Discover and install skills, docs, and rules to enhance your AI agent's capabilities.
| Name | Contains | Score |
|---|---|---|
Narcooo/inkos 识别并修复空泛、模板化、总结腔和其他AI写作痕迹,同时保留作者声音。Use for semantic prose cleanup, not keyword deletion. | Skills | |
digoal/blog 输入一个产品 idea(一句话或详细描述均可),自动生成图文并茂、结构完整的 BRD(商业需求文档),以 Markdown 格式保存到当前项目 markdown/ 目录,同时输出配套 SVG 图表文件。触发条件:用户提到"写 BRD"、"帮我写需求文档"、"生成 BRD"、"写商业需求文档"、"我有个产品想法"、"帮我把这个 idea 写成文档"、"PRD/BRD 模板"、"产品立项文档"。即使用户只给出一句简短的产品描述如"我想做一个 XX 产品",也应立即使用本 skill 生成 BRD。本 skill 面向产品经理、创业者、产品负责人,输出可直接用于团队评审和立项决策的专业文档。 | Skills | |
digoal/blog Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Skills | |
digoal/blog 用红蓝双队辩论模式深度解答通用问题,以非讨好型人格的理性人视角输出最终报告。 触发条件:用户提出任何值得深度分析的问题,尤其是存在争议、有多个维度、需要权威数据支撑的问题。 提到"红蓝辩论"、"辩证分析"、"正反两面"、"两种观点"、"帮我深度分析"、"有没有反驳意见"、"理性分析一下"、"客观看待",或提出任何开放性、争议性问题时必须使用本 skill。 即使用户只是提出一个看似简单的问题如"XX 到底值不值得做"或"XX 是对的吗", 只要涉及价值判断、策略选择、事实真相等复杂情境,也应使用本 skill。 本 skill 不追求讨好用户,拒绝模糊骑墙,双队结论必须互斥,最终裁判整合并输出面向小白的第一人称深度文章。 | Skills | |
digoal/blog 基于功能设计文档与现有源码,端到端实现一个产品功能:开发、代码 review、测试用例编写与执行, 循环迭代直到测试通过,最终产出用户手册与实现总结文档(保存到当前项目 markdown/ 目录)。 触发条件:用户提供了功能设计文档(PRD/设计文档/需求描述)+ 源码目录(或代码库路径), 并希望"实现这个功能"、"开发这个功能"、"把这个设计文档变成代码"、"做这个功能的开发+测试"、 "完整实现并测试"、"端到端开发",或明确要求按"开发-review-测试"循环推进直到测试通过。 也适用于需要额外运行环境的开发任务,例如 PostgreSQL/MySQL 等数据库插件开发 (可能需要编译、搭建实例、配置参数、初始化、跑测试)、需要启动服务进程才能测试的后端功能、 需要特定运行时环境的库或框架功能。 即使用户只是说"帮我把这个功能做出来"、"按设计文档实现一下"、"这个功能开发完了麻烦测试一下", 但同时给出了设计文档和代码路径,也应使用本 skill。 本 skill 的核心是严格的"开发 ⇄ Review"循环 + "测试者不预先看代码"的盲测试原则, 因此当用户提到"独立测试"、"测试不能看代码"、"先写测试用例再看代码"、"black-box 测试"时, 也应优先使用本 skill。 不适用于:只是要求"写一个脚本"、"改一行代码"、"快速修一个 bug"等轻量级、 无需走完整开发-review-测试闭环的任务;也不适用于纯粹的代码评审(无需新开发功能) 或纯粹的测试用例编写(无设计文档、无需开发)这类单一环节请求—— 这些更适合直接处理而非套用本 skill 的完整闭环流程。 | Skills | |
digoal/blog 对任何领域的棘手问题进行深度思考分析,先识别问题所属领域并按需调度多位领域专家并行作答, 之后由事实核查员和红队做克制的事实审计与对抗性反驳,最后整合为面向小白的第一人称终稿。 适用:用户抛出一个跨领域/有深度的真实问题,希望听到多位专家的视角、看到观点的边界与证伪条件, 并得到一气呵成、通俗有据的最终文章。不适用:简单事实查询、纯情绪吐槽、不要求证据的随口一问。 | Skills | |
Orchestra-Research/AI-Research-SKILLs Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance. | Skills | |
Orchestra-Research/AI-Research-SKILLs Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning. | Skills | |
Orchestra-Research/AI-Research-SKILLs Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner. | Skills | |
Orchestra-Research/AI-Research-SKILLs Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU). | Skills | |
aiming-lab/AutoResearchClaw Multi-GPU and distributed training patterns with PyTorch DDP. Use when scaling training across GPUs. | Skills | |
aiming-lab/AutoResearchClaw Best practices for image classification tasks. Use when working on CIFAR, ImageNet, or other classification benchmarks. | Skills | |
microsoft/data-formulator Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts. | Skills | |
kubesphere/kubesphere Use when working with WizTelemetry Auditing extension for KubeSphere, including installation, configuration, and audit query API | Skills | |
kubesphere/kubesphere Use when installing or configuring the WizTelemetry Data Pipeline (vector) extension for KubeSphere, which provides data collection, transformation, and routing for observability data including logs, auditing, events, and notifications | Skills | |
RightNow-AI/openfang System administration expert for Linux, macOS, Windows, services, and monitoring | Skills | |
RightNow-AI/openfang GitHub operations expert for PRs, issues, code review, Actions, and gh CLI | Skills | |
warpdotdev/oz-skills Triage GitHub bug reports for actionability. Use when evaluating whether a bug issue has sufficient detail and identifying missing information from the reporter. | Skills | |
Prisma-Labs-Dev/apple-skills Index of Apple developer documentation for iOS, macOS, and related frameworks. Use when looking up what APIs exist in a framework, browsing available documentation, or deciding what docs to fetch. Covers SwiftUI, UIKit, Core Animation (QuartzCore), XCTest, HealthKit, Combine, SwiftData, and more. | Skills | |
tomashrdlicka/engram Show resources marked for deep learning, grouped by topic. Use when the user wants to study saved content. | Skills |
Can't find what you're looking for? Evaluate a missing skill.