration, async/await patterns, pytest testing, FastAPI integration, scheduled tasks, Volume usage, cost optimization, and production-ready examples following Python 3.11+ best practices.
Complete Python package management system. PROACTIVELY activate for: (1) uv package manager (10-100x faster), (2) pyproject.toml configuration, (3) Virtual environment setup, (4) Dependency management with uv.lock, (5) Ruff linting and formatting, (6) src layout project structure, (7) Publishing to PyPI, (8) pip and requirements.txt. Provides: uv commands, pyproject.toml templates, ruff config, pre-commit setup. Ensures modern Python project setup with fast tooling.
Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.
IBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads, or needing IBM optimization tools. Best for IBM hardware execution, quantum error mitigation, and enterprise quantum computing. For Google hardware use cirq; for gradient-based quantum ML use pennylane; for open quantum system simulations use qutip.
Simulate and audit closed and open quantum-system models with QuTiP 5, including deterministic, trajectory, steady-state, spectral, and phase-space workflows. Use for local quantum-dynamics work where physical assumptions, dimensions, and numerical convergence must be explicit.
Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms.
Protocol reversing gateway. Orchestrates: capture → crypto identification → keys → decryption → state machine reconstruction. Sub-skills: [[re-netcap]] [[re-crypto-id]] [[re-crypto-keys]] [[re-crypto-decrypt]] [[re-proto-rev]] [[re-ics]] [[re-iot-proto]] [[re-whitebox]] [[re-tls]]. Trigger words: protocol reversing, packet capture, traffic analysis, decrypt traffic, C2 protocol, custom protocol, protocol analysis.
Consult at every judgment checkpoint: before committing to an approach, after a failure or direction change, and before presenting a result. Also unblocks decisions, challenges consequential claims, or asks irreducible user-owned questions. Skip only mechanical work with nothing left to judge.
Skills for creating and publishing Xiaohongshu posts. Use to: (1) generate Xiaohongshu-style post content (title, body, and tags); (2) obtain or generate post images; (3) automatically upload to the Xiaohongshu Creator Platform. Trigger phrases: Xiaohongshu creation, create redbook, Xiaohongshu, Red Book, note creation, post creation
Use when the user asks for safe refactoring suggestions, refactor opportunities, or cleanup ideas. Analyzes codebase patterns (duplicate blocks, long functions, magic values, unused code, simple type improvements) and proposes low-risk refactors grouped by safety level. Does not execute changes—suggests only.
Use when the user invokes /reflect or asks to reflect on, wrap up, or take stock of the current session. Re-reads the in-context conversation for anything that would die when the session closes—dropped action items, durable lessons with no home, stale docs, skillify opportunities, global/project CLAUDE.md and AGENTS.md and README gaps, and follow-ups worth an issue or a PR—surfaces them as one ranked shortlist, then acts on the ones the user selects. Not a git-history retro and not a full doc audit.
Write security findings and assessment reports — severity scoring with CVSS and business impact, reproducible proof of concept, remediation guidance, executive summaries, and coordinated disclosure. Use when writing up a vulnerability, producing a pentest or audit report, triaging a bug bounty submission, or preparing a disclosure timeline.
Conduct topic and competitor research for any content type. Use when researching a topic before creating content, analyzing the competitive landscape, identifying content gaps, or when the user says "research this", "what's out there on", "analyze competitors", or needs to understand a content landscape before writing.
Book reservations through Google Maps using browser automation. Searches for businesses, checks availability, and completes bookings via "Reserve with Google" or 3rd-party providers (OpenTable, Resy, Vagaro). Supports restaurants (primary), salons, fitness, healthcare. Use when user wants to book, reserve, or schedule at a business found on Google Maps.
Generate reveal.js HTML slide presentations from topics, outlines, or content. Use when the user asks to create slides, presentations, decks, or talks. Triggers on: "create a presentation", "make slides about", "build a deck", "generate a talk", "slide deck for", or any request involving presentation creation. Supports code highlighting, fragments, speaker notes, math, markdown, and Mermaid.js diagrams (flowcharts, sequence, class, ER, mindmap, timeline, etc.).
Walk a SubImage attack path step by step, identify the most sensitive impacted assets, propose the fastest remediation, hunt for credible n+1 extensions the engine has not yet modeled, and optionally simulate what-if scenarios. Use when the user asks to “review this attack path”, “explain this attack path”, “what would happen if X is compromised”, “what attack paths involve <asset>”, “find lateral movement opportunities from <asset>”, “assess the blast radius of <asset>”, or pivots from `subimage-mcp:investigate-cve`. Three entry modes: by path id, by asset id, or n+1 extension hunt.
Review an RWX config generated from a GitHub Actions migration. Compares the source workflow against the generated config to catch semantic gaps, missing steps, and optimization opportunities. TRIGGER when: the user asks to review, validate, or check an RWX config that was migrated from GitHub Actions.
Review a GitLab merge request and post approved comments. Use when the user asks to review a GitLab MR, provides a GitLab merge request URL / `group/project !IID` / `!IID`, or wants a code review posted to GitLab. Talks to GitLab through the embedded zero-dependency CLI at scripts/gitlab.mjs (no MCP server required).
Reviews the platform and integration version tables and the key-date table in an RHDH test-plan Jira issue against vendor lifecycle data and the release schedule, then applies the accepted edits. Covers OCP, ARO, OSD, ROSA, AKS, EKS, GKE, PostgreSQL, RHBK, and Quay rows. Use for "review the test plan for 1.11", "which platform versions should the 1.10 test plan list", "update the test plan dates", or a test-plan Jira URL or key such as RHIDP-1234.
Migrate Riverpod from StateNotifier to Notifier/AsyncNotifier, from ChangeNotifier to AsyncNotifier, or upgrade from 0.13/0.14/1.0; ref.onDispose, family, lifecycle, riverpod migrate CLI. Use when the user asks about migrating from StateNotifier, from ChangeNotifier, upgrading Riverpod 0.13 to 0.14, 0.14 to 1.0, or Riverpod migration guides.
Import HD Map or OpenDRIVE files into a RoadRunner scene using MATLAB. Use when loading driving scenes in RoadRunner or RoadRunner Scene Builder, importing RRHD, OpenDRIVE, or other RoadRunner-supported formats for simulation, or verifying Lanelet2-to-RRHD conversion results visually. Requires rrApp handle from roadrunner-core.
Build RoadRunner HD Map entities in MATLAB — lanes, boundaries, markings, junctions, signs, signals, barriers, parking. Use when creating driving scenes from scratch, authoring road networks for simulation and testing automated driving systems, or assembling RRHD maps from Lanelet2 or other HD map sources.
Author the smallest sufficient route of suite capabilities into ignored `route.md`. Use when the next capability is unclear, work spans several capabilities, or current state may already satisfy part of the request; skip it when one capability obviously applies.
Cloud-based quantum chemistry platform with Python API. Preferred for computational chemistry workflows including pKa prediction, geometry optimization, conformer searching, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2). Use when tasks involve quantum chemistry calculations, molecular property prediction, DFT or semiempirical methods, neural network potentials (AIMNet2), protein-ligand binding predictions, or automated computational chemistry pipelines. Provides cloud compute resources with no local setup required.
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.