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 4785 个相关结果 / 提示词与 LLM

软件工程 / 诊断修复

short-video-production

short-video-production

431

Use when creating video content for Xiaohongshu, filming vlogs or tutorials, editing short-form vertical video, or optimizing video for mobile viewing

Stars 167
uiuxapiworkflow

软件工程 / 诊断修复

rev-unicorn-debug

rev-unicorn-debug

430

Debug and emulate specific code fragments or functions using the Unicorn engine. Activate when the user wants to emulate a function with Unicorn, trace binary…

Stars 1,073
ragdebuggingrevunicorn

软件工程 / 诊断修复

performance-engineer

performance-engineer

430

Expert performance engineer specializing in modern observability,

Stars 37,695
frontendbackenddesignui

软件工程 / 诊断修复

frontend-slides

frontend-slides

430

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files.

Stars 37,683
frontenddesignuislides

软件工程 / 诊断修复

flask

flask

430

Build Python web apps with Flask using application factory pattern, Blueprints, and Flask-SQLAlchemy. Prevents 9 documented errors including stream_with_context teardown issues, async/gevent conflicts, and CSRF cache problems. Use when: creating Flask projects, organizing blueprints, or troubleshooting circular imports, context errors, registration, streaming, or authentication.

Stars 783
uitestingauthapi

软件工程 / 诊断修复

form-cro

form-cro

429

Optimize any form that is NOT signup or account registration — including lead capture, contact, demo request, application, survey, quote, and checkout forms.

Stars 37,683
uiformcrooptimize

软件工程 / 诊断修复

rev-dex-dumper

rev-dex-dumper

429

Dump DEX files from a running Android app for unpacking/deobfuscation. Activate when the user wants to unpack an Android APK, dump DEX from memory, extract…

Stars 1,073
workflowrevdexdumper

软件工程 / 诊断修复

playcanvas-engine

playcanvas-engine

429

Lightweight WebGL/WebGPU game engine with entity-component architecture and visual editor integration. Use this skill when building browser-based games,…

Stars 115
designuiperformanceworkflow

软件工程 / 诊断修复

pdf

pdf

429

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to…

Stars 638
uipdfcomprehensivemanipulation

软件工程 / 部署发布

quarto-authoring

quarto-authoring

429

Use when the user is explicitly working with Quarto, .qmd files, _quarto.yml, Quarto projects, or Quarto features such as callouts, cross-references,…

Stars 354
authquartoauthoringthe

软件工程 / 诊断修复

serving-llms-vllm

serving-llms-vllm

428

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference…

Stars 27,329
uiperformanceapillm

软件工程 / 诊断修复

observability-engineer

observability-engineer

428

Build production-ready monitoring, logging, and tracing systems. Implements comprehensive observability strategies, SLI/SLO management, and incident response…

Stars 37,692
designuiperformancemonitoring

软件工程 / 诊断修复

nextjs

nextjs

428

Next.js App Router expert guidance. Use when building, debugging, or architecting Next.js applications — routing, Server Components, Server Actions, Cache…

Stars 162
reactnextjsuidebugging

软件工程 / 诊断修复

php-development

php-development

428

Expert guidance for PHP 8+ development with SOLID principles, PSR standards, and modern best practices

Stars 111
designuiphpdevelopment

软件工程 / 诊断修复

diffity-tree

diffity-tree

428

Open the diffity file tree browser to browse and comment on repository files

Stars 665
uidiffitytreeopen

软件工程 / 诊断修复

problem-solving

problem-solving

428

Creative problem-solving techniques for breaking through stuck points - includes collision-zone thinking, inversion, pattern recognition, and simplification

Stars 2,080
uiproblemsolvingcreative

软件工程 / 诊断修复

context-mode

context-mode

427

Use context-mode tools (ctx_execute, ctx_execute_file) instead of Bash/cat when processing large outputs. Triggers: "analyze logs", "summarize output", "process data", "parse JSON", "filter results", "extract errors", "check build output", "analyze dependencies", "process API response", "large file analysis", "page snapshot", "browser snapshot", "DOM structure", "inspect page", "accessibility tree", "Playwright snapshot", "run tests", "test output", "coverage report", "git log", "recent commits", "diff between branches", "list containers", "pod status", "disk usage", "fetch docs", "API reference", "index documentation", "call API", "check response", "query results", "find TODOs", "count lines", "codebase statistics", "security audit", "outdated packages", "dependency tree", "cloud resources", "CI/CD output". Also triggers on ANY MCP tool output that may exceed 20 lines. Subagent routing is handled automatically via PreToolUse hook.

Stars 0
reactnextjsuiplaywright

软件工程 / 部署发布

llama-cpp

llama-cpp

426

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is…

Stars 27,325
dockerdeploymentllmllama

软件工程 / 诊断修复

ralph

ralph

426

Self-referential loop until task completion with configurable verification reviewer

Stars 33,997
uiralphselfreferential

软件工程 / 诊断修复

promptfoo-evaluation

promptfoo-evaluation

426

Configures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing…

Stars 1,050
uitestingllmprompt

78 / 240