Agent Skills
Read from each publisher's repository, labelled by what each skill lets an agent do. Nothing is run.
2,104 skills
- blip-2-vision-languageDaniel AvilaVision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.Instructions only
- brand-guidelinesDaniel AvilaApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Instructions only
- brand-guidelinesDaniel AvilaApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Instructions only
- chromaDaniel AvilaOpen-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or docum…Instructions only
- clipDaniel AvilaOpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Bes…Instructions only
- computer-use-agentsDaniel AvilaBuild AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and …Instructions only1 high finding
- constitutional-aiDaniel AvilaAnthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude…Instructions only
- context-window-managementDaniel AvilaStrategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context engineering, long context.Instructions only
- context7-auto-researchDaniel AvilaAutomatically fetch latest library/framework documentation for Claude Code via Context7 APIInstructions only
- conversation-memoryDaniel AvilaPersistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.Instructions only1 high finding
- crewaiDaniel AvilaExpert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows f…Instructions only
- crewai-multi-agentDaniel AvilaMulti-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hie…Instructions only
- data-engineerDaniel AvilaBuild scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.Instructions only
- data-scientistDaniel AvilaExpert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence.Instructions only
- datadog-cliDaniel AvilaDatadog CLI for searching logs, querying metrics, tracing requests, and managing dashboards. Use this when debugging production issues or working with Datadog observability.Instructions only
- deep-researchDaniel AvilaRun autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.Instructions only
- deep-research-notebooklmDaniel AvilaDeep research skill powered by NotebookLM MCP. Conducts structured multi-source research (market analysis, competitive intel, trend analysis, prospect research) using Google NotebookLM as the research engine, then delivers formatted briefs and optional studio …Instructions only
- deepspeedDaniel AvilaExpert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attentionInstructions only
- dispatching-parallel-agentsDaniel AvilaUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesInstructions only
- distributed-llm-pretraining-torchtitanDaniel AvilaProvides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.Instructions only
- docs-searchDaniel AvilaSearch auto-generated codebase documentation for function signatures, API docs, class definitions, and code comments. Use when the user asks to "search docs", "find documentation", "look up a function", "check the API", or before implementing changes to verify…Instructions only
- dspyDaniel AvilaBuild complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programmingInstructions only
- evaluating-code-modelsDaniel AvilaEvaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard f…Instructions only
- evaluating-llms-harnessDaniel AvilaEvaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, …Instructions only
- faissDaniel AvilaFacebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similar…Instructions only
- fine-tuning-with-trlDaniel AvilaFine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works …Instructions only
- geminiDaniel AvilaUse when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.Instructions only1 high finding
- gemini-api-agent-platformDaniel AvilaGuides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK for enterprise AI applications. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like Live API, tools, multimedia generation, caching, and batch prediction.Instructions only
- gepettoDaniel AvilaCreates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.Instructions only
- gguf-quantizationDaniel AvilaGGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.Instructions only
- google-analyticsDaniel Avila · 2 scriptsAnalyze Google Analytics data, review website performance metrics, identify traffic patterns, and suggest data-driven improvements. Use when the user asks about analytics, website metrics, traffic analysis, conversion rates, user behavior, or performance optim…Runs commands1 finding
- gptqDaniel AvilaPost-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates wit…Instructions only
- graph-queryDaniel AvilaQuery the code graph database to understand component relationships, dependencies, and change impact. Use when the user asks to "find callers", "check dependencies", "what uses this", "show relationships", "find serializers", or when reading code and needing t…Instructions only
- grpo-rl-trainingDaniel Avila · 2 scriptsExpert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model trainingRuns commands1 finding
- guidanceDaniel AvilaControl LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation frameworkInstructions only1 high finding
- hqq-quantizationDaniel AvilaHalf-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.Instructions only
- huggingface-accelerateDaniel AvilaSimplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosys…Instructions only
- huggingface-tokenizersDaniel AvilaFast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with t…Instructions only
- implementing-llms-litgptDaniel AvilaImplements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Singl…Instructions only
- instructorDaniel AvilaExtract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output libraryInstructions only1 high finding
Labels come from the skill's own files, read on the date shown: the tools its frontmatter allows and the scripts it ships. They are not a safety rating, and no finding is not a safety guarantee. How skills are checked.