Loading…
Showing 4141–4170 of 15616 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| jimeng-dialogue-assistanthashgraph-online/awesome-codex-pluginsUse when 核对即梦分镜台词本(阶段一)。对照剧本原文校验一致性。 | Stars: 1.5k | Updated | Claude CodeCodex | Verified | Install |
| cost-trackerzeuikli/claude-code-workspace追蹤並計算當前 session 的 Token 使用量和花費(USD)。產出前後對比報告,幫助使用者了解 workspace 優化的實際效益。 | Stars: 157 | Updated | Claude CodeCodex | Verified | Install |
| marketingzeuikli/claude-code-workspace行銷策略全流程:受眾分析、GTM 規劃、A/B 測試設計、KPI 設定、競品定位。適合在規劃行銷活動、制定上市策略、或設計成長實驗時使用。 | Stars: 157 | Updated | Claude CodeCodex | Verified | Install |
| pmzeuikli/claude-code-workspace專案管理工作流:Sprint 規劃、Issue 優先排序(MoSCoW/RICE)、狀態報告、風險評估、Sprint 回顧。適合在啟動新專案、Sprint 規劃會議、撰寫進度報告、或做任務優先排序時使用。 | Stars: 157 | Updated | Claude CodeCodex | Verified | Install |
| retrozeuikli/claude-code-workspaceSession 回顧報告:提取本次對話的關鍵決策、完成事項與改善建議。適合 session 結束前或 /compact 前使用。 | Stars: 157 | Updated | Claude CodeCodex | Verified | Install |
| writingzeuikli/claude-code-workspace文案撰寫全套工作流:分析受眾語調、套用說服公式(AIDA/PAS/FAB)、產出部落格/Email/Landing Page/社群文案,並提供 SEO 優化建議。適合在撰寫行銷文案、內容行銷、或需要匹配特定品牌語調時使用。 | Stars: 157 | Updated | Claude CodeCodex | Verified | Install |
| bump-rfcencero-systems/incanTransition an Incan RFC from one status to the next. Use when the user asks to promote, advance, or finalize an RFC, or says /bump-rfc. Handles Draft → Planned, Planned → In Progress, and In Progress → Implemented transitions. | Stars: 75 | Updated | Claude CodeCodex | Verified | Install |
| closeoutencero-systems/incanSafely close out completed Incan work after a PR is merged by verifying merge status, syncing the base branch, removing task-owned local worktrees/assets, deleting merged local/remote branches, pruning refs, and reporting dirty or ambiguous leftovers. Use when the user says /closeout, asks to clean up after a merged PR, or wants local RFC/issue branch/worktree cleanup. | Stars: 75 | Updated | Claude CodeCodex | Verified | Install |
| sync-texbrycewang-stanford/Auto-Empirical-Research-SkillsTransfers prose edits from latex/index.tex (Overleaf) back into index.qmd. Use after pulling LaTeX edits from a collaborator. | Stars: 5k | Updated | Claude CodeCodex | Verified | Install |
| implementing-llms-litgptOrchestra-Research/AI-Research-SKILLsImplements 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. Single-file implementations, no abstraction layers. | Stars: 14k | Updated | Claude CodeCodex | Verified | Install |
| distributed-llm-pretraining-torchtitanOrchestra-Research/AI-Research-SKILLsProvides 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. | Stars: 14k | Updated | Claude CodeCodex | Verified | Install |
| nnsight-remote-interpretabilityOrchestra-Research/AI-Research-SKILLsProvides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture. | Stars: 14k | Updated | Claude CodeCodex | Verified | Install |
| sparse-autoencoder-trainingOrchestra-Research/AI-Research-SKILLsProvides 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. | Stars: 14k | Updated | Claude CodeCodex | Verified | Install |
| miles-rl-trainingOrchestra-Research/AI-Research-SKILLsProvides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput. | Stars: 14k | Updated | Claude CodeCodex | Verified | Install |
| openrlhf-trainingOrchestra-Research/AI-Research-SKILLsHigh-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing. | Stars: 14k | Updated | Claude CodeCodex | Verified | Install |
