Official Agent Skills

Build, test, lint, version, and publish production-grade Python libraries to PyPI with support for multiple build backends, versioning strategies, and CI/CD.

Connects an AI agent to a FlowStudio MCP server for Power Automate, handling authentication, tool discovery, and response parsing. Load this foundation skill before using specialized workflow skills for building, debugging, monitoring, or governing flows.

Design, implement, and validate Python-based IoT Edge modules for telemetry processing, local inference, protocol translation, and edge-to-cloud integration.

Build, scaffold, and deploy Power Automate cloud flows programmatically via the FlowStudio MCP server, including constructing flow definitions, wiring connections, deploying, and testing.

Runs a Trailmark summary analysis on a codebase to auto-detect languages, count entry points, and list dependencies.

Iteratively reviews and fixes Claude Code skill quality issues by running automated fix-review cycles using the skill-reviewer agent until they meet standards.

Parse, analyze, and process SARIF files from static analysis tools like CodeQL and Semgrep, including filtering, deduplication, aggregation, and CI/CD integration.

Fuzz C/C++ projects with multi-core support using AFL++, a fork of AFL with better performance and advanced features.

Translates Mermaid sequence diagrams of cryptographic protocols into ProVerif formal verification models (.pv files) for proving security properties like secrecy, authentication, and forward secrecy.

Runs full Trailmark structural analysis by building a graph and computing pre-analysis passes for hotspots, taint, blast radius, privilege boundaries, and attack surface.

Find similar vulnerabilities and bugs across codebases using pattern-based analysis after identifying an initial issue.

Creates pre-configured devcontainers with Claude Code, language-specific tooling (Python, Node, Rust, Go), and persistent volumes for isolated development environments.

Identifies state-changing entry points in smart contract codebases for security auditing. Detects externally callable functions that modify state, categorizes them by access level, and generates structured audit reports.

Scans Android APKs for Firebase security misconfigurations including open databases, storage buckets, authentication issues, and exposed cloud functions. For authorized security research only.

Patch code to bypass checksums, global state, and validation checks that block fuzzer progress, using conditional compilation for C/C++ and Rust.

Guides fuzzers with domain-specific tokens to reach deeper code paths in parsers, protocol handlers, and file format processors.

Analyzes cryptographic code to detect operations that leak secret data through execution timing variations, supporting multiple languages.

Provides guidance for property-based testing across multiple languages and smart contracts, helping detect patterns where PBT offers stronger coverage than example-based tests.

Detect timing side channels in cryptographic code using formal, symbolic, dynamic, and statistical testing tools.

Prepares codebases for security review using Trail of Bits' checklist by setting review goals, running static analysis, increasing test coverage, removing dead code, and generating documentation.

Verifies that blockchain code implements exactly what documentation specifies, identifying gaps between specs and implementation for audit engagements.

Assesses codebase maturity using Trail of Bits' 9-category framework, producing a professional scorecard with evidence-based ratings and actionable recommendations.

Analyzes token implementations and integrations for ERC20/ERC721 conformity, weird token patterns, contract composition, owner privileges, and on-chain scarcity.

Scans Cosmos SDK blockchain modules and CosmWasm contracts for consensus-critical vulnerabilities such as chain halts, fund loss, and state divergence.

Scans Solana programs for 6 critical vulnerabilities including arbitrary CPI, improper PDA validation, missing signer/ownership checks, and sysvar spoofing.

Scans Substrate/Polkadot pallets for 7 critical vulnerabilities including arithmetic overflow, panic DoS, incorrect weights, and bad origin checks. Use when auditing Substrate runtimes or FRAME pallets.

Clarify requirements before implementing by asking targeted questions when a request has multiple plausible interpretations or key details are unclear.

Sets up an isolated Python environment for SageMaker and AWS work, pinning Python version and installing current boto3/awscli to avoid dependency conflicts and stale SDKs.

Creates SageMaker endpoints (real-time or async) with autoscaling, CloudWatch alarms, and tagging enabled by default, then smoke-tests them before declaring success.

