Skill-uri pentru agenți pe care le poți verifica înainte să le instalezi
Skill-uri SKILL.md publice din depozite GitHub cu peste 50 de stele și de la producători, scanate și evaluate. Instalează oricare dintre ele cu o singură comandă în Claude Code, Cursor, Codex, GitHub Copilot sau Gemini CLI.
24.131 de skill-uri din 889 de depozite · actualizat acum 2 minute
2.629 de skill-uri
- optimized-nextjs-typescriptMindrally/skillsOptimized Next.js TypeScript best practices with modern UI/UX, focusing on performance, security, and clean architectureInginerieFără avertismente★ 284↓ —
- expo-react-native-typescriptMindrally/skillsExpert in Expo React Native TypeScript mobile development with best practicesInginerieFără avertismente★ 284↓ —
- robocorp-cursor-rulesMindrally/skillsGuidelines for building RoboCorp RPA automation with Python, emphasizing functional programming, Pydantic validation, and async operations.InginerieFără avertismente★ 284↓ —
- kiln-batch-dispatchinstruktlabs/kilnRun requested Kiln asset batches or compare coding-agent harnesses and models in isolated workspaces. Use for repeatable trials, source-reference workflow checks, and distinguishing provider, tool, and asset-quality failures.InginerieFără avertismente★ 292↓ —
- framer-motionMindrally/skillsExpert guidelines for building performant animations with Framer Motion/Motion library in React applicationsInginerieFără avertismente★ 284↓ —
- basecamp-doctorbasecamp/basecamp-cliDiagnose Basecamp CLI, authentication, and agent-plugin health.InginerieFără avertismente★ 294↓ —
- basecampActualizatbasecamp/basecamp-cliInteract with Basecamp through the Basecamp CLI. Use for any Basecamp question or action, including projects, todos, cards, messages, files, schedules, check-ins, people, assignments, notifications, search, and account settings.InginerieFără avertismente★ 294↓ —
- code-reviewjustxor/claude-code-pro-courseРевью изменений в текущей ветке относительно main. Используй, когда просят проверить код, сделать ревью, найти проблемы перед PR или коммитом.InginerieFără avertismente★ 320↓ —
- healthtw93/WazaAudits agent config, instruction drift, hooks or MCP, and AI maintainability. Use when Claude, Codex, or Pi setup looks wrong. Not for application bugs or PR review.InginerieFără avertismente★ 7,4 K↓ —Apare și în 1 alt depozit
- typescript-strictBlackBeltTechnology/pi-agent-dashboardTypeScript strict mode patterns with interfaces, type guards, generics, and utility types. Use when defining types, creating type-safe functions, handling nullable values, or implementing generic components.InginerieFără avertismente★ 330↓ —
- nextjs-react-redux-typescript-cursor-rulesMindrally/skillsComprehensive Next.js, React, Redux, and TypeScript development guidelines covering SOLID principles, component architecture, and best practices.InginerieFără avertismente★ 284↓ —
- python-cybersecurity-tool-developmentMindrally/skillsGuidelines for building Python cybersecurity tools with secure coding practices, async scanning, and structured security testing.InginerieFără avertismente★ 284↓ —
- systematic-debuggingBlackBeltTechnology/pi-agent-dashboardRoot-cause a bug already in front of you, instead of guessing at fixes. Use on triggers like "root cause this", "why is this failing", "debug systematically", "this test is flaky", "it works locally but not in CI", or when a fix attempt has already failed once. Enforces a phased evidence-first process before any code change. Not a feature-build or ship workflow.InginerieFără avertismente★ 330↓ —
- Project Managementskillmds/skillmdLint, search, and install Agent Skills (SKILL.md) — CLI + MCP server + lint engineInginerieFără avertismente★ 249↓ —
