369 skills · sorted by relevance
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.
The English summary is being prepared. Showing the original description.
Prevent token balances and values from being scaled incorrectly across EVM blockchains. Look up each token's decimal places at runtime, cache them by chain and address, and use precise arithmetic with consistent units.
Create monitoring dashboards for Grafana, SigNoz, and similar platforms. Choose metrics around operational questions, organize panels by purpose, and define clear titles, units, filters, and thresholds to help operators assess health and bottlenecks.
Prepare text for language models by splitting it into tokens, small units represented by numbers. The skill covers batch processing, training custom vocabularies, tracking positions in the original text, and adjusting input lengths.
Manage files in Box, organize folders, share content, and search documents or metadata. Use Box AI to summarize files, answer questions, and extract information, with guidance for bulk processing and building applications connected to Box.
Inspect AI costs, token usage—the units used to measure model input and output—and call logs from the OmniRoute command line. Filter records, review spending by connection, and export usage reports for further review.
Estimate the cost per million tokens, units of model text, on hardware you own using power consumption, electricity rates, hardware costs, and measured generation speed. Compare utilization levels to find when local operation costs less than a hosted model.
Work with large scientific arrays by storing data in smaller blocks and reading selected portions. Guides compression, cloud storage, format migration, and NumPy, Dask, or Xarray integration while preserving dimensions, units, and other metadata.
Simulate quantum dynamics, steady states, and spectra with QuTiP 5. The skill guides solver selection and checks physical assumptions, units, state validity, and numerical convergence so local simulation results can be reviewed with their limitations.
Plan experiments before collecting data. Helps choose study designs, randomly assign subjects or samples, organize treatment combinations, and generate reproducible schedules while checking for confounding and repeated measurements incorrectly counted as independent samples.
Review and improve statistical reporting in manuscript methods, results, and figure captions. It checks sample definitions, repeated measurements, tests, and uncertainty, then provides revised wording and identifies missing information or issues reviewers may raise.
Build Java applications that store, query, update, and delete data in Azure Cosmos DB. Covers synchronous and asynchronous clients, partition keys for distributing data, consistency settings, request usage, and error handling.
Use Python to analyze astronomical data, convert celestial coordinates, units, and times, and read or write FITS astronomy files. It also guides catalog matching and calculations of cosmic distances and ages using cosmological models.
Build concurrent Go applications with goroutines, lightweight execution units, and channels for communication. Apply patterns for worker pools, cancellation, synchronization, and orderly shutdown, and investigate race conditions when concurrent operations access shared data.
Consult a field reference for slide JSON, the structured data behind each page. It explains where content and styling live, how edits are validated, and why a saved change may display differently or have no visible effect.
Split a large goal into clearly bounded tasks that can run in parallel. Coordinate existing agent and worktree tools, then combine and verify the results. The skill starts only when explicitly requested.
Create and fix Adobe Illustrator automation scripts using ExtendScript, Adobe’s JavaScript-based scripting language. Automate changes to artwork, text, layers, and artboards, process multiple files, and prepare exports such as PDF, SVG, and PNG.
Rewrite lengthy prompts, tool descriptions, and agent instructions into compact text while preserving requirements, exceptions, and exact values. The process records removed content and compares token counts, the units models use to measure text length.
Use Wireshark and tshark to capture and inspect network packets, the small units of network communication. Investigate suspicious connections and protocol problems, extract transferred files, and export evidence and summaries for incident investigations.
Design pricing and subscription plans around customer value and willingness to pay. The skill guides pricing surveys, billing units, feature bundles, free plans, trials, and price increases, helping organize options and define how to evaluate changes.
Prepare text for language models using HuggingFace Tokenizers, which splits text into model-readable units. Train custom vocabularies, process batches, track original text positions, and configure input lengths for use with transformers.
Build text tokenizers that split multilingual text into small units for AI models. Learn how to train SentencePiece on raw text, configure BPE or Unigram splitting methods, and convert text to token IDs and back.
Analyze CSV files with Python and get concise numerical summaries. The skill checks column structure before calculating requested aggregates, includes units when available, and explains assumptions when data is missing or incorrectly formatted.
Explore local or remote repositories with Repomix CLI to understand their structure, locate related code across files, and review file counts and estimated tokens, the units AI models use to process text.