Comprehensive C/C++ programming reference covering everything from C11-C23 and C++11-C++23, system programming, CUDA GPU computing, debugging tools, Rust interop, and advanced topics. Use for: C/C++ questions, modern language features, RAII/memory management, templates/generics, CUDA programming, system programming, debugging/profiling, performance optimization, cross-platform development, build systems, assembly, shell scripting, and any C/C++/CUDA development tasks.
检查并补充前端和后端的i18n翻译文件。以中文（zh-CN）为基准，检查其他语言翻译文件是否缺少key，并补充缺失的key和对应的翻译值。对于日语(ja-JP)、韩语(ko-KR)、繁体中文(zh-TW)，使用与非CJK语言对比的方式检测未翻译内容。
Plan and build an RLM (Recursive Language Model) with predict-rlm. Interactively defines inputs, outputs, skills, and architecture from a goal, then implements the code. Use when the user wants to create a new RLM or explore whether one is feasible.
detailed development workflow with modular patterns for git, code review, testing, documentation, and deployment
Apply findings by making the suggested code changes. Applies accepted verdicts, escalates ambiguous findings to the user, and offers to note skipped genuine improvements. Use when the user asks to \"apply findings\", \"apply fixes\", \"apply suggestions\", \"apply accepted findings\", \"fix the findings\", or \"apply the review results\".
在工作区 drift/skills 下创建或更新一个 drift skill，用于把新的长期小任务沉淀成可复用技能。
- 📁 collectors/
- 📁 distill-protocol-skill/
- 📁 distill-shield-skill/
- 📄 .gitignore
- 📄 FOR_AI.md
- 📄 LICENSE
通用数字永生框架：从聊天记录、社交媒体、文档等多平台数据中蒸馏任何人的数字分身——支持自己、同事、导师、亲人、伴侣/前任、朋友、公众人物 7 种角色模板，接入国内外 12+ 数据平台。
- 📁 scripts/
- 📄 LICENSE
- 📄 README.md
- 📄 SKILL.md
Delegates coding tasks to Codex CLI for prototyping, debugging, and code review. Use when needing algorithm implementation, bug analysis, or code quality feedback. Supports multi-turn sessions via SESSION_ID.
- 📁 examples/
- 📁 prompts/
- 📁 reference/
- 📄 INSTALLATION.md
- 📄 SKILL.md
Manage GPU and CPU cloud instances with the Brev CLI for ML workloads and general compute. Use when users want to create instances, search for GPUs or CPUs, SSH into instances, open editors, copy files, port forward, manage organizations, or work with cloud compute. Supports fine-tuning, reinforcement learning, training, inference, batch processing, and other ML/AI workloads. Trigger keywords - brev, gpu, cpu, instance, create instance, ssh, vram, vcpu, A100, H100, cloud gpu, cloud cpu, remote machine, finetune, fine-tune, RL, RLHF, training, inference, deploy model, serve model, batch job.
Use when analyzing evalyn evaluation results, investigating failures, comparing runs, or understanding agent performance
Automatically sync documentation and configuration after any skill is added or updated. Triggers on every AI code execution to keep README Available Skills and .claude-plugin/marketplace.json up to date.
This has a mismatched name
