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
Use when creating video content for Xiaohongshu, filming vlogs or tutorials, editing short-form vertical video, or optimizing video for mobile viewing
软件工程 / 诊断修复
rev-unicorn-debug
rev-unicorn-debug
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…
软件工程 / 诊断修复
performance-engineer
performance-engineer
Expert performance engineer specializing in modern observability,
软件工程 / 诊断修复
frontend-slides
frontend-slides
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files.
软件工程 / 诊断修复
flask
flask
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.
软件工程 / 诊断修复
form-cro
form-cro
Optimize any form that is NOT signup or account registration — including lead capture, contact, demo request, application, survey, quote, and checkout forms.
软件工程 / 诊断修复
rev-dex-dumper
rev-dex-dumper
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…
软件工程 / 诊断修复
playcanvas-engine
playcanvas-engine
Lightweight WebGL/WebGPU game engine with entity-component architecture and visual editor integration. Use this skill when building browser-based games,…
软件工程 / 诊断修复
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to…
软件工程 / 部署发布
quarto-authoring
quarto-authoring
Use when the user is explicitly working with Quarto, .qmd files, _quarto.yml, Quarto projects, or Quarto features such as callouts, cross-references,…
软件工程 / 诊断修复
serving-llms-vllm
serving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference…
软件工程 / 诊断修复
observability-engineer
observability-engineer
Build production-ready monitoring, logging, and tracing systems. Implements comprehensive observability strategies, SLI/SLO management, and incident response…
软件工程 / 诊断修复
nextjs
nextjs
Next.js App Router expert guidance. Use when building, debugging, or architecting Next.js applications — routing, Server Components, Server Actions, Cache…
软件工程 / 诊断修复
php-development
php-development
Expert guidance for PHP 8+ development with SOLID principles, PSR standards, and modern best practices
软件工程 / 诊断修复
diffity-tree
diffity-tree
Open the diffity file tree browser to browse and comment on repository files
软件工程 / 诊断修复
problem-solving
problem-solving
Creative problem-solving techniques for breaking through stuck points - includes collision-zone thinking, inversion, pattern recognition, and simplification
软件工程 / 诊断修复
context-mode
context-mode
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.
软件工程 / 部署发布
llama-cpp
llama-cpp
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…
软件工程 / 诊断修复
ralph
ralph
Self-referential loop until task completion with configurable verification reviewer
软件工程 / 诊断修复
promptfoo-evaluation
promptfoo-evaluation
Configures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing…