Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Guides privacy-focused API design, data modeling, authentication, logging, retention, deletion, and infrastructure reviews. Covers personal data protections, exports, anonymization, and breach response, drawing on CNIL guidance and GDPR articles.
Fetches and annotates traces, spans, and sessions to investigate errors. Also inspects datasets, reviews experiments and annotation configurations, and accesses the GraphQL API.
Derives behavioral requirements from code and generates specification-linked functional tests. Combines three-pass code review, regression testing, and a multi-model specification audit into a consolidated bug report with TDD-verified patches.
Builds search-engine queries using domain, file type, URL, title, text, and date operators. Covers differences among major search engines and supports exposure audits, reconnaissance, leaked-document searches, and competitive or regulatory research.
Cover deep research, literature and systematic reviews, research questions, experiment planning, and research-to-paper workflows. Support drafts, abstracts, revisions, citation checks, integrity checks, peer review, and rebuttal audits.
Use Unicorn to emulate functions or code fragments without running a complete program. Supports execution tracing, decryption or decoding through emulated algorithms, and bypassing dependencies such as JNI, syscalls, and libc.
Shared Cosmos3 frontend that explicitly routes Cosmos Framework and Cosmos-RL, validates runtime model/video-dataset/SLURM inputs, consumes an SQSH or packaged backend image, optionally plans explicit clean source builds, prepares checkpoints, validates the first update in-process, and returns token-weighted losses and task-aware accuracy.
Supports node, link, and graph classification using message-passing models such as GCN, GAT, GraphSAGE, and GIN. Covers heterogeneous graphs, neighbor sampling, and custom datasets in torch_geometric.
Manipulates .pptx files through an MCP server. Supports slide creation, presentation formatting, placeholders, images, templates, and text extraction.
Supports video-text embeddings for text-to-video retrieval and video-to-video search. Covers Cosmos-Embed1 fine-tuning, inference, export, and semantic deduplication.
Creates concise profiles of public or private companies using S&P Capital IQ data through the Kensho LLM-ready API MCP server. Supports equity research, investment banking and M&A, corporate development, and sales or business development audiences.
Provides assistance with high-performance GPU kernels using cuTile's tile-based programming model. Includes validation, optimization, and deep agent orchestration for complex tasks involving multiple kernels.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name