灵感菇

AI 技能的自然生态,你的一句话,蔓延出无限连接。

搜索结果

全部能力

找到 17783 个相关结果

设计与产品 / 审核评估

muapi-photo-pack-generator

muapi-photo-pack-generator

264

Generate a pack of professional or aesthetic photos from a single reference image while preserving the exact identity of the person.

Stars 0
uiuxapiprompt

通用助手 / 编排推荐

supermemory

supermemory

263

Supermemory is a state-of-the-art memory and context infrastructure for AI agents. Use this skill when building applications that need persistent memory, user…

Stars 22,592
designuiagentagents

研究学习 / 检索整理

stable-baselines3

stable-baselines3

263

Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick…

Stars 22,987
uiapiagentagents

通用助手 / 编排推荐

python

python

263

Python development guidelines and best practices. Use when working with Python code.

Stars 17
designuiagentpython

通用助手 / 编排推荐

study-habits

study-habits

263

Build effective study habits with spaced repetition, active recall, and session tracking

Stars 8
uiragstudyhabits

通用助手 / 编排推荐

subagent-driven-development

subagent-driven-development

263

当在当前会话中执行包含独立任务的实现计划时使用

Stars 3,264
agentsubagentdrivendevelopment

软件工程 / 部署发布

deep-interview

deep-interview

263

Socratic deep interview with mathematical ambiguity gating before explicit execution approval

Stars 33,983
uideepinterviewsocratic

软件工程 / 诊断修复

frontend-architecture

frontend-architecture

263

Component architecture, design patterns, state management strategies, module systems, build tools, and scalable application structure

Stars 55
frontenddesignuiux

通用助手 / 编排推荐

handover

handover

263

Generate project handover documentation for AEM Edge Delivery Services projects. Creates comprehensive guides for content authors, developers, and…

Stars 93
uiauthhandovergenerate

软件工程 / 部署发布

API 设计

api-design

263

使用仅扩展设计原则设计稳定、兼容的公共 API。管理 NuGet 包的 API 兼容性、协议兼容性和版本控制,并…

Stars 0
designapistablecompatible

软件工程 / 诊断修复

playwright-core

playwright-core

263

Battle-tested Playwright patterns for writing and debugging reliable E2E, API, component, visual, accessibility, and security tests. Use when you need locator…

Stars 240
designuitestingplaywright

软件工程 / 诊断修复

generate-synthetic-data

generate-synthetic-data

263

Create diverse synthetic test inputs for LLM pipeline evaluation using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user data is sparse, or when stress-testing specific failure hypotheses. Do NOT use when you already have 100+ representative real traces (use stratified sampling instead), or when the task is collecting production logs.

Stars 1,281
uitestingllmgenerate

软件工程 / 诊断修复

fal-image-edit

fal-image-edit

263

AI-powered image editing with style transfer and object removal

Stars 37,680
uifalimageedit

通用助手 / 编排推荐

chat-sdk

chat-sdk

263

Vercel Chat SDK expert guidance. Use when building multi-platform chat bots — Slack, Telegram, Microsoft Teams, Discord, Google Chat, GitHub, Linear — with a…

Stars 162
uiauthapigithub

通用助手 / 编排推荐

document-summary

document-summary

263

Summarize documents, extract key points, and generate structured outlines

Stars 4
ragagentagentsdocument

通用助手 / 编排推荐

cliche-transcendence

cliche-transcendence

263

Transform predictable story elements into fresh, original versions. Use when something feels generic, when feedback says "I've seen this before," when elements…

Stars 76
agentclichetranscendencetransform

通用助手 / 编排推荐

clr-activation-debugging

clr-activation-debugging

263

Diagnoses .NET Framework CLR activation issues using CLR activation logs (CLRLoad logs) produced by mscoree.dll. Use when: the shim picks the wrong runtime, fails to load any runtime, shows unexpected .NET 3.5 Feature-on-Demand (FOD) dialogs, unexpectedly does NOT show FOD dialogs, loads both v2 and v4 into the same process causing failures, or any time someone is wondering "what is happening with .NET Framework activation?"

Stars 1,708
apidebuggingclractivation

软件工程 / 诊断修复

chinese-code-review

chinese-code-review

263

中文 review 沟通参考——话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发。

Stars 3,236
chinesereviewbugjnmetacode

设计与产品 / 审核评估

slogan-generator

slogan-generator

263

Generate and evaluate marketing slogans and taglines for any product or service. Use when naming a campaign, need a tagline for branding, or want scored slogan…

Stars 39
jestslogangeneratorgenerate

设计与产品 / 审核评估

memetic-depth

memetic-depth

263

Create the perception of cultural depth through strategic juxtaposition of familiar and unfamiliar elements. Use when settings feel shallow, when you need…

Stars 76
designuiuxsecurity

462 / 890