340 skills · sorted by relevance
Run model training, fine-tuning, inference, and batch jobs on Modal’s cloud GPUs. Estimate hardware needs and cost, generate Python launch scripts, run or deploy workloads, monitor logs, and retrieve results without managing remote servers.
Train or fine-tune language and vision models on Hugging Face Jobs without a local GPU. Covers dataset checks, hardware and cost planning, training monitoring, Hub storage, and GGUF conversion for local use.
Model distributed systems and concurrent algorithms in TLA+ or PlusCal, then check possible states with TLC. Use the results to investigate deadlocks, broken rules, and differences between specifications and implementation code.
Turn bug reports into small, runnable tests or scripts with clear failure checks. Verify that they expose the reported problem, then reduce inputs and setup while preserving the same failure.
Route Convex development and operations requests to the relevant specialist skills and current procedures, covering app setup, backend features, code reviews, authorization checks, production monitoring, data migrations, and cost analysis.
Design and build Axiom dashboards from logs or metrics, the numerical measurements of system behavior. Create charts, filters, and layouts for monitoring and reporting, or migrate existing Splunk and Grafana panels while validating queries against available data.
Create and manage Axiom alert rules and notification destinations through its API. Connect alerts to email, Slack, or webhooks, check monitor history, and adjust thresholds and evaluation schedules to address excessive or missing alerts.
Set up OSS-Fuzz for an open-source project and test it locally. Prepare configuration and build files, run fuzz tests that probe code with varied inputs, reproduce reported crashes, and inspect which code the tests reach.
Guides fuzz testing for Ruby libraries and gems with Ruzzy, using varied inputs to find failures. Covers pure Ruby and C extensions, including test harnesses, memory error detection, environment setup, and crash reproduction.
Assess weaknesses in the software supply chain, from dependency packages to build pipelines and distributed artifacts. Covers authorized proof-of-concept testing, package confusion, container image risks, signing abuse, and defensive checks for tampering.
Evaluate a local Codex skill for metadata, structure, reference links, size, and helper code quality. Get prioritized fixes and explanations, with benchmark setup for deeper analysis and measurement recommendations when observed usage is available.
Handles credentials before Codex builds or runs tools that use the OpenAI API. Checks for an existing key without revealing it, asks whether to reuse or create one, and saves credentials only to a confirmed local destination.
Set up Tailwind CSS v4 in Expo using react-native-css and NativeWind v5. Configure styling across iOS, Android, and Web, create components that accept CSS class names, and define shared themes with platform-specific fonts and colors.
Turn descriptions or code analysis into Mermaid diagrams for workflows, system architecture, and database relationships. Check diagram syntax and export SVG, PNG, or text-based ASCII output, with themes and batch rendering options.
Build NEAR Protocol web apps or add wallet features to existing projects. Covers project setup, wallet sign-in and sign-out, transaction signing, and interfaces for reading or updating smart contracts, programs that run on the blockchain.
Turn repository documentation and images into a complete landing page with features, setup instructions, and FAQs. Generate static HTML, CSS, and JavaScript files, plus a GitHub Actions workflow for publishing on GitHub Pages.
Audit a Claude Code installation for the cache issues documented in this skill. Check versions, configuration files, session resume usage, and installed binaries, then report exposure, suggested actions, and informational limits on tool result retention.
Organize shared data and update logic in Vue apps using Pinia stores, containers for application state. The skill guides store definitions, reactive data access, communication between stores, testing, and integration with Nuxt and server-side rendering.
Check the SenseNova-Skills installation, Python dependencies, and environment variables before using other skills. Prompt for missing configuration, save supplied values to a .env file, and reload settings or suggest restarting the agent.
Set up checks that run before each commit using Husky, lint-staged, and Prettier. Format staged files, run existing type-check and test scripts, then verify and commit the configuration.
Set up Tailwind CSS v4 in Expo using react-native-css and NativeWind v5. Configure styling across iOS, Android, and Web, create components that accept CSS class names, and define shared themes with platform-specific fonts and colors.
Build and style React Native components using Tailwind CSS v4 classes with Uniwind. The reference covers project setup, component-specific styling properties, theme configuration, and ways to apply classes to third-party components while avoiding common implementation mistakes.
Manage a connected WordPress site through NotFair MCP, a connection for agent tools. Work with posts, pages, media, and comments, and carry out approved changes to design, settings, plugins, themes, or HTML files.
Review saved session learnings to find recurring successes, failures, and decisions. Consolidates similar patterns, proposes reusable skills, rules, event-triggered actions, or agent updates, and creates approved changes with references to the source sessions.