Generates a polished, leadership-ready performance briefing with KPI tiles, executive narrative bullets, and a driver analysis — all as a print-ready HTML document.

Writes internal communications using company-specific formats for status reports, leadership updates, newsletters, FAQs, incident reports, and project updates.

Analyze a screen recording of a manual process and produce targeted, working automation scripts. Extracts frames and audio narration from video files, reconstructs the step-by-step workflow, and proposes automation at multiple complexity levels using tools already installed on the user machine.

Detects generalizable learnings from problem-solving interactions and proposes skill updates to improve future performance.

Build and manage applications on the Cloudflare platform, including Workers, Pages, storage, AI, networking, security, and infrastructure-as-code.

Compare identical tables across two SQL Server instances using Python with mssql-python and Apache Arrow, detecting missing rows, column mismatches, schema drift, and generating a reconciliation report.

Generates custom design system rules for AI coding agents by analyzing a project's codebase and conventions, then saving them to the appropriate rule file (CLAUDE.md, AGENTS.md, or .cursor/rules).

Transforms vague UI ideas into polished, Stitch-optimized prompts by enhancing specificity, adding UI/UX keywords, injecting design system context, and structuring output for better generation results.

Create, synthesize, and iteratively improve agent skills following the Agent Skills specification. Handles source capture, precision passes, authoring, registration, and validation.

Scan AEM Edge Delivery Services pages for WCAG 2.1 AA violations and generate specific fixes for content authors and developers.

Creates CodeTour .tour files — persona-targeted, step-by-step walkthroughs that link to real files and line numbers for any repository.

Verifies suspected security bugs to eliminate false positives, producing a TRUE POSITIVE or FALSE POSITIVE verdict with documented evidence for each.

Search models, datasets, Spaces, and papers on the Hugging Face Hub, retrieve repository details and documentation, run compute jobs, and use Gradio Spaces as AI tools via the Hugging Face MCP server.

Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page.

Answers questions about a code repository by analyzing source files, providing evidence-based explanations with inline citations.

Install or update the M365 Agents Toolkit (ATK) CLI and VS Code extension using npx and the VS Code CLI.

Manage Microsoft Fabric capacities via Azure Resource Manager: provision, scale, suspend, resume, check name availability, and list SKUs using the .NET SDK.

Analyze images using Azure AI Vision SDK: generate captions, tags, detect objects, extract text (OCR), detect people, and suggest smart crops.

Build augmented reality interfaces for display glasses using Jetpack Compose Glimmer, covering design principles, theming, input mapping, and projected activity setup.

Generate and edit videos using the Gemini Omni Flash model: text-to-video, image-to-video, video editing, and turn-by-turn refinement via the official google-genai SDK.

Call the Gemini API for text generation, chat, multimodal understanding, image/video/audio generation, streaming, function calling, structured output, and managed agents using the Interactions API in Python and TypeScript.

Review pull requests following Sentry engineering practices, covering security, performance, testing, and design.

Improve code structure and readability without changing external behavior through surgical refactoring techniques.

Review and refactor code according to project-specific coding guidelines and instructions.

Quantifies the business and regulatory impact of a potential data breach by inventorying sensitive data, tracing data flows, scoring exposure vectors, and estimating regulatory fines using law-sourced figures.

Routes requests to design, create, update, debug, or upgrade GitHub Agentic Workflows by loading the appropriate workflow prompt or skill file.

Design and implement Arduino integration with Azure IoT Hub and IoT Edge, including secure provisioning, resilient telemetry, command handling, and production guardrails.

Orchestrates a dimensional-analysis pipeline to annotate codebases with unit/dimension comments, discover dimensional vocabulary, and detect arithmetic bugs from unit mismatches or precision loss.

Provides creative direction for HyperFrames videos, handling design specs, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand/style decisions.

Render a proposed redesign of a page as a self-contained static HTML file, then iterate via chat-driven commands until approved.

Send custom logs to Azure Monitor Log Analytics workspace using the Logs Ingestion API and Python SDK.