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

通用助手 / 编排推荐

local-descriptions

local-descriptions

202

USE FOR getting AI-generated POI text descriptions. Requires POI IDs obtained from web-search (with result_filter=locations). Returns markdown descriptions…

Stars 133
uiapilocaldescriptions

软件工程 / 诊断修复

graph-viewer

graph-viewer

202

Integrate the reusable CDF graph viewer (useGraphViewer) into a Flows app by copying the local code bundle. Use when embedding a graph visualization, adding a…

Stars 4
reactuiauthworkflow

软件工程 / 诊断修复

remotion-ads

remotion-ads

202

Professional video ad creation with Remotion — Instagram Reels (9:16), website explainers (16:9), and carousels (4:5). Use when creating video ads, animated…

Stars 38
uiremotionadsprofessional

通用助手 / 编排推荐

headline-formulas

headline-formulas

201

25+ proven headline formulas that stop the scroll, capture attention, and drive clicks. Templates and examples for every situation. Use when: Writing headlines…

Stars 108
uitestingragheadline

研究学习 / 检索整理

hqq-quantization

hqq-quantization

201

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast…

Stars 8,475
backendllmhqqquantization

安全与治理 / 审核评估

linux-privilege-escalation

linux-privilege-escalation

201

Execute systematic privilege escalation assessments on Linux systems to identify and exploit misconfigurations, vulnerable services, and security weaknesses…

Stars 37,687
uiuxsecurityauth

软件工程 / 诊断修复

faststore-storefront

faststore-storefront

201

Core coding rules and workflow for developing VTEX FastStore storefronts. Use when starting any FastStore development task, writing TypeScript/React…

Stars 28
reactdesignworkflowfaststore

通用助手 / 编排推荐

AI/ML-时间序列

ai-ml-timeseries

201

时间序列预测 — LightGBM、Transformers、时序验证、特征工程和生产部署。用于构建时间序列模型时。

Stars 0
uitestingdeploymentrag

研究学习 / 检索整理

grpo-rl-training

grpo-rl-training

201

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

Stars 8,475
uiworkflowgrpotraining

软件工程 / 诊断修复

streamlit

streamlit

201

Fast Python framework for building interactive web apps, dashboards, and data visualizations without HTML/CSS/JavaScript. Use when user wants to create data…

Stars 2
frontenduiapistreamlit

通用助手 / 编排推荐

memos-memory-guide

memos-memory-guide

201

Use the MemOS Local memory system to search and use the user's past conversations. Use this skill whenever the user refers to past chats, their own preferences…

Stars 9,126
uiagentagentsmemos

研究学习 / 检索整理

k6-docs

k6-docs

201

Use when writing or reviewing k6 documentation across TypeScript types, user docs, and release notes.

Stars 39
uitestingagentagents

研究学习 / 检索整理

speculative-decoding

speculative-decoding

201

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6×…

Stars 8,489
llmspeculativedecodingaccelerate

软件工程 / 诊断修复

svelte-components

svelte-components

201

Svelte component patterns. Use for web components, component libraries (Bits UI, Ark UI, Melt UI), form patterns, or third-party integration.

Stars 79
uisveltecomponentscomponent

通用助手 / 编排推荐

promptslide

promptslide

201

Creates and authors slide deck presentations using the PromptSlide framework (Vite + React 19 + Tailwind v4 + Framer Motion). Use when the user wants to create a new slide deck, add or edit slides, customize themes or branding, work with slide animations and transitions, capture slides as images, or visually verify slide appearance. Triggers on mentions of slides, decks, presentations, PromptSlide, slide screenshots, or slide-related tasks.

Stars 9
reacttailwinduiauth

研究学习 / 检索整理

pyvene-interventions

pyvene-interventions

201

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing,…

Stars 8,486
uigithubpyveneinterventions

研究学习 / 检索整理

memory-protocol

memory-protocol

201

Persistent cross-session memory using Memento MCP knowledge graph (mcp__memento__* tools). Recall-before-acting: search memory before starting tasks, on errors, and when receiving corrections. Multi-dimensional search: two queries per recall event (technical topic + process/workflow learnings). Store-after-discovery: persist solutions, conventions, and corrections immediately. Three-step recall: search, open_nodes, traverse relations. WORKING_STATE.md for crash recovery. Self-reminder protocol every 5-10 messages. Activate on task start, errors, corrections, session boundaries, or explicit memory requests. See references/agents-md-setup.md for AGENTS.md integration.

Stars 2
agentagentsworkflowdebugging

软件工程 / 诊断修复

snapshot-testing

snapshot-testing

201

Use Verify for snapshot testing in .NET. Approve API surfaces, HTTP responses, rendered emails, and serialized outputs. Detect unintended changes through…

Stars 927
testingapisnapshotverify

安全与治理 / 审核评估

smart-contract-security

smart-contract-security

201

Master smart contract security with auditing, vulnerability detection, and incident response

Stars 1
uisecurityauditagent

数据与分析 / 分析洞察

product-analytics

product-analytics

201

Measure what matters with proper event tracking, funnels, cohorts, and metrics. Use when setting up analytics, tracking features, or understanding behavior.

Stars 26
productanalyticsmeasurematters

第 546 / 890 页