自动化
工作流自动化与调度
unity-mcp-orchestrator
CoplayDev
Orchestrate Unity Editor via MCP (Model Context Protocol) tools and resources. Use when working with Unity projects through MCP for Unity - creating/modifying GameObjects, editing scripts, managing scenes, running tests, or any Unity Editor automation. Provides best practices, tool schemas, and workflow patterns for effective Unity-MCP integration.
docx-processing-anthropic
lawvable
"Toolkit for comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks"
research-deep
Weizhena
Read research outline, launch independent agent for each item for deep research. Disable task output.
research-deep
Weizhena
读取调研outline，为每个item启动独立agent进行深度调研。禁用task output。
research-report
Weizhena
Summarize deep research results into markdown report, cover all fields, skip uncertain values.
research-deep
Weizhena
Read research outline, launch independent agent for each item for deep research. Disable task output.
subagent-driven-development
obra
Use when executing implementation plans with independent tasks in the current session
senior-data-engineer
borghei
Expert data engineering covering data pipelines, ETL/ELT, data warehousing, streaming, and data quality.
customer-success-manager
borghei
Expert customer success covering onboarding, adoption, retention, expansion, health scoring, and customer advocacy.
ux-researcher
borghei
Expert UX research covering user research methods, usability testing, data synthesis, and research operations.
unity-mcp-orchestrator
CoplayDev
Orchestrate Unity Editor via MCP (Model Context Protocol) tools and resources. Use when working with Unity projects through MCP for Unity - creating/modifying GameObjects, editing scripts, managing scenes, running tests, or any Unity Editor automation. Provides best practices, tool schemas, and workflow patterns for effective Unity-MCP integration.
openclaw-medical-skills
Yuan1z0825
"Codex adaptation of the OpenClaw Medical Skills library. Use for biomedical, clinical, healthcare AI, genomics, bioinformatics, drug discovery, pharmacovigilance, clinical trials, medical imaging, public health, medical device, regulatory, scientific data analysis, lab automation, and medical research workflows; also use when the user mentions OpenClaw Medical Skills, medical skill library, or any named capability preserved in the OpenClaw capability index."
nature-downloader
Yuan1z0825
Use when a user needs lawful academic full text, CNKI institutional access, English OA retrieval, publisher API access, institutional browser fallback, or supporting information downloads.
inbound-lead-qualifier
OneWave-AI
Analyze inbound leads (form fills, demo requests) and score based on ICP fit, intent, and urgency. Auto-generates qualification questions, routes to right rep, and suggests personalized first touch. Use for qualifying and routing inbound leads at scale.
retrospective
Donchitos
"Generates a sprint or milestone retrospective by analyzing completed work, velocity, blockers, and patterns. Produces actionable insights for the next iteration."
fine-tuning-serving-openpi
majiayu000
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues.
serving-llms-vllm
majiayu000
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
blip-2-vision-language
majiayu000
Vision-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.
verl-rl-training
majiayu000
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
sparse-autoencoder-training
majiayu000
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
nanogpt
majiayu000
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
rpi-quick
microsoft
"Sequence Research, Plan, Implement, Review, and Follow-up for an RPI task. Use when one workflow should coordinate the full delivery lifecycle."
backlog-plan
microsoft
"Read-only backlog planning for Azure DevOps, GitHub, and Jira. Use to discover, triage, sprint-plan, or resume without mutating a tracker."
using-superpowers
obra
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions