Menu
Skills in this repository
SkillsMP has collected 1,566 skills from yanacuti1121/Yana-AI. Open a skill to review its source and details.
yanacuti1121/Yana-AIShowing 40 of 1,566 collected skills.
Fix accessibility issues hands-on — focus management, keyboard traps, missing ARIA labels, skip links, color contrast failures, interactive element sizing, and screen reader announcements. Use when asked to "fix accessibility issues", "keyboard navigation…
Fix animation jank and layout thrashing — compositor-only properties, will-change hints, avoiding layout-triggering CSS, GPU layer promotion, requestAnimationFrame usage, reduced-motion support, and auditing with DevTools Performance panel. Use when asked to…
Build streaming and generative UI with Vercel AI SDK — useChat, useCompletion, streamText, streamUI, tool calling in the UI layer, loading states for streaming, error boundaries, and AI-native component patterns. Use when asked about "Vercel AI SDK",…
Coordinate multiple AI agents using Git as the shared protocol — issues as task queues, branches as agent workspaces, PRs as deliverables, and commit messages as structured agent signals. Use when asked about "GNAP", "git native agent", "agents coordinating…
Eliminate generic-looking UI — anti-default checklist, custom hover states, precision typography, non-stock spacing, surface depth, and production-grade polish that separates professional from template. Use when asked to "make this look less generic", "UI…
Make interfaces feel responsive and alive — micro-interactions, spring physics, press states, optimistic updates, skeleton loaders, cursor feedback, sound design hints, and delight moments. Use when asked to "make this feel better", "interface feels…
Minimize token cost and latency with Anthropic prompt caching — cache breakpoints, static vs dynamic block separation, skills snapshot pre-computation, context invalidation strategy, and 90% cost reduction patterns for repeated system content. Use when asked…
Build cognitive security firewalls against prompt injection, jailbreak attacks, and Unicode homoglyph smuggling. Instruction-data segregation, jailbreak token filtering, LLM-as-a-Judge semantic guard, and system prompt reinforcement.
Diagnose and fix React component health issues — unnecessary re-renders, missing keys, stale closures, useEffect misuse, memory leaks, bundle size regressions, and dangerouslySetInnerHTML XSS risks. Use when asked to "React performance audit", "why does this…
Autonomous multi-source research agent group. Given an unknown bug or technology topic, research-team spawns parallel sub-agents to search StackOverflow, GitHub Issues, official docs, and changelogs. Synthesizes findings into a ranked solution report.…
Build and customize UI components with shadcn/ui — component installation, CSS variable theming, Radix UI primitive composition, variant patterns with cva(), dark mode wiring, and extending components without forking. Use when asked about "shadcn",…
Secure the software supply chain — SBOM generation, dependency provenance verification, package integrity (Sigstore/npm provenance), lockfile auditing, typosquatting detection, CI artifact signing, and dependency update policy. Use when asked about "SBOM",…
Multi-path reasoning before acting. Agent generates 3 candidate solutions, self-scores each on correctness/token-cost/safety, selects the best branch, and backtracks if it hits a dead end. Use before /deep-heal or any complex fix. Inspired by…
Apply zero-trust architecture to services — mTLS with SPIFFE/SPIRE, per-request authentication, short-lived credentials, least-privilege service accounts, network policy enforcement, and audit logging every access decision. Use when asked about "zero trust",…
Build production AI agents with Agno (formerly Phidata) — define Agent with model/tools/instructions/memory/knowledge, compose Agent Teams with coordinator routing, add Storage for persistence, and integrate RAG via built-in KnowledgeBase with PDF/URL/text…
Write production-safe code that survives maintenance — avoid the 15 patterns AI agents commonly generate that work on day 1 but break 3 months later; enforce error handling, logging, type safety, no magic values, and testable structure before writing any code.
REST API design — versioning, pagination, error responses, idempotency, rate limiting, OpenAPI spec
Build conversational multi-agent systems with AutoGen (AG2) — define AssistantAgent and UserProxyAgent, set up GroupChat with GroupChatManager for round-robin or auto routing, enable code execution, and compose nested chats or sequential pipelines.
