1.1K skills · sorted by relevance
Set up reinforcement learning, training guided by response rewards, for large language models. Use Megatron-LM and SGLang to prepare data, configure training and response generation, and build asynchronous or multi-turn experiments.
Try a sample that invokes another skill from within a skill. Running its command triggers example-skill internally, providing a concrete test case for skill chaining in the bundled skills registry.
Create an HTML prototype of a social media analytics dashboard for creators. It uses consistent sample data to show platform metrics, follower growth, a top post, trending topics, and comments, with styling drawn from your design system.
Start using RuView by choosing a Docker demo, a source build, or a live ESP32 setup. The skill guides the next concrete step, distinguishing sample data playback from sensing an actual room with WiFi signals.
Create and run automated tests that score LLM answers against expected outputs or judging criteria. Monitor progress, inspect individual results, compare models on the same tests, and use score thresholds in CI, an automated checking workflow.
Manage how context, the text supplied to an AI, is compressed with RTK filters. Preview compression on real prompts, validate and install filter files, and inspect filter loading diagnostics.
Build a Claude Code mod, a plugin that extends behavior through event hooks, from ruflo’s template. Sets up function hooks with a classic fallback, user options, status reporting, validation, and tests.
Use DashScope to generate images, turn text into narration, and transcribe audio with timing for each word. The skill guides API setup and output handling for preparing video images, voice tracks, and subtitle material.
Generate Mandarin and multilingual narration with Volcengine Doubao Speech 2.0. Choose a voice and speaking speed, save the audio, and retain character-level timing metadata for subtitles in an OpenMontage workflow.
Generate narration, dialogue, sound effects, and music with ElevenLabs APIs for videos, podcasts, and games. The skill covers voice settings, pronunciation, pauses, voice cloning, and using measured audio lengths to synchronize scenes in Remotion, a video creation framework.
Verify documents, spreadsheets, presentations, and web deliverables before sharing them. Combine file checks with inspection of freshly rendered output, and scan for unfinished text to catch clipped content, layout problems, and leftover placeholders.
Draft or edit emails, messages, documents, and slides in the user's own voice. Use relevant writing samples to match the audience and medium while preserving the intended meaning, facts, and any wording that should stay.
Review synced Apple Health records, including steps, heart rate, sleep, and workouts. Retrieve daily summaries or detailed samples for a chosen period, and check sync status and missing data before interpreting the results.
Analyzes the user's own sent emails, messages, and documents to capture characteristic phrasing, sentence rhythm, and audience-based tone changes. It saves a personal writing profile as a skill for future drafts in the user's voice.
Prepare a repository for Claude Code on the web by creating a startup hook that installs project dependencies. Register the hook and check that it runs successfully, along with a sample test and code quality check.
Maintain visual snapshot tests, which compare rendered images, for Remotion’s web renderer. Update existing tests after implementation changes, or add explicitly requested tests with sample components, preview registration, and documentation updates for supported properties.
Edit prose that sounds AI-generated while preserving its meaning and the writer’s voice. Review repetitive structures, inflated claims, stock phrases, and unnecessary formatting, then rewrite naturally without inventing facts or losing supported information.
Clean messy tabular data through OpenRefine using command-line operations. Import files, inspect rows, apply reusable JSON transformation histories, and export cleaned CSV or TSV data, with session support for undoing and redoing changes.
Process 3D scan data with CloudCompare through text commands. Clean point clouds, collections of measured 3D points, extract ground surfaces, align scans, calculate distances, and convert or export point clouds and surface meshes in supported formats.
Work with genomic regions in Polars tables to find overlaps, nearby regions, covered bases, and gaps. Read and write bioinformatics files, query data with SQL, and check coordinate conventions when joining datasets or migrating from bioframe.
Analyze gene-expression differences in bulk RNA-seq data using PyDESeq2. Validate count tables and experimental designs, test explicit comparisons, adjust for multiple testing, shrink effect estimates, and export statistical results with volcano and MA plots.
Explore public pathogen genome data to verify lineage names, summarize weekly sequence proportions, examine reporting delays, and compare mutation frequencies. Results include filters and denominators, with clear limits on what submitted sequences reveal about infections.
Build, analyze, and visualize relationship data in Python with NetworkX. Find shortest routes, identify important nodes and groups, generate networks for simulations, and exchange graph data through tables and common file formats.
Prepare experiments for Ginkgo Cloud Lab by choosing a protocol, organizing required inputs, checking configured pricing, and navigating browser ordering. Covers protein expression, RNA synthesis, stability assays, and setup of measurement methods.