Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engine build, custom nvinfer bbox parser, multi-stream benchmark, and PDF report. Object detection models only.
E2E and integration testing for TypeScript/NestJS projects using Jest, supertest, and real infrastructure via Docker (Kafka, PostgreSQL, MongoDB, Redis) with the Given-When-Then pattern. Use whenever the user is working on `.e2e-spec.ts` files or anything under `test/e2e/`, or asks to set up, write, review, run, debug, or optimize E2E or integration tests — including flaky tests, docker-compose for tests, Kafka/Redpanda consumers, test isolation, or GWT compliance.
Quality review and audit for Claude Code skills. Analyzes skill structure, description quality, workflow design, token efficiency, and anti-patterns against best practices. Use when user wants to review a skill, audit a skill, check skill quality, evaluate a skill, critique a skill, lint a skill, or validate a skill. Triggers: 'review skill', 'audit skill', 'skill quality', 'check my skill', 'evaluate skill', 'skill lint', 'validate skill', 'skill review', 'is this skill good', 'improve this skill'.
Performs general code reviews of PRs and code changes. Evaluates code quality, security, and design against common criteria, and decides approve/reject. Use for requests such as "review this PR", "code review", or "pre-merge check", and when running the gh pr view command.
Ask the user for a code review by opening the changes in difit, a local diff viewer. Explicit opt-in only — use when the user names difit, asks to open or show the diff in the viewer, or has a standing instruction to request reviews through difit after changes. Do not use it for ordinary requests to review code, diffs, commits, branches, or pull requests.
Use when writing or reviewing Jetpack Compose UI tests, screenshot tests or baseline-recording evidence, previews, semantics assertions, fake image loading, keyboard input, focus assertions, interaction state (hover/pressed/focused), or tests for plain state-driven UI composables
Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this spreadsheet", "sanity check this", "debug model", "model check", "model won't balance", "something's off in my model", "model review".
Design a usability study — research questions, methodology, participant criteria, metrics, and facilitation guide. Use when planning the study as a whole. For writing the task scenarios inside it, use `test-scenario` (prototyping-testing).
Run Semgrep static analysis scans and create custom detection rules. Use when asked to scan code with Semgrep, find security vulnerabilities, write custom YAML rules, or detect specific bug patterns. IMPORTANT: Also use this skill when users ask to 'scan for bugs', 'check code quality', 'find vulnerabilities', 'static analysis', 'lint for security', 'audit this code', or want to enforce coding standards — even if they don't mention Semgrep by name. Semgrep is the right tool for pattern-based code scanning across 30+ languages.
Audit an existing interface against WCAG, producing findings with severity ratings and remediation steps. Use when you have a design or build to assess now. Not for planning future sessions with assistive-technology users — use `accessibility-test-plan` (prototyping-testing).
Applies and explains code conventions across TypeScript, React, C#, and Markdown. Enforces naming rules, file naming patterns, TSDoc and XML doc standards, inline comment intent (the *why*, not the *what*), code structure, error handling, async patterns, and dead code policy. Also enforces ADR and contributor doc decisions, and flags decisions that appear stale or misaligned with current tooling. USE FOR: convention questions, code review against project standards, applying naming rules, auditing intent comments, checking TSDoc completeness, enforcing recorded ADR decisions, and flagging stale architectural decisions. DO NOT USE FOR: security vulnerability scanning, performance profiling, runtime debugging, or generating net-new code without a review target.
Use when making code changes to ensure they pass VS Code's hygiene checks. Covers the pre-commit hook, unicode restrictions, string quoting rules, copyright headers, indentation, formatting, ESLint, and stylelint. Run the hygiene check before declaring work complete.
Make every number in the final PDF traceable to the exact code line that produced it. Uses \hypertarget/\hyperlink LaTeX commands and \num{formula} evaluated at compile time. Use for reproducibility and data integrity verification.