Use when an AI agent needs to control a browser, automate web tasks, scrape pages, fill forms, or click buttons autonomously. Triggers on: 'browser automation', 'web agent', 'browser-use', 'AI browse', 'tự động duyệt web', 'điều khiển trình duyệt', 'scrape…
Systematic code review checklist — correctness, security, performance, maintainability, AI-specific anti-patterns
Crawl and extract web content for AI with Crawl4AI — async browser-based crawling with clean Markdown output, CSS/XPath/LLM extraction strategies, chunking, screenshot capture, session reuse for SPAs, and Docker deployment.
Build multi-agent pipelines with CrewAI — define Agents with roles/goals/backstory, assemble them into a Crew, assign Tasks sequentially or in parallel, and wire LLM + tools per agent.
DeepEval — LLM evaluation framework, RAG metrics, hallucination detection, red-teaming, CI/CD integration
Program LM pipelines with DSPy — define Signatures (input/output fields), build Modules (ChainOfThought, ReAct, Predict), compose them into Programs, then optimize with Teleprompters (BootstrapFewShot, MIPRO, COPRO) to auto-improve prompts from examples.
Production error handling — typed errors, Result type, error boundaries, structured logging, retry strategies
Scrape and crawl websites for AI with Firecrawl — scrape single URLs to clean Markdown/HTML, crawl entire sites with depth/path filters, extract structured data with LLM schema, use map to discover all URLs, and batch scrape multiple pages in parallel.
Use when extracting structured data (JSON, typed objects) from LLM responses with validation and retries. Triggers on: 'instructor', 'structured output', 'extract JSON from LLM', 'pydantic llm', 'LLM return JSON', 'trích xuất dữ liệu từ LLM', 'LLM trả về…
Source text: Mixed languages
LLM observability with Langfuse — tracing, evals, prompt management, cost tracking
Use when building stateful multi-step agents, agent graphs, or workflows with LLMs. Triggers on: 'langgraph', 'state graph', 'stateful agent', 'agent workflow', 'agent loop', 'multi-step agent', 'persistent agent', 'human-in-the-loop agent', 'agent with…
Call 100+ LLMs through a single OpenAI-compatible interface with LiteLLM — use completion/acompletion/embedding with any provider (Anthropic, OpenAI, Google, Groq, Ollama, etc.), run a proxy server for team rate-limiting and cost tracking, load-balance across…
Use when fine-tuning, training, or doing LoRA/QLoRA on LLMs. Triggers on: 'fine-tune LLM', 'LoRA', 'QLoRA', 'llamafactory', 'llama factory', 'train model', 'SFT', 'RLHF', 'DPO', 'fine tuning', 'custom model', 'instruction tuning', 'finetuning'.
Source text: Mixed languages
Production logging — structlog, structured JSON logs, correlation IDs, log levels, OpenTelemetry traces, no print()
Add persistent, intelligent memory to AI agents with Mem0 — add/search/update/delete memories per user/agent/session, supports vector + graph + key-value storage, integrates with LangChain, CrewAI, OpenAI Assistants, and any LLM.
Deploy AI workloads to serverless GPU/CPU with Modal — define @app.function with GPU/memory specs, build custom container images, run batch jobs and web endpoints, schedule cron tasks, and use distributed volumes for model caching.
Use when setting up workflow automation, connecting APIs, building AI pipelines, or automating repetitive tasks with 400+ integrations. Triggers on: 'n8n', 'workflow automation', 'tự động hóa', 'kết nối API', 'no-code automation', 'zapier alternative',…
Source text: Mixed languages
Outlines — structured generation with guaranteed JSON/regex output from local LLMs
Profile and optimize Python/Node.js — cProfile, py-spy, clinic.js, memory profiling, async bottlenecks, DB query analysis
Use when asked to create or generate a video automatically from a topic, text, or idea. Triggers on: 'tạo video', 'generate video', 'make a video about', 'video từ chủ đề', 'short video', 'create reel', 'pixelle', 'video tự động', 'video AI'. Requires…
Source text: Vietnamese
Portkey AI gateway — unified LLM API, load balancing, fallbacks, caching, guardrails, observability
Build type-safe AI agents with PydanticAI — define Agent with result_type, system_prompt, tools (function tools + structured tools), deps injection, and run sync/async with full Pydantic validation on inputs and outputs.