770 skills · sorted by relevance
Guides language model training with GRPO in TRL, comparing several responses and rewarding better results. Covers dataset preparation, scoring rules for correctness and format, training configuration, monitoring, and saving models for later use.
Build image generation workflows in Python with Stable Diffusion and HuggingFace Diffusers. The guide covers text prompts, transforming existing images, replacing selected regions, controlling composition, applying learned styles, and adjusting memory use during generation.
Create and refine Jupyter notebooks for experiments, exploratory analysis, or tutorials. Bundled templates help organize runnable code and short explanations into clear steps, while validation guidance supports notebooks that others can read and rerun.
Build end-to-end tests that follow user journeys in browsers and mobile simulators or emulators. Guides e2e configuration, AI-driven actions, precise outcome checks, failure investigation, and exploratory bug hunts backed by reproducible tests.
Write and debug code for further training large language models with TRL. Match training methods to dataset formats, configure supervised or preference-based training, and set up reward functions through Python or the command line.
Explore computer architecture and circuit design settings by repeatedly running programs, measuring results, and adjusting parameters. Compare configurations against a baseline, respect design constraints, and receive a report with the best configuration found and the search history.
Explore hardware and electronic design configurations by repeatedly running programs, measuring results, and adjusting parameters. Track constraints and every trial, then report the best configuration found within the time and iteration limits.
Turn data exploration findings into one Markdown report with embedded charts and tables. Adapt the structure for a short summary, blog post, executive briefing, KPI overview, or detailed analysis while checking supporting data.
Build image generation workflows in Python with Stable Diffusion and HuggingFace Diffusers. The guide covers text prompts, transforming existing images, replacing selected regions, controlling composition, applying learned styles, and adjusting memory use during generation.
Turn papers, code, experiment logs, and notes into an ARA, a structured research package for AI agents. Organizes claims, evidence, verification plans, code stubs, and research decisions, then checks coverage and consistency across the generated files.
Write and debug code for further training large language models with TRL. Match training methods to dataset formats, configure supervised or preference-based training, and set up reward functions through Python or the command line.
Route requests for idea exploration, rough planning, time-boxed technical investigation, phase specifications, or thought capture to the appropriate GSD skill. It selects and invokes a skill based on the intended task.
Coordinate temporary agents for code exploration, independent implementation tasks, verification, reviews, or complex debugging. Define self-contained assignments, run independent work in parallel, and check returned evidence before combining the results.
Route product design requests to focused skills for user research, experience reviews, visual exploration, prototype building, or sharing. This entry point selects the appropriate workflow rather than performing the design work itself.
Explore how a website provides data or handles actions, then turn verified methods into a reusable Skill package with SKILL.md and Python scripts. The workflow includes testing, installation, and execution when requested.
Inspect scientific data files to understand their format, structure, and quality. Covering over 200 formats, this skill produces Markdown reports with statistical summaries, potential issues, and recommendations for preprocessing, visualization, and further analysis.
Draft replies to a single LinkedIn comment or relevant comments across a post. Review conversation context, see which comments were skipped and why, then approve suggested reactions and replies for publishing.
Style documents and other visual artifacts using Anthropic's brand colors and typography. Applies distinct heading and body fonts, selects text colors for the background, and assigns accent colors to shapes, with fallback fonts when needed.
Explore scientific data files to understand their structure, statistical patterns, and quality. References cover over 200 formats, with workflows for producing Markdown reports that summarize findings and recommend preprocessing, visualizations, and further analysis.
Choose LLM settings for theorem proving, code generation, and creative exploration. It provides examples for output limits and response variety, plus proof planning prompts and a method for generating multiple proof attempts and selecting the best candidate.
Explore scientific data across more than 200 file formats to understand its structure, contents, and quality. Produce Markdown reports with statistical summaries, format-specific findings, and recommendations for preprocessing, visualization, and further analysis.
Create and refine Jupyter notebooks for experiments, exploratory analysis, or tutorials. Bundled templates help organize runnable code and short explanations into clear steps, while validation guidance supports notebooks that others can read and rerun.
Create charts from existing CSV files, tables, or query results to show trends, distributions, comparisons, and relationships. The skill guides chart selection and axis choices for everyday analysis, presentation slides, and simple dashboards.
Test changed screens or explore an entire app in a real browser. Check interactions, accessibility, and mobile layouts, then document failures with screenshots, reproduction steps, expected results, and suggested fixes.