全部能力

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use…

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model…

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or…

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M…

Use when the user wants to review a pull request, understand what a PR changes, assess risk of merging, or check for missing test coverage. Examples: \"Review…

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run…

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding…

Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides…

Professional PDF solution. Create PDFs using HTML+Paged.js (academic papers, reports, documents). Process existing PDFs using Python (read, extract, merge,…

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval…

Summarize deep research results into markdown report, cover all fields, skip uncertain values.

Conduct technical research on technologies and architecture. Use when the user says they would like to do or produce a technical research report

Screen incoming NDAs and classify them as GREEN (standard), YELLOW (needs review), or RED (significant issues). Use when a new NDA comes in from sales or…

Generate templated responses for common legal inquiries and identify when situations require individualized attention. Use when responding to routine legal…

Use immediately for any pasted OpenClaw GitHub issue or PR URL/number, and for OpenClaw issue/PR review, triage, duplicate search, opener identity/who wrote…

Robust URL-to-Markdown extraction for OpenClaw workflows. Use when the user wants to "extract/summarize/convert a webpage to markdown" (especially WeChat…

Generate OpenAPI documentation from source code. Analyzes repository to automatically discover API endpoints and create swagger.json and interactive HTML…

将学术论文转化为深度技术文章，支持多种写作风格选择。 使用 MinerU Cloud API 高精度解析 PDF，自动提取图片、表格、公式。 可选公式讲解、GitHub 代码分析，生成 Markdown 和 HTML 格式。

Builds interactive HTML presentation from project docs with Mermaid diagrams. Use when sharing project overview with stakeholders.

Explore-lane code adaptation skill for deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated…