Daniel Avila

Reduce LLM weight usage through pruning, which removes selected model parameters. Explore Wanda and SparseGPT for compression without retraining, choose hardware-friendly patterns for faster inference, and compare the compressed model's accuracy with the original.

中文简介正在准备中。当前显示英语简介。

• Compressing an LLM without retraining
• Comparing pruning methods
• Exploring faster inference on supported hardware

Design autonomous AI agents that break goals into tasks, use tools, and review their own work. Covers reasoning and action loops, separate planning and execution, and reliability measures such as cost limits, validation, and logging.

中文简介正在准备中。当前显示英语简介。

• Choosing how an agent plans and executes tasks
• Breaking goals into constrained steps
• Adding self-review and correction to an agent

Build LlamaIndex applications that retrieve relevant material before generating answers, a method called RAG. Connect documents, websites, and databases to support document questions, conversational search, structured summaries, and checks of answer relevance and source consistency.

中文简介正在准备中。当前显示英语简介。

• Building question answering over internal documents
• Creating a chatbot that remembers the conversation
• Searching information across files, websites, and databases

Develop Garry's Mod addons with guidance on Lua scripts, file organization, assets, and packaging. Covers server and client execution contexts, API lookup, and debugging, with in-game testing included in the workflow.

中文简介正在准备中。当前显示英语简介。

• Planning a new Garry's Mod addon
• Writing Lua scripts for server and client contexts
• Organizing addon assets and directories

Build and operate AutoGPT agents that carry out multi-step workflows. Covers a visual editor for connecting processing blocks, scheduled and webhook triggers, deployment, execution monitoring, and benchmarks for evaluating agent performance.

中文简介正在准备中。当前显示英语简介。

• Build an AI workflow in a visual editor
• Run agents on a schedule or external event
• Add custom agent abilities with Forge

Design tests that assess an AI agent's capabilities and reliability. Covers repeated runs to measure variation, checks for required behavior, and adversarial testing to expose failures that ordinary successful examples may miss.

中文简介正在准备中。当前显示英语简介。

• Measuring variation across repeated runs of the same test
• Checking whether an agent follows required behavior
• Testing responses to unexpected or adversarial inputs

Collect daily AI release news from major labs, product changelogs, blogs, and Hacker News. Remove previously reported items and email a digest with source links and brief explanations tailored to the intended audience.

中文简介正在准备中。当前显示英语简介。

• Receiving a daily AI release digest
• Tracking changes to AI development tools
• Sharing relevant AI updates with a team

Adapt machine learning training to run across multiple GPUs or machines with Ray Train. Covers changes to existing code, comparing training settings with Ray Tune, and saving checkpoints so training can resume after failures.

中文简介正在准备中。当前显示英语简介。

• Adapting existing PyTorch code for multiple GPUs
• Training HuggingFace models across multiple machines
• Comparing learning rates and batch sizes with Ray Tune

Manage multiple AI agents through the AI Maestro command-line tool. Create agents, inspect their status, pause and resume work, rename them, export or import configurations, and manage plugins from one interface.

中文简介正在准备中。当前显示英语简介。

• Creating an agent for a specific project
• Checking agent status and assigned tasks
• Hibernating agents and resuming them later

Helps speed up LLM text generation by comparing methods that predict and verify multiple tokens at once. Covers draft model selection, Medusa prediction heads, Lookahead Decoding settings, and deployment examples for inference services.

中文简介正在准备中。当前显示英语简介。

• Reducing chatbot response latency
• Comparing methods for faster code generation
• Selecting a small draft model for a larger LLM

Organize complex tasks with three Markdown files for plans, findings, and progress. Keep goals, decisions, errors, and test results available across sessions so the agent can review its position and continue work with a clear next step.

中文简介正在准备中。当前显示英语简介。

• Planning and tracking a task with multiple phases
• Saving findings during a research project
• Recording implementation progress and test results

Split independent debugging or repair tasks among multiple AI agents. Define a focused scope, constraints, and expected report for each agent, then review their changes, check for conflicts, and test the combined result.

中文简介正在准备中。当前显示英语简介。

• Investigating unrelated failures across test files
• Assigning separate subsystems to different agents
• Writing focused tasks with clear constraints

Extend the amount of text a language model can process at once. Compares RoPE, YaRN, ALiBi, and position interpolation, with implementation examples, additional training guidance, and memory optimization approaches for long document processing.

中文简介正在准备中。当前显示英语简介。

• Extend an existing model to handle longer inputs
• Compare methods for representing token positions
• Plan additional training with long documents

Interact with Langfuse and access its documentation. Use when needing to (1) query or modify Langfuse data programmatically via the CLI — traces, prompts, datasets, scores, sessions, and any other API resource, (2) look up Langfuse documentation, concepts, integration guides, or SDK usage, or (3) understand how any Langfuse feature works. This skill covers CLI-based API access (via npx) and multiple documentation retrieval methods.

中文简介正在准备中。当前显示原文说明。

Push the current branch and all tags to origin, then create a GitHub release using the latest tag and its CHANGELOG.md entry. Use after tag-version to complete a release.

中文简介正在准备中。当前显示原文说明。

Draft the changelog entry for all unreleased commits in Keep a Changelog format. Groups commits into Added, Changed, Fixed, Removed, and Security. Use before releasing a new version or when updating CHANGELOG.md.

中文简介正在准备中。当前显示原文说明。

Check whether changed source files have corresponding test files. Use for code quality review before merging a PR, or when asked whether new code has tests.

中文简介正在准备中。当前显示原文说明。

Review database migration files for naming conventions and dangerous operations. Auto-activates for migration files.

中文简介正在准备中。当前显示原文说明。

Scan the codebase for common security issues: hardcoded secrets, SQL injection vectors, XSS, unvalidated inputs, and insecure defaults. Use before deploying, as part of code quality review, or when asked to check for security issues.

中文简介正在准备中。当前显示原文说明。

Rename a code symbol (variable, function, class) across a specified scope.

中文简介正在准备中。当前显示原文说明。

Apply frontend code quality rules for React and TypeScript components. Auto-activates when editing component files.

中文简介正在准备中。当前显示原文说明。

Find overly complex code: files over 300 lines, functions over 50 lines, deeply nested conditions (4+ levels), and magic numbers. Use for code quality reviews, pre-release checks, or when asked to assess code maintainability.

中文简介正在准备中。当前显示原文说明。

Demonstrates the personal scope for Claude Code skills. Use when testing personal-scoped skills or when the user wants to understand the difference between personal and project skill scopes.

中文简介正在准备中。当前显示原文说明。

Explains what a skill is and demonstrates that skills are working. Use when testing skills, when asked about skills, or when asked to demonstrate how skills work.

中文简介正在准备中。当前显示原文说明。