Top Rated
The most starred skills loved by the community. Quality guaranteed!
quantizing-models-bitsandbytes
by Orchestra-Research
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
autoresearch
by Orchestra-Research
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
pytorch-fsdp2
by Orchestra-Research
Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.
aws dsql
by awslabs
Build with Aurora DSQL - manage schemas, execute queries, and handle migrations with DSQL-specific requirements. Use when developing a scalable or distributed database/application or user requests DSQL.
amazon aurora dsql
by awslabs
Build with Aurora DSQL - manage schemas, execute queries, and handle migrations with DSQL-specific requirements. Use when developing a scalable or distributed database/application or user requests DSQL.
ray-train
by Orchestra-Research
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.
verl-rl-training
by Orchestra-Research
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.
implementing-android-code
by bitwarden
This skill should be used when implementing Android code in Bitwarden. Covers critical patterns, gotchas, and anti-patterns unique to this codebase. Triggered by "How do I implement a ViewModel?", "Create a new screen", "Add navigation", "Write a repository", "BaseViewModel pattern", "State-Action-Event", "type-safe navigation", "@Serializable route", "SavedStateHandle persistence", "process death recovery", "handleAction", "sendAction", "Hilt module", "Repository pattern", "implementing a screen", "adding a data source", "handling navigation", "encrypted storage", "security patterns", "Clock injection", "DataState", or any questions about implementing features, screens, ViewModels, data sources, or navigation in the Bitwarden Android app.
codex-worker
by MoonshotAI
Spawn and manage multiple Codex CLI agents via tmux to work on tasks in parallel. Use whenever a task can be decomposed into independent subtasks (e.g. batch triage, parallel fixes, multi-file refactors). When codex and tmux are available, prefer this over the built-in Task tool for parallelism.
gen-docs
by MoonshotAI
Update Kimi Code CLI user documentation.
harness
by revfactory
"하네스를 구성합니다. 전문 에이전트를 정의하며, 해당 에이전트가 사용할 스킬을 생성하는 메타 스킬. (1) '하네스 구성해줘', '하네스 구축해줘' 요청 시, (2) '하네스 설계', '하네스 엔지니어링' 요청 시, (3) 새로운 도메인/프로젝트에 대한 하네스 기반 자동화 체계를 구축할 때, (4) 하네스 구성을 재구성하거나 확장할 때, (5) '하네스 점검', '하네스 감사', '하네스 현황', '에이전트/스킬 동기화' 등 기존 하네스 운영/유지보수 요청 시 사용."
ML Training Recipes
by Orchestra-Research
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.
gen-rust
by MoonshotAI
Sync Rust implementation with Python changes (exclude UI/login) by reviewing recent changes, mapping modules, porting logic, and updating tests.
openspec-bulk-archive-change
by studyzy
一次归档多个已完成的变更。用于归档多个并行变更。
openspec-sync-specs
by studyzy
将变更中的增量规范同步到主规范。当用户想要使用增量规范中的更改更新主规范，而不归档该变更时使用。
material-component-doc
by bytedance
用于 FlowGram 物料库组件文档撰写的专用技能，提供组件文档生成、Story 创建、翻译等功能的指导和自动化支持
openspec-explore
by studyzy
进入探索模式 - 一个用于探索想法、调查问题和澄清需求的思考伙伴。当用户想要在进行更改之前或期间深入思考某事时使用。
dsql
by awslabs
Build with Aurora DSQL - manage schemas, execute queries, and handle migrations with DSQL-specific requirements. Use when developing a scalable or distributed database/application or user requests DSQL.
distributed sql
by awslabs
Build with Aurora DSQL - manage schemas, execute queries, and handle migrations with DSQL-specific requirements. Use when developing a scalable or distributed database/application or user requests DSQL.
release
by MoonshotAI
Execute the release workflow for Kimi Code CLI packages.
gha
by ykdojo
Analyze GitHub Actions failures and identify root causes
distributed postgres
by awslabs
Build with Aurora DSQL - manage schemas, execute queries, and handle migrations with DSQL-specific requirements. Use when developing a scalable or distributed database/application or user requests DSQL.
higress-daily-report
by alibaba
生成 Higress 项目每日报告，追踪 issue/PR 动态，沉淀问题处理经验，驱动社区问题闭环。用于生成日报、跟进 issue、记录解决方案。
architecture
by vudovn
Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.