Loading...
Loading...
Found 10,405 Skills
Creates isolated container environments for testing local uncommitted changes before pushing. Use when testing library changes, multi-repo coordination, or validating "works on my machine" → "works in CI". Provides git bundle snapshots, embedded git server, selective URL rewriting, and package manager cache isolation. Works with any coding agent via standalone CLI, shell scripts, or Docker Compose.
Use this skill for generating data-driven charts and visualizations using Python. Triggers: "create chart", "generate graph", "plot data", "visualize data", "bar chart", "line chart", "pie chart", "comparison chart", "positioning matrix", "trend chart", "market size chart", "TAM SAM SOM", "growth chart", "data visualization" Outputs: PNG/SVG chart images with accurate data representation. Used by: competitive-intel-agent, market-researcher-agent, pitch-deck-agent, review-analyst-agent
Autonomous ML experimentation framework by Andrej Karpathy. AI agent autonomously modifies train.py, runs 5-minute GPU experiments, evaluates with val_bpb, and commits only improvements via git ratcheting — so you wake up to 100+ experiments and a better model. Use when setting up autoresearch, writing program.md directives, interpreting results, configuring hardware, or running overnight autonomous ML experiments. Triggers on: autoresearch, autonomous ml experiments, overnight gpu experiments, karpathy autoresearch, train.py experiments, val_bpb, program.md research directives, ai runs experiments.
Instrument Python LLM apps, build golden datasets, write eval-based tests, run them, and root-cause failures — covering the full eval-driven development cycle. Make sure to use this skill whenever a user is developing, testing, QA-ing, evaluating, or benchmarking a Python project that calls an LLM, even if they don't say "evals" explicitly. Use for making sure an AI app works correctly, catching regressions after prompt changes, debugging why an agent started behaving differently, or validating output quality before shipping.
A comprehensive starting point for AI agents to work with the Ionic Framework. Covers core concepts, components, CLI, theming, layout, lifecycle, navigation, and framework-specific patterns for Angular, React, and Vue. Pair with the other Ionic skills in this collection for deeper topic-specific guidance like app creation, framework integration, and upgrades.
Guides the agent through general Ionic Framework development including core concepts, component reference, CLI usage, layout, theming, animations, gestures, development workflow, and troubleshooting. Covers all Ionic UI components grouped by category with properties, events, methods, slots, and CSS custom properties. Do not use for creating a new Ionic app (use ionic-app-creation), framework-specific patterns (use ionic-angular, ionic-react, ionic-vue), or upgrading Ionic versions (use ionic-app-upgrades).
Guides the agent through Angular-specific patterns for Ionic app development. Covers project structure, standalone vs NgModule architecture detection, Angular Router integration with Ionic navigation (tabs, side menu, modals), lazy loading, Ionic page lifecycle hooks, reactive forms with Ionic input components, Angular services for state management, route guards, performance optimization, and testing. Do not use for creating a new Ionic app from scratch, upgrading Ionic versions, general Ionic component usage unrelated to Angular, Capacitor plugin integration, or non-Angular frameworks (React, Vue).
Clayton Christensen's Disruption Analysis applied to a company, market, or business idea. Spawns a team of specialist agents — Disruption Cartographer, RPV Diagnostician, Jobs Archaeologist, Trajectory Analyst, Incumbent's Advocate — who each apply a distinct lens from Christensen's framework to evaluate disruption risk and opportunity. The lead synthesizes into a disruption verdict: is this company vulnerable to disruption from below, is this startup on a genuine disruption trajectory, or is this a sustaining innovation that incumbents will crush? Use when the user says "christensen this", "disruption analysis", "is this disruptive", "vulnerable to disruption", or wants to evaluate whether a company/market faces disruption risk. Works as a standalone analysis or paired with /munger for a complete picture.
Convert websites into LLM-ready data with Firecrawl API. Features: scrape, crawl, map, search, extract, agent (autonomous), batch operations, and change tracking. Handles JavaScript, anti-bot bypass, PDF/DOCX parsing, and branding extraction. Prevents 10 documented errors. Use when: scraping websites, crawling sites, web search + scrape, autonomous data gathering, monitoring content changes, extracting brand/design systems, or troubleshooting content not loading, JavaScript rendering, bot detection, v2 migration, job status errors, DNS resolution, or stealth mode pricing.
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
Build with Claude Messages API using structured outputs for guaranteed JSON schema validation. Covers prompt caching (90% savings), streaming SSE, tool use, and model deprecations. Prevents 16 documented errors. Use when: building chatbots/agents, troubleshooting rate_limit_error, prompt caching issues, streaming SSE parsing errors, MCP timeout issues, or structured output hallucinations.
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.