1.1K skills · sorted by relevance
Learn how GPT language models work by preparing text, training a small model, and generating samples. Covers CPU experiments, custom datasets, further training of pretrained GPT-2 models, and reproducing GPT-2 with multiple GPUs.
Ask questions about your journal, Obsidian vault, or other text notes, and continue conversations that remember earlier chats. The companion uses cognee memory with local databases, reads your notes without changing them, and saves conversations for later reference.
Draft a reply to the newest Gmail inbox message using Granola meeting notes and past emails stored in cognee. Incorporates prior discussions, commitments, and writing style, then displays the draft without sending it.
Connect a company SQL database, support ticket exports, and documents in cognee, linking shared people, teams, and projects so questions about ownership, decisions, and ongoing work can draw on several sources together.
Guide development of custom Windows video applications with Zoom Video SDK and C++. Covers session setup, video display, screen sharing, and raw media access, meaning direct capture or injection of audio samples and video frames.
Build a workflow for importing large collections of audio, email, documents, or chats into knowledge pages. Test varied samples first, track progress in a persistent JSON file, and verify outputs before marking work complete.
Draft posts, replies, launch copy, or emails in a specific person's writing style using a validated profile and stored source material. Produce two or three checked options, or build and validate the profile first when needed.
Create Vitest tests for Mastra playground features using MSW to simulate network responses. Exercise the real client SDK, React Query cache, and components with typed sample data to check loading, access conditions, redirects, and errors.
Plan user research by matching methods to study goals and explaining participant numbers and confidence. Synthesize tagged observations into recurring findings, distinguish isolated anecdotes, and organize evidence so research results can be found and reused.
Route product questions to a specialist for prioritization, research, analytics, experiments, or implementation. Support recurring discovery by tracking interviews and assumption tests, checking how customer needs connect to proposed solutions, and returning results with a concise digest.
Check Agent Skills for documentation structure and Python script behavior, then score quality and security posture. Get grades and improvement priorities, and use pass criteria in pre-commit checks or continuous integration, which runs checks automatically.
Plan A/B tests that compare page variations, from headlines to pricing layouts. Define a hypothesis, choose success metrics, calculate sample size and duration, and prepare launch checks and results reports to support decisions.
Create unit test scaffolds, sample data, and mocks from code or specifications. Analyze coverage reports to prioritize missing tests, and guide test-driven development through failing tests, minimal implementation, and refactoring.
Build and improve Windows desktop apps with C#, WinUI 3, and the Windows App SDK. Guidance covers development setup, native interface design, implementation, troubleshooting, packaging choices, and verification through both builds and actual app launches.
Measure chat layout jumps while a response runs by tracking the Working line through CDP, a browser debugging connection. Count upward movements and compare the same prompt before and after changes to status lines, step rows, or folding behavior.
Analyze saved NemoClaw CI timings to rank consistently slow command-line tests and compare base-image publication with reuse. Read-only analyzers report execution times, runner queues, and sample coverage as bounded JSON output.
Generate Python code to clean, transform, analyze, visualize, and model BigQuery data with BigQuery DataFrames. The skill keeps processing in the cloud and uses familiar table operations, with guidance for previews, schema checks, and machine learning.
Add business knowledge missing from a Wren project's database definitions. Compare source documents with existing context, then add explanations, rules, SQL examples, and proposed metrics through guided questions or an automatic mode with an audit report.
Receive live Lark/Feishu updates for messages, approvals, tasks, meetings, and more. Stream them as NDJSON, one JSON record per line, with filtering and time or event limits for bots and automated event processing.
Supports analysis of tables already in the workspace through data inspection, Python calculations, and charts chosen for the question. It also explains how to ask users for clarification and label results with meaningful units and names.
Create and debug formulas for Excel and Google Sheets, including formulas that return multiple results. Get placement instructions, worked examples, checks for blanks and duplicates, and equivalent formulas when moving between platforms.
Run Scenic traffic scenarios on a CARLA server. First test whether a valid scene can be generated, then simulate with limits on runs and steps, record the outcome, and restore the world's asynchronous setting afterward.
Track machine learning experiments with SwanLab by recording training settings, metrics, and media such as images and audio. Learn to compare runs, inspect training charts, and connect existing training code to local, cloud, or self-hosted dashboards.
Evaluate language models on knowledge, math, coding, safety, and image understanding benchmarks. The skill guides reproducible runs in containers using local Docker, Slurm clusters, or cloud execution, with shared configurations for model comparison and result export.