This skill guides review of security practices and potential vulnerabilities; no checklist ensures all code is secure. Use when implementing authentication or authorization, handling user input or file uploads, or creating new API endpoints
Design, implement, optimize, and review SIMD code in .NET. Use for vectorizing scalar loops with TensorPrimitives, Vector64/128/256/512, or platform hardware intrinsics; reviewing existing SIMD code, including the generic Vector type, for contract equivalence, tail handling, memory safety, portability, fallbacks, and measured performance. Do not use for performance work unrelated to SIMD or vectorization.
Interactive QA session where the user reports bugs or issues conversationally and the agent creates GitHub issues. Explores the codebase in the background for context and domain language. Use when the user wants to report a bug, run QA, submit issues conversationally, or mentions "QA session".
Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL alignment (DPO/RLVR/GRPO/RLHF), BYOB/MCQ benchmarks, checkpoint conversion, ModelOpt optimization, env profiles, and evaluation of trained checkpoints or existing/hosted endpoints. Use when a request names a Nemotron step or workflow, or asks to clean, translate, train, fine-tune, align, convert, optimize, evaluate, or compose these into a pipeline. Do NOT use for frontend/dashboard/visualization work, generic ML advice, billing/access, or non-Nemotron coding tasks.
Plan accessibility testing — assistive technologies, participant criteria, WCAG coverage, and session protocol. Use when scheduling testing with real AT users. Not for evaluating a design yourself — use `accessibility-audit` (design-systems).
Scan an iOS/macOS Xcode project for common App Store rejection patterns before submission. Use when preparing an app for App Store review, after receiving a rejection from Apple, or when auditing metadata, subscriptions, privacy manifests, entitlements, or design compliance. Integrates with the asc CLI for metadata inspection.
Use only when the user explicitly requests a review or audit of backend code under `api/`. Supports pending-change, file-focused, and pasted-diff reviews. Do not use for implementation-only requests, diagnosis without review intent, frontend code, or backend code outside `api/`.
Enhances Vitest with Midscene for AI-powered UI testing across Web (Playwright), Android (ADB), and iOS (WDA). Scaffolds new projects, converts existing projects, and creates, updates, debugs, and runs E2E tests using natural-language UI interactions. Triggers: write test, add test, create test, update test, fix test, debug test, run test, e2e test, midscene test, new project, convert project, init project, 写测试, 加测试, 创建测试, 更新测试, 修复测试, 调试测试, 运行测试, 新建工程, 转化工程.
Upgrade a vigiles spec's guidance() rules to enforce() — scan the guidance rules in a CLAUDE.md/AGENTS.md spec and find existing linter rules (ESLint, Ruff, Clippy, Pylint, RuboCop, Stylelint) that back them. Use when asked to strengthen, harden, or make vigiles rules enforceable; NOT for general linting or fixing lint errors.
Performs comprehensive Rust security reviews for safe/unsafe boundary issues, memory safety in unsafe blocks, concurrency hazards, panic-induced DoS, FFI safety, and async runtime mistakes. Use when auditing Rust crates, services, or libraries—particularly those with `unsafe`, FFI, or concurrent code.
Install vigiles and test a Claude Code harness — hooks, skills, agents, settings, CLAUDE.md — by picking the right tier (unit / deterministic / eval) and writing a test that passes. Use to check that a hook fires or blocks, that a skill triggers, that injected context lands; or to observe a run — which tools it called, whether it stayed inside its declared allowed-tools, what files and side effects it produced, how to intercept a call without executing it.
Review dependency PRs with structured research, existing-PR-discussion capture, multi-lens analysis (security, code quality, impact), and a repeatable verdict template. USE FOR: dependency update PRs, Renovate/Dependabot PRs, library upgrade reviews, "review this dependency PR", "should we merge this update". DO NOT USE FOR: feature PRs, application code reviews, dependency automation/bot configuration, or unattended merge without confirmation
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy
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.