Skill rating

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, N

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture fro

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNe

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of arc

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 fo

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systemati

PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melod

Audit a codebase and bind every claim it makes about itself to a mechanism that fails when the claim stops being true, so it is legible to people and AI agents. Applies Context Architecture's nine pri

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or

Use when the user asks to generate images via the Luma AI API (Dream Machine / Photon); collects a prompt and options interactively, then calls the API using the bundled script. Requires LUMA_API_KEY

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management,

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal a

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deployin

Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message ano

Generate patent-office-compliant figures via the PatentFig AI API — patent line art from text (PNG or SVG), vectorize drawings to SVG/DXF/vector PDF, AI-upscale images, and convert to filing-ready TIF

Optimize LLM prompt caching hit rate to reduce API costs and improve latency. Analyzes prompt structure, identifies cacheable vs non-cacheable content, and recommends restructuring to maximize cache r

Supermemory is a state-of-the-art memory and context infrastructure for AI agents. Use this skill when building applications that need persistent memory, user personalization, long-term context retent

Show what happened in recent past sessions on this project as a clean timeline. Use when the user asks "what did we do last time", "session history", "past sessions", or wants an overview of previous

Trace a file, function, or line back to the agent session that produced its current commit. Use when the user asks "why is this code here", "what was the agent doing when this changed", "who wrote thi

List recent git commits linked to agent sessions, optionally filtered by branch or repo. Use when the user asks "show agent commits", "what has the agent shipped", "list linked commits", or wants comm

Save an insight, decision, or learning to agentmemory's long-term storage with searchable concept tags. Use when the user says "remember this", "save this", "note that", "don't forget", or wants to pr

Resume the most recent agent session for the current working directory, leading with any unanswered question. Use when the user says "where were we", "resume", "handoff", "pick up where I left off", o

Delete selected durable memories from agentmemory after showing them and getting explicit confirmation. Use when the user says "forget this", "delete memory", "remove that note", or wants to scrub spe

Search agentmemory for past observations, sessions, and learnings about a topic using hybrid BM25 plus vector plus graph search. Use when the user says "recall", "what did we do about", "did we ever",

Summarize the last N agent sessions for the current project, grouped by date, with highlight observations per session. Use when the user asks "recap", "what have we been doing", "today", "this week",

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This sk

Use after a Codex or Claude Code feature has been implemented in Qwen Code to run the selected reference agent and Qwen Code under the same scenario, capture HTTP and terminal traces, compare request

Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real mode

Breaks one epic into implementable stories with acceptance criteria. Use when the user wants stories for an epic or the next batch of work to build. Not for turning the whole design into epics.

Turns the GDDs and architecture into epics, one per architectural module. Use when the user wants to break the game into epics or plan the work before writing stories. Not for splitting one epic into

Manages the end-to-end lifecycle of on-demand, temporary access using Privileged Access Manager (PAM). Use when a user asks to create, read, update, or delete PAM entitlements, request temporary acces

Provides safety-critical validation, guardrails, and data reduction for gcloud CLI operations across Google Cloud Platform (GCP) services and infrastructure. Use when planning, generating, constructin

Configures best-practice alerting policies for AI agents using OpenTelemetry (OTel) metrics, generating output as Terraform (.tf) configuration files. Use when analyzing, writing, or deploying alertin

Interact with the Gemini Enterprise Agent Platform Skill Registry to create and search for available skills. Use this skill to enable agents to register functionality or discover new capabilities.

Manages custom Agent resources on Gemini Enterprise Agent Platform. Use when the user wants to programmatically create, configure, list, update, or delete stateful, server-managed Agent resources (inc

Generates a Gemini LiveAPI client service class in the user's chosen programming language. Use when the user wants to build, scaffold, or integrate a client that connects to the Gemini Enterprise Live

Manage Google Security Operations (SecOps) SOAR cases throughout their lifecycle. Use when listing, creating, inspecting, updating, or closing SOAR cases; adding investigative comments and notes; upda

Spin up a single agent as an advisor — second opinion on the current task. Use when the user says "advisor", "second opinion", "what does X think", or wants an outside take without delegating the work

Hand off the current task to another agent with full context. Use when the user says "handoff", "hand off", "hand this to", or wants to pass work to another agent.

Query curated cybersecurity market and company intelligence. USE WHEN security market data OR cybersecurity funding OR cyber M&A OR security-company/investor research OR market maps OR deal activity O

Audit technical SEO across crawlability, indexability, security, URLs, mobile, Core Web Vitals, rendering, structured data, and IndexNow. Use when the user asks for a technical SEO audit or about craw

Audit and fix agent readiness: the Lighthouse Agentic Browsing fraction, accessibility tree for agents, robots.txt and Content-Signal for AI agents, WAF treatment of agent traffic, llms.txt, Markdown

Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.

Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.

Install guardrails as code so AI sessions cannot reintroduce leaked secrets, injection, or untested code. Use when "set up guardrails", "stop vibe-coding regressions", or "add pre-commit security chec

Plan-only audit of an LLM app's runaway-cost and quota-abuse exposure. Use when "cap my AI costs", "my LLM bill could blow up", "rate limit my AI", "token budget", "runaway agent loop", or hardening L

Conversion pass for landing, pricing, and upgrade paths: positioned hero, one CTA, real proof, anchored tiers, upgrade prompts at value moments. Use when "pricing page", "improve conversion", or "payw

Plan-only audit of answer-engine (AEO/GEO) citation readiness for ChatGPT, Perplexity, and AI Overviews. Use when "AEO", "GEO", "show up in ChatGPT/Perplexity", "AI search visibility", "llms.txt", or