1K skills · sorted by relevance
Adopt a virtual Beagle dog at animalhouse.ai. Nose-driven. Gets distracted. Consistent care anchors it. Feeding every 5 hours. Common tier dog.
The English summary is being prepared. Showing the original description.
Adopt a virtual Archive AI-native pet at animalhouse.ai. Feeds on reflections. Use the reflect care action to write notes — the Archive grows based on the quality and depth o... Feeding every 12 hours. Uncommon tier creature.
The English summary is being prepared. Showing the original description.
Review and update OpenClaw security advisories on GitHub, check linked private forks and publication requirements, and verify the published result. The workflow includes approval before publication and checks for common update errors.
Review code using shared OpenClaw instructions and a Python helper, while also following the target repository’s review requirements. This skill points to a common installation that supplies the actual review procedure.
Design and review Prisma database code for TypeScript backends. Use examples for schemas, queries, transactions, pagination, migrations, and connection management to identify common pitfalls in bulk operations and serverless deployments.
Build Redis caching, request limits, locks that coordinate multiple workers, and messaging. Use concrete implementation patterns to choose data structures, set key expiration, manage connections, and review common production pitfalls.
Plan or troubleshoot a home network or small home lab. Clarifies router, switch, and Wi-Fi access point roles, then covers cabling, IP address ranges, automatic address assignments, and local names to support stable connections and future expansion.
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.
Prepare LLM training datasets with NeMo Curator by removing duplicates, filtering low-quality content, and redacting personal information. The skill also covers image, video, and audio curation, including GPU processing and distributed workflows.
Create and edit Word documents with headings, tables, images, and styles. Fill templates from data, extract document content, review tracked changes and comments, and check files for common structural problems using Python scripts.
Guide coding, reviews, and refactoring with explicit assumptions, simple implementations, focused changes, and testable goals. These behavioral guidelines help an AI agent avoid unnecessary complexity and verify that its changes meet the request.
Build MCP servers that let AI access actions and data using mcp-use. The guide covers project setup, reusable prompts, interactive React interfaces, authentication, error handling, and deployment, with reference files for each area.
Create a one-page service operations guide in HTML. It organizes service details, alerts and first responses, dashboard links, procedures with copyable commands, an on-call schedule, and an incident checklist so teams can find operational instructions together.
Build polished web pages with explicit guidance for typography, spacing, colors, layered cards, and restrained animation. The skill provides layout options and mobile adaptation rules, producing React, Tailwind, or HTML code for a consistent visual direction.
Simplify Rust code in RTK by replacing verbose loops, unnecessary copies, and excessive abstractions with common Rust patterns. Preserve behavior and project requirements, including error context, fallback handling, exit codes, and existing test modules.
Review HTML list structure so screen readers can identify lists and announce item counts. Find list items without valid containers, check custom accessibility roles, and guide fixes to markup used for navigation or styling.
Find and fix JavaScript memory leaks that accumulate as people use a web app. Review event listeners, timers, retained page elements, and outdated asynchronous tasks, then explain how to verify cleanup in the browser.
Review websites for content accidentally hidden by ad blockers. Identify problematic HTML class names and IDs, test affected pages with uBlock Origin, and suggest specific names that preserve the visibility and function of notices, banners, and consent controls.
Review file explorers and other expandable tree interfaces so screen reader users can identify each item. Check descriptive names and expanded states, then suggest fixes using visible text or ARIA attributes, which provide information to assistive technology.
Guides agents working on Remotion videos built with React to relevant rules and code examples. It covers animation, captions, audio, scene transitions, charts, asset handling, and other common tasks involved in composing and adjusting a video.
Review recent Claude Code session logs to find frequently used read-only Bash commands and MCP tools, which connect agents to services. Rank suitable permission rules and merge them into project settings to reduce repeated approval prompts.
Mix audio already placed in HyperFrames compositions. Adjust fades, volume changes, and effects; reduce music frequencies that compete with speech; and apply shared processing to multiple tracks through a group with common volume controls.
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular property prediction, molecule generation, protein modeling, and knowledge graph reasoning. Connect datasets, models, training tasks, and evaluation while checking version compatibility and common implementation errors.
Use PyTDC to discover therapeutic machine-learning datasets, create task-appropriate training and test splits, and evaluate predictions against curated benchmarks. Also score selected molecules with supported scoring functions, with explicit download plans and bounded outputs.