696 skills · sorted by relevance
Search more than 400 social networks and platforms for accounts using a given username. Receive organized links to matching pages for checking username availability or researching publicly available account information.
Find relevant guides and runnable workflows for genomics and computational biology through an index of over 400 skills. Retrieve references or scripts for tasks such as sequence quality checks, gene expression analysis, and reporting.
Track updates across blogs and RSS/Atom feeds, then manage unread articles in one place. Automatically discover feeds, import subscription lists, and filter articles by blog or category using blogwatcher-cli.
Investigate subdomains, SSL certificates, domain registration details, and DNS records with a Python helper. Run checks across multiple domains, estimate registration availability, and receive structured JSON results without additional packages or API keys.
Search local notes, documents, and meeting transcripts using keywords and meaning. Combine both methods and use local AI models to reorder results by relevance, then retrieve full documents or selected passages without cloud processing.
Evaluate large language models on shared tests of knowledge, reasoning, and code generation with lm-evaluation-harness. Save scores and individual predictions, compare models in tables, and track performance across saved stages of model training.
Set up and optimize large language model inference, or response generation, on NVIDIA GPUs. Use quantization, batch processing, and multiple GPUs to improve serving performance, and expose models through a chat completion API.
Search across multiple engines through SearXNG, a service that combines search results. Filter by category, date range, or engine, and get titles, links, and snippets. Public instances require no API key.
Let Hermes handle purchases through Stripe Link using one-time virtual cards or Shared Payment Tokens, credentials for supported paid APIs. Each spend requires your approval in the Link app before payment can proceed.
Test an authorized web application, map its exposed pages and inputs, and verify suspected vulnerabilities with reproducible evidence. Produce a security report covering confirmed findings, their impact, reproduction steps, and suggested fixes.
Prepare machine learning and AI research papers, from literature searches and experiment planning to analysis, drafting, and submission preparation. The workflow connects experiments to research claims and includes citation verification and revisions in response to reviews.
Publish websites and files on here.now and get a URL to share them. Store private documents and agent files in cloud Drives, with access limited to selected paths and a set duration when sharing.
Turn facts into question-and-answer cards and review them at intervals based on your answers. Create quizzes from YouTube transcripts, organize cards into collections, and import or export CSV files, with card data stored locally.
Set up services such as databases and SMS for a project through Stripe Projects. Sync generated credentials into `.env`, connect supported provider accounts, and manage credential rotation, plan changes, and service removal.
Cross-reference public records to investigate companies, contracts, sanctions, property, and litigation. Match names across sources, label confidence levels, and build structured findings linked to original records, with optional statistical analysis of event timing.
Monitor RSS feeds, JSON APIs, and GitHub activity at regular intervals. Included scripts track previously seen item IDs and output only new entries, letting an agent report updates while staying silent when nothing has changed.
Generate an interactive bash script that guides people through manual service setup. It opens relevant pages, explains what to click, collects credentials, and saves values to .env files or GitHub secrets with stage confirmations.
Modify and troubleshoot services managed by s6, a process supervisor, inside the Hermes Docker image. Trace startup scripts, inspect profile gateways, add static services, and investigate restart failures or file ownership problems.
Analyze and modify refusal behavior in open-weight language models without retraining. Use OBLITERATUS to select methods suited to available hardware, compare approaches, and evaluate changes in refusal rates and response quality.
Implement and debug large-model training with PyTorch FSDP, which splits training state across devices. Consult documentation and code patterns for sharding choices, mixed precision, and checkpoints when building or reviewing distributed training code.
Run machine learning training and predictions on cloud GPUs, then publish models as APIs that other applications can call. The skill guides Python-based setup, automatic scaling, persistent storage, parallel processing, and scheduled jobs.
Search Polymarket prediction markets, where prices express market estimates of event probabilities. Retrieve current prices, trading volume, buy and sell orders, and price history to examine expectations and market movements.
Classify images using written labels without additional training data, or find images that match a text query. This skill provides CLIP workflows for image-text similarity, batch processing, and storing searchable image representations in vector databases.
Have an agent join Google Meet, collect live captions, and use the transcript for summaries and follow-up tasks. An optional voice mode lets it speak during calls after additional audio setup.