- code-overviewtestdouble/hanProduces a human-readable, progressive-disclosure overview of unfamiliar code or a pull request's changes — why it exists (the real problem it solves or goal it serves for the business or a user), and from there what it does, how it flows, and where to start — so you can get up to speed before working on or reviewing it. Use when you want to understand, get oriented in, make sense of, explain, or get up to speed on a chunk of code, a file, a directory, a symbol, or a PR's changes. Writes the overview to a scratch file and changes no code. Does not review code quality or raise findings — use code-review for auditing changes or post-code-review-to-pr for posting them. Does not produce durable feature or system documentation — use project-documentation. Does not assess architecture or structural risk — use architectural-analysis. Does not diagnose bugs or root-cause failures — use investigate. Does not pace a person through the code one step at a time in conversation — use code-walkthrough.InginerieFără avertismente★ 320↓ —
- git-commit-smartmajiayu000/spellbookGenerates meaningful, conventional commit messages automatically. Use when committing code changes. Analyzes diff to create descriptive commits following best practices.InginerieFără avertismente★ 288↓ —
- action-list-reviewxiaomoBoy/pi-bluebook把会议记录整理为可核对的行动清单；当任务要求提取负责人、截止日期、交付物和限制时使用。InginerieFără avertismente★ 325↓ —
- remixMindrally/skillsExpert guidance for Remix development with TypeScript, loaders/actions, nested routes, and full-stack web application best practicesInginerieFără avertismente★ 284↓ —
- refactorjustxor/claude-code-pro-courseБезопасный рефакторинг маленькими шагами без изменения поведения. Используй, когда просят отрефакторить, упростить, разделить модуль, убрать дублирование или почистить код.InginerieFără avertismente★ 320↓ —
- reactMindrally/skillsExpert in React development with modern patterns, hooks, and performance optimizationInginerieFără avertismente★ 284↓ —
- project-health-auditormajiayu000/spellbookComprehensive codebase health analysis. Use when reviewing code quality, identifying technical debt, checking dependencies, or assessing project structure.InginerieFără avertismente★ 288↓ —
- concurrency-reviewdecebals/claude-code-javaReview Java concurrency code for thread safety, race conditions, deadlocks, and modern patterns (Virtual Threads, CompletableFuture, @Async). Use when user asks "check thread safety", "concurrency review", "async code review", or when reviewing multi-threaded code.InginerieFără avertismente★ 759↓ —
- commitjustxor/claude-code-pro-courseСоздаёт git-коммит в формате Conventional Commits по текущим изменениям. Используй, когда просят закоммитить или сделать коммит.InginerieFără avertismente★ 320↓ —
- reviewjustxor/claude-code-pro-courseРевью изменений с фокусом на безопасность по стандартам команды. Используй перед мерджем или по просьбе проверить безопасность.InginerieFără avertismente★ 320↓ —
model-inference-optimize
majiayu000/spellbook
InginerieActualizat alaltăieri
De la autor
优化实际模型推理链路，将正确性对齐、分段 profiling、显存与数据搬运、TensorRT/ONNX/PyTorch 后端、attention/kernel、FP8/compile、缓存与少步采样、质量回归、GPU 成本和服务验收串成同一实验闭环。当用户要求推理提速、降低显存或 GPU 成本、复现模型效果、定位 GPU 利用率低、优化图像/视频/扩散模型或自托管 LLM 时使用，提供 model inference performance optimization 的脱敏案例。纯 API 调用、提示词或 token 用量优化，以及电脑卡顿，不进入本技能的模型推理实验流程。
Instalare
npx skills add majiayu000/spellbook --skill model-inference-optimize -a claude-code
Se instalează în .claude/skills/model-inference-optimize/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Descarcă .zip
Identic octet cu octet cu commit-ul scanat, cu licența depozitului și un fișier SOURCE.txt.
La ce are acces
Doar instrucțiuniNu am văzut acces la rețeaLicență: MIT
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 85
Securitate100
Proveniență70
Întreținere100
Licență100
Adopție41
Fișiere (5)
- SKILL.md
- agents/openai.yaml
- references/cases.md
- references/experiment-template.md
- references/playbook.md