| simpo-trainingOrchestra-Research/AI-Research-SKILLsSimple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO. | Stars: 14k | Updated | Claude CodeCodex | Verified | Install |
| slime-rl-trainingOrchestra-Research/AI-Research-SKILLsProvides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling. | Stars: 14k | Updated | Claude CodeCodex | Verified | Install |
| fine-tuning-with-trlOrchestra-Research/AI-Research-SKILLsFine-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 with HuggingFace Transformers. | Stars: 14k | Updated | Claude CodeCodex | Verified | Install |
| quantizing-models-bitsandbytesOrchestra-Research/AI-Research-SKILLsQuantizes 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. | Stars: 14k | Updated | Claude CodeCodex | Verified | Install |
| experiment-tracking-swanlabOrchestra-Research/AI-Research-SKILLsProvides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows. | Stars: 14k | Updated | Claude CodeCodex | Verified | Install |
| qdrant-vector-searchOrchestra-Research/AI-Research-SKILLsHigh-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance. | Stars: 14k | Updated | Claude CodeCodex | Verified | Install |
| phoenix-observabilityOrchestra-Research/AI-Research-SKILLsOpen-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights. | Stars: 14k | Updated | Claude CodeCodex | Verified | Install |
| evaluating-cosmos-policyOrchestra-Research/AI-Research-SKILLsEvaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines. | Stars: 14k | Updated | Claude CodeCodex | Verified | Install |
| benchthun-res/vlink构建并运行 vlink-bench 性能基准(showcase/quick/full 预设),生成 HTML/JSON 报告。用户要求"跑 bench"、"性能测试"、对比后端吞吐/延迟、 验证性能回归时使用。 | Stars: 114 | Updated | Claude CodeCodex | Verified | Install |
| clang-tidythun-res/vlink对指定文件或全仓库运行 clang-tidy(WarningsAsErrors='*')。用户要求 "跑 clang-tidy"、"tidy 检查某文件"、排查 CI tidy 门禁失败时使用。 | Stars: 114 | Updated | Claude CodeCodex | Verified | Install |
| formatthun-res/vlink运行 tools/format.sh 对整个仓库做 clang-format、cmake-format 与行尾符 统一。用户要求"格式化代码"、"跑 format"、提交前统一格式时使用。 | Stars: 114 | Updated | Claude CodeCodex | Verified | Install |
| issuethun-res/vlink调查 VLink 中可复现的缺陷、文档遗漏或功能建议,搜索 open/closed Issue 去重,按仓库模板用自然、具体、证据充分的简体中文草拟或创建 Issue, 可读取既有 Issue 上下文后草拟或发布单条回复.用户要求"提 issue"、 "创建 issue"、"检查是否已有 issue"、"回复 issue"、"评论 issue"、 "帮我回应 issue"时使用;不得伪装人类身份、批量回复或灌水。 | Stars: 114 | Updated | Claude CodeCodex | Verified | Install |
| abstraction-powersyahiidkamil/Software-Engineer-AI-Agent-AtlasActivate ATLAS pattern recognition mode. Identify repeated patterns, extract essential characteristics, and create reusable abstractions from concrete examples. | Stars: 406 | Updated | Claude CodeCodex | Verified | Install |
| learning-from-mistakessyahiidkamil/Software-Engineer-AI-Agent-AtlasRecord a hard-won engineering lesson after a bug or mistake is resolved. Use when a bug resisted ATLAS until Boss's guidance cracked it, or when a long debugging hunt ended in an aha moment worth never relearning. | Stars: 406 | Updated | Claude CodeCodex | Verified | Install |
| super-product-ownersyahiidkamil/Software-Engineer-AI-Agent-AtlasDecide what is worth building and what "great" means for it — interview the user one question at a time, write a one-page brief, hand off to a prototype, judge the prototype with taste, and turn it into acceptance checks. Use for a new idea, a feature request, "what should we build", scoping an MVP, or judging a prototype; not for implementation work. | Stars: 406 | Updated | Claude CodeCodex | Verified | Install |