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

软件工程 / 诊断修复

mobile-app-testing

mobile-app-testing

200

Mobile app testing with unit tests, UI automation, performance testing. Use for test infrastructure, E2E tests, testing standards, or encountering test…

Stars 147
reactuiperformancetesting

软件工程 / 诊断修复

nextjs-dynamic-routes-params

nextjs-dynamic-routes-params

200

Guide for Next.js App Router dynamic routes and pathname parameters. Use when building pages that depend on URL segments (IDs, slugs, nested paths), accessing…

Stars 93
nextjsuidynamicroutes

软件工程 / 诊断修复

quasar-skilld

quasar-skilld

200

Build high-performance VueJS user interfaces (SPA, PWA, SSR, Mobile and Desktop) in record time. ALWAYS use when writing code importing \"quasar\". Consult for…

Stars 161
vuedesignuiperformance

软件工程 / 诊断修复

miles-rl-training

miles-rl-training

200

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing…

Stars 8,481
backenduiperformancemiles

研究学习 / 检索整理

guidance

guidance

200

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance…

Stars 8,475
uillmpromptworkflow

软件工程 / 诊断修复

axiom-testing

axiom-testing

200

Use when writing ANY test, debugging flaky tests, making tests faster, or choosing Swift Testing vs XCTest. Covers unit tests, UI tests, async testing, test…

Stars 902
uitestingdebuggingaxiom

研究学习 / 检索整理

constitutional-ai

constitutional-ai

200

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from…

Stars 8,473
uiconstitutionalanthropicmethod

研究学习 / 检索整理

gguf-quantization

gguf-quantization

200

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible…

Stars 8,475
uiggufquantizationformat

软件工程 / 诊断修复

axiom-tools

axiom-tools

200

Use when asking how to use Axiom, what skills are available, getting started with Axiom, capturing iOS simulator console output with xclog, or symbolicating…

Stars 902
uiaxiomtoolsasking

软件工程 / 诊断修复

axolotl

axolotl

200

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

Stars 8,471
uiapillmdebugging

软件工程 / 诊断修复

axiom-swiftui-nav-ref

axiom-swiftui-nav-ref

200

Reference — Comprehensive SwiftUI navigation guide covering NavigationStack (iOS 16+), NavigationSplitView (iOS 16+), NavigationPath, deep linking, state…

Stars 902
designuiapirag

软件工程 / 诊断修复

conductor-validator

conductor-validator

200

Validates Conductor project artifacts for completeness,

Stars 37,673
uiworkflowconductorvalidator

通用助手 / 编排推荐

gmail

gmail

200

Send, search, and organize Gmail messages, drafts, and labels. Read full threads and get shareable Google Groups permalinks. Use when asked to compose an…

Stars 3
authapiagentgmail

软件工程 / 诊断修复

golf-data

golf-data

200

PGA Tour, LPGA, and DP World Tour golf data via ESPN public endpoints — tournament leaderboards, scorecards, season schedules, golfer profiles/overviews, and news. Zero config, no API keys. Use when: user asks about golf scores, tournament leaderboards, scorecards, PGA Tour schedule, golfer profiles, golfer season stats, LPGA results, or golf news. Don't use when: user asks about other sports — use football-data (soccer), nfl-data (NFL), nba-data (NBA), wnba-data (WNBA), nhl-data (NHL), mlb-data (MLB), tennis-data (tennis), cfb-data (college football), cbb-data (college basketball), or fastf1 (F1). For betting odds use polymarket or kalshi. For news use sports-news.

Stars 102
uiapigolfdata

通用助手 / 编排推荐

cli-anything-drawio

cli-anything-drawio

200

cli-anything-drawio — an installable skill for AI agents, published by hkuds/cli-anything.

Stars 34,986
agentagentsclianything

研究学习 / 检索整理

awq-quantization

awq-quantization

200

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…

Stars 8,471
backendllmawqquantization

研究学习 / 检索整理

adk-docs

adk-docs

200

创建、审阅、更新和搜索 ADK 文档的指南 - 当用户询问编写、维护或审计 ADK 机器人文档时使用

Stars 0
uiauditworkflowadk

研究学习 / 检索整理

evaluating-llms-harness

evaluating-llms-harness

200

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting…

Stars 8,475
uillmpromptevaluating

研究学习 / 检索整理

outlines

outlines

200

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize…

Stars 8,483
llmgithuboutlinesguarantee

研究学习 / 检索整理

nsfc-research-content-writer

nsfc-research-content-writer

200

当用户明确要求"写/改研究内容""研究内容+创新+年度计划编排"时使用。为 NSFC 正文"(二)研究内容"写作/重构,并同步编排"特色与创新"和"三年年度研究计划",输出可直接落到 LaTeX 模板的三个 extraTex 文件。

Stars 1,580
nsfcresearchcontentwriter

第 548 / 890 页