提示词与推理
提示词工程、角色设定和推理模式
Skills 列表
ads-tiktok
审计TikTok广告的衡量、Pixel和Events API、移动优先创意、受众、Smart+、购物和电商广告活动、出价、预算、投放节奏、归因和政策。适用于TikTok广告、TikTok Pixel、Events API、Smart+、TikTok Shop广告、GMV Max、Spark Ads或TikTok广告活动优化。
agricidanielads-meta
审核Meta广告的衡量、Pixel和Conversions API、归因、Facebook和Instagram创意、受众、版位、自动化、预算、账户结构和政策。适用于Meta广告、Facebook广告、Instagram广告、Advantage+、Pixel、CAPI、事件管理工具、创意疲劳或Meta广告系列优化。
agricidaniel
ljg-rank
给一个领域，找出背后真正撑着它的几根独立的力。十几个现象砍到不可再少的生成器——砍完能把现象一个个生回来，才算数。Use when user says '降秩', '找秩', '秩是什么', '这个领域靠什么撑着', '背后是什么', or wants to decompose any domain to its irreducible generators.
lijigang
second-opinion
对未提交的更改、分支差异或特定提交运行外部LLM代码审查（OpenAI Codex或Google Gemini CLI）。当用户要求第二意见、外部审查、codex审查、gemini审查或提及/second-opinion时使用。
trailofbits
technology-selection
Guides technology selection and implementation of AI and ML features in .NET 8+ applications using ML.NET, Microsoft.Extensions.AI (MEAI), Microsoft Agent Framework (MAF), GitHub Copilot SDK, ONNX Runtime, and OllamaSharp. Covers the full spectrum from classic ML through modern LLM orchestration to local inference. Use when adding classification, regression, clustering, anomaly detection, recommendation, LLM integration (text generation, summarization, reasoning), RAG pipelines with vector search, agentic workflows with tool calling, Copilot extensions, or custom model inference via ONNX Runtime to a .NET project. DO NOT USE FOR projects targeting .NET Framework (requires .NET 8+), the task is pure data engineering or ETL with no ML/AI component, or the project needs a custom deep learning training loop (use Python with PyTorch/TensorFlow, then export to ONNX for .NET inference).
dotnet
rewardkit
Write Harbor task verifiers using Reward Kit. Use when creating or editing a
harbor-framework
_references
共享规范知识库。包含数学建模竞赛的写作规范、题型防错速查、图表规范等参考内容。其他 skills 在执行过程中按需读取，无需单独触发。
jihe520
wiki-setup
Initialize a new Obsidian wiki vault with the correct structure, special files, and configuration. Use this skill when the user wants to set up a new wiki from scratch, initialize the vault structure, create the .env file, or says things like "set up my wiki", "initialize obsidian", "create a new vault", "get started with the wiki". Also use when the user needs to reconfigure their existing vault or fix a broken setup.
ar9av
jetson-customize-uphy
Configure Jetson UPHY lane allocation (uphy0/uphy1-config) on Orin/Thor custom carriers. Do NOT use for pinmux or PCIe-only edits.
nvidiajetson-customize-pinmux
Per-pin SFIO / direction / initial-state configurator for a Jetson Orin or Thor custom carrier from the pinmux XLSM. Do NOT use for kernel-DT overlay or ODMDATA edits.
nvidiajetson-derive-carrier
Bootstrap a custom carrier board by forking carrier files and scaffolding a DT overlay from the reference devkit. Use after jetson-init-source; not for module-level or kernel-DTB changes.
nvidiajetson-speculative-decoding
Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.
nvidiatao-generate-video-reasoning-annotations
Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with reasoning traces, via VLM/LLM distillation. Use when the user wants to "create video training data", "generate video QA datasets", "build CoT reasoning traces from videos", "auto-label videos", or run the video_reasoning_annotation pipeline. Triggers include "video annotation", "video CoT", "video QA", "chain-of-thought", "video captioning pipeline", "video distillation".
nvidia
credentials
Instructions for handling API keys and credentials safely, verifying their presence, and prompting the user to add them if missing using a safe protocol.
google-deepmindearth2studio-data-fetch
Fetch weather/climate data via Earth2Studio data sources for specific variables and times. Do NOT use for inference pipelines, model discovery, or installation.
nvidiavss-summarize-video
Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.
nvidiarag-perf
Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying / repairing services (use rag-blueprint).
nvidiadata-designer
Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.
nvidia
breadth-chart-analyst
This skill should be used when analyzing market breadth charts, specifically the S&P 500 Breadth Index (200-Day MA based) and the US Stock Market Uptrend Stock Ratio charts. Use this skill when the user provides breadth chart images for analysis, requests market breadth assessment, positioning strategy recommendations, or wants to understand medium-term strategic and short-term tactical market outlook based on breadth indicators. Also works WITHOUT chart images by fetching CSV data directly from public sources. All analysis and output are conducted in English.
tradermonty
adhd
面向编码智能体的并行发散式构思。在多种认知框架（监管者、生物学、速通玩家、10岁小孩、零预算）下生成N个独立分支，进行评分、聚类、修剪陷阱，并深化最优幸存者。用于 /adhd、“ADHD模式”、头脑风暴/构思意图，或开放式设计、架构、命名、API/SDK接口以及模糊调试决策。跳过语法、查询、已知根因的bug或封闭式表述（“快速”、“标准”、“规范”、“教科书”）。完整的预检门控在技能正文中。
uditakhourii
codex
当用户要求运行 Codex CLI（codex exec、codex resume）或引用 OpenAI Codex 进行代码分析、重构或自动编辑时使用。默认使用 GPT-5.2 以获得最先进的软件工程能力。
softaworksgemini
当用户要求运行 Gemini CLI 进行代码审查、计划审查或大上下文（>200k）处理时使用。适用于需要大上下文窗口的全面分析。默认使用 Gemini 3 Pro，提供最先进的推理和编码能力。
softaworks
sequential-thinking
Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.
mrgoonie
llm-council
Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a council question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles.
aiwithremy