Topic: codex-cli
4,700 skills in this topic.
-
guide-updater
当用户明确要求"更新项目指南""同步指南""沉淀洞见到指南"时使用。将对话中新产生的可复用写作洞见实时沉淀到项目指南文件，保持术语口径一致、结构稳定、可检验与可复现。调用时必须指定指南文件路径。
huangwb8/ChineseResearchLaTeX 1,358
-
nsfc-roadmap
当用户明确要求"生成 NSFC 技术路线图/技术路线图绘制/roadmap/flowchart"或需要把标书研究内容转成"可打印、A4 可读"的技术路线图时使用。默认输出可编辑源文件（`.drawio`）与可嵌入文档的渲染结果（`.svg`/`.png`/`.pdf`）；当用户主动提及 Nano Banana/Gemini 图片模型时，可切换为 PNG-only 模式。⚠️ 不适用：用户只是想修改某张已有图片的格式/尺寸（应使用图片处理技能）、只是想润色技术路线文字描述（应直接改写正文）。
huangwb8/ChineseResearchLaTeX 1,358
-
systematic-literature-review
当用户明确要求"做系统综述/文献综述/related work/相关工作/文献调研"时使用。AI 自定检索词，多源检索→去重→AI 逐篇阅读并评分（1–10分语义相关性与子主题分组）→按高分优先比例选文→自动生成"综/述"字数预算→资深领域专家自由写作（固定摘要/引言/子主题/讨论/展望/结论），保留正文字数与参考文献数硬校验，强制导出 PDF 与 Word。支持多语言翻译与智能编译（en/zh/ja/de/fr/es）。
huangwb8/ChineseResearchLaTeX 1,358
-
nsfc-length-aligner
基于国自然标书篇幅预算标准；检查目标标书篇幅并总结差距；给出针对性优化建议；在尽量不改变原意的前提下扩写/压缩到达标。
huangwb8/ChineseResearchLaTeX 1,358
-
transfer-old-latex-to-new
当用户明确要求“迁移 LaTeX 模板”“把旧项目接入 ChineseResearchLaTeX”“把旧标书/论文/毕业论文/简历套进当前模板”“把 Word/PDF/Markdown/零散 tex 整理进现有项目”，或直接提到 `transfer-old-latex-to-new` 时使用。旧别名 `migrating-latex-templates` 可兼容理解。该 skill 只负责把正文内容迁移到当前仓库现有模板的内容层；绝不能修改 `packages/` 内公共包源码、也绝不能修改 `projects/` 内模板样式或入口骨架，只能写入目标项目允许承载正文的内容文件。
huangwb8/ChineseResearchLaTeX 1,358
-
nsfc-budget
当用户明确要求“写/生成 NSFC 预算说明书”“写预算说明”“生成 budget.tex / budget.pdf”“写国自然预算 justification”时使用。基于用户标书正文或补充材料，输出一份可提交的预算说明书 LaTeX 项目并渲染 `budget.pdf`。若用户未指定工作目录，必须暂停并先要求其指定。⚠️ 不适用：用户只是想了解预算原则；用户仅要预算表数字而不写说明书；或用户是 2026 青年 A/B/C 默认包干制且无需预算说明书的场景。
huangwb8/ChineseResearchLaTeX 1,358
-
nsfc-justification-writer
当用户明确要求"写/改 NSFC 立项依据""立项依据写作/重构"时使用。基于最小信息表输出价值与必要性、现状不足、科学问题/假说与项目切入点，并保持模板结构不被破坏。适用于 NSFC 及各类科研基金申请书的立项依据写作场景。
huangwb8/ChineseResearchLaTeX 1,358
-
nsfc-humanization
去除 NSFC 标书中的 AI 机器味，使文本读起来像资深领域专家亲笔撰写（不适用：非标书内容/需修改格式/需补充新内容）
huangwb8/ChineseResearchLaTeX 1,358
-
paper-write-sci
根据 LaTeX 论文项目撰写、修订和润色 SCI 期刊论文，默认 AI 自主模式，也支持人机协作仅输出审查计划；提供作者风格化写作、数字事实核验、逻辑树多轮审查与 PDF/Word 渲染闭环。⚠️ 不适用：仅改格式/样式参数、纯参考文献管理、图片处理、非论文写作任务。
huangwb8/ChineseResearchLaTeX 1,358
-
nsfc-abstract
当用户明确要求"写/润色 NSFC 标书摘要""生成中文摘要和英文摘要""把中文摘要翻译成英文摘要"时使用。输出中文、英文两个版本（英文必须是中文的忠实翻译版），同时输出标题建议（1个推荐标题+5个候选标题及理由）。中文摘要默认≤400字符，英文摘要默认≤4000字符。输出方式：将结果写入工作目录下的 `NSFC-ABSTRACTS.md`。⚠️ 不适用：用户只想翻译一段与标书无关的通用文本（应直接翻译）；用户只想写立项依据/研究内容/研究基础正文（应使用对应 nsfc 系列 skill）。
huangwb8/ChineseResearchLaTeX 1,358
-
nsfc-code
根据 NSFC 标书正文内容，结合申请代码推荐库，为你给出 5 组申请代码1/2（主/次）推荐与理由；输出到 NSFC-CODE-vYYYYMMDDHHmm.md（只读，不修改标书）
huangwb8/ChineseResearchLaTeX 1,358
-
memex-search
Search, filter, and retrieve Claude/Codex history indexed by the memex CLI. Use when you want to search history, run lexical/semantic/hybrid search, fetch full transcripts, or produce LLM-friendly JSON output.
nicosuave/memex 74
-
instruction-improver
Search memex for user feedback patterns (frustration, corrections, praise, successful outcomes) to identify recurring mistakes and wins, then generate CLAUDE.md or AGENTS.md improvements.
