全部能力

README 优先的 AI 仓库复现主编排器。当用户需要端到端、最小可信的复现流程，且该流程会读取仓库…

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from…

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting…

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from…

Tailwind CSS integration guide for React, Vue, Next.js, and other frameworks

Advanced Tauri event patterns for bidirectional communication, streaming data, window-to-window messaging, and custom event handling

Build high-performance VueJS user interfaces (SPA, PWA, SSR, Mobile and Desktop) in record time. ALWAYS use when writing code importing \"quasar\". Consult for…

Data analysis, visualization, and storytelling skill for financial and RevOps contexts. Use when: analyzing revenue data, building forecasts, cohort analysis, churn modeling, pipeline analytics, creating data-driven reports, building dashboards, cleaning messy data, sanity-checking analytical claims, exporting to Excel with formulas, or extracting data from PDFs. Features decision logging, bias-aware interpretation, and progressive disclosure (slide deck -> detailed report -> full notebook with all decisions documented).

Validates Conductor project artifacts for completeness,

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing…

Use when asking how to use Axiom, what skills are available, getting started with Axiom, capturing iOS simulator console output with xclog, or symbolicating…

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

Mobile app testing with unit tests, UI automation, performance testing. Use for test infrastructure, E2E tests, testing standards, or encountering test…

Apply when implementing fulfillment, invoice, or tracking logic for VTEX marketplace seller connectors. Covers the External Seller fulfillment protocol:…

Use when writing ANY test, debugging flaky tests, making tests faster, or choosing Swift Testing vs XCTest. Covers unit tests, UI tests, async testing, test…

cli-anything-drawio — an installable skill for AI agents, published by hkuds/cli-anything.

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible…

Generate images using Google's Gemini API — hero backgrounds, OG images, placeholder photos, textures, and style-matched variants. Uses free-tier models for…

Set up real-time indicator computation on live WebSocket market data. Streams LTP/Quote/Depth and computes indicators in real-time with optional Plotly live…

Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organization with…