nicosuave/memex 74
-
memex-search
Search, filter, and retrieve Claude/Codex history indexed by the memex CLI. Use when the user wants to index history, run lexical/semantic/hybrid search, fetch full transcripts, or produce LLM-friendly JSON output for RAG.
nicosuave/memex 74
-
memex-search
Search, filter, and retrieve Opencode history via memex CLI. Use for context resumption, finding past code/decisions, and self-correction based on history.
nicosuave/memex 74
-
pytorch
Building and training neural networks with PyTorch. Use when implementing deep learning models, training loops, data pipelines, model optimization with torch.compile, distributed training, or deploying PyTorch models.
itsmostafa/llm-engineering-skills 17
-
mlx
Running and fine-tuning LLMs on Apple Silicon with MLX. Use when working with models locally on Mac, converting Hugging Face models to MLX format, fine-tuning with LoRA/QLoRA on Apple Silicon, or serving models via HTTP API.
itsmostafa/llm-engineering-skills 17
-
lora
Parameter-efficient fine-tuning with Low-Rank Adaptation (LoRA). Use when fine-tuning large language models with limited GPU memory, creating task-specific adapters, or when you need to train multiple specialized models from a single base.
itsmostafa/llm-engineering-skills 17
-
context-engineering
Strategies for managing LLM context windows effectively in AI agents. Use when building agents that handle long conversations, multi-step tasks, tool orchestration, or need to maintain coherence across extended interactions.
itsmostafa/llm-engineering-skills 17
-
rlhf
Understanding Reinforcement Learning from Human Feedback (RLHF) for aligning language models. Use when learning about preference data, reward modeling, policy optimization, or direct alignment algorithms like DPO.
itsmostafa/llm-engineering-skills 17
-
qlora
Memory-efficient fine-tuning with 4-bit quantization and LoRA adapters. Use when fine-tuning large models (7B+) on consumer GPUs, when VRAM is limited, or when standard LoRA still exceeds memory. Builds on the lora skill.
itsmostafa/llm-engineering-skills 17
-
transformers
Loading and using pretrained models with Hugging Face Transformers. Use when working with pretrained models from the Hub, running inference with Pipeline API, fine-tuning models with Trainer, or handling text, vision, audio, and multimodal tasks.
itsmostafa/llm-engineering-skills 17
-
prompt-engineering
Crafting effective prompts for LLMs. Use when designing prompts, improving output quality, structuring complex instructions, or debugging poor model responses.
itsmostafa/llm-engineering-skills 17
-
agents
Patterns and architectures for building AI agents and workflows with LLMs. Use when designing systems that involve tool use, multi-step reasoning, autonomous decision-making, or orchestration of LLM-driven tasks.
itsmostafa/llm-engineering-skills 17