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.
47.966 de skill-uri din 2.309 depozite · actualizat acum 6 ore
9.883 de skill-uri
- llmquant-portfolio-labLLMQuant/skillsRouter skill for LLMQuant portfolio-lab workflows. Use when the user needs portfolio exposure maps, what-if simulations, scenario states, or virtual portfolio comparisons.AlteleFără avertismente★ 239↓ —
- skill-scanXBuilderLAB/cheat-on-skillcheat-on-skill 的核心。连 BOSS 直聘真实招聘数据 + 网页信号，按用户能力画像找「高薪 × 你学得动 × AI 增强」交集里的候选岗位。每个岗位给：薪资量级 / 需求热度 / 你的差距 / 可学性分 / 诚实学习周期，并过 AI 影响分类与反诈红线。触发词："帮我找岗位"/"找AI时代高薪工作"/"有什么我能学的高薪岗"/"skill scan"/"扫一遍招聘"。前置：需要 .skill-state.json（无则先路由到 skill-init）。AlteleFără avertismente★ 197↓ —
- llmquant-strategiesLLMQuant/skillsRouter skill for LLMQuant hedge-fund and PM strategy workflows. Use when the user needs equity long/short, long-biased, event-driven, macro, quant, or multi-strategy playbooks.AlteleFără avertismente★ 239↓ —
- style-guideDaleSeo/korean-skills문서 내부 또는 프로젝트 전체에서 일관된 작성 스타일을 유지하도록 돕는 검사기. 어조(경어체/반말), 용어(사용자/유저), 숫자 형식, 목록 스타일, 따옴표, 날짜/시간 형식의 불일치를 감지합니다. 다중 작성자 문서 검토 시, 프로젝트 전체 용어 표준 유지 시, 공식 문서 준비 시, 브랜드 일관성을 위한 문서 작업 시 사용하세요.AlteleFără avertismente★ 242↓ —
- brollappariciojunior/video-editor-skillsHow to find, watch and cut B-roll in a vlog - clips with no speech placed by time between talking clips, chosen by their action and story, not a fixed length. Use when footage mixes talking clips (A-roll) and silent clips, or when the creator says the B-roll pacing feels wrong.AlteleFără avertismente★ 344↓ —
- search-integrationkangarooking/system-prompt-skills当系统提示词需要定义 AI 模型何时搜索、如何搜索、搜索哪些数据源、以及如何处理搜索结果时调用此 Skill。适用于所有涉及实时知识检索的 AI 产品设计——聊天机器人、研究助手、企业知识库问答等。不适用于：纯离线场景（无搜索能力的环境）、已完全内化的知识问答（如数学推导）、创意生成任务。当需求仅涉及"从本地文件读取内容"而非"联网检索外部信息"时，这不是最佳 Skill。AlteleFără avertismente★ 214↓ —
- go-data-structurescxuu/golang-skillsUse when working with Go slices, maps, or arrays — choosing between new and make, using append, declaring empty slices (nil vs literal for JSON), implementing sets with maps, and copying data at boundaries. Also use when building or manipulating collections, even if the user doesn't ask about allocation idioms. Does not cover concurrent data structure safety (see go-concurrency).AlteleFără avertismente★ 188↓ —
- alpha-evolvegaasher/Agent-Loop-SkillsUse when the user wants to evolve an ML model/program through population-based search rather than a single sequential refine loop — a generational evolution where parallel proposers each apply one small SEARCH/REPLACE diff to a parent, scored by a cascade-evaluated training run, and children are kept in a MAP-Elites archive across islands (with migration + checkpointing) so diverse high performers survive. A finite, bounded-parallelism re-creation of AlphaEvolve/OpenEvolve, bent for ML autoresearch. Runs to a fixed compute budget or until interrupted. Not for the sequential single-thread autoresearch loops (one change → measure → keep/revert), and not for verifying a known bug or external claim — this is parallel, diversity-preserving search over a program.AlteleFără avertismente★ 178↓ —
- vouch-propose-from-prvouchdev/vouchDistill a merged PR into vouch claim proposalsAlteleFără avertismente★ 65↓ —
- citation-systemkangarooking/system-prompt-skills当系统提示需要设计引用格式、信息溯源机制、来源标注系统时调用。适用于文档问答、搜索增强生成（RAG）、代码引用、浏览器辅助等需要让用户追溯信息来源的场景。不适用于纯创作类输出（如故事、诗歌），不适用于无需溯源的常识问答，也不适用于注入防御（虽然两者都涉及内容可信度）。AlteleFără avertismente★ 214↓ —
- conversation-flowkangarooking/system-prompt-skills当系统提示词需要定义 AI 如何分类用户意图、路由到不同处理流程、决定澄清策略和自主度级别时调用此 Skill。适用于多任务型 AI 助手、客服机器人、编程工具、研究助手等需要结构化对话管理的场景。不适用于：纯问答型系统（无任务执行）、单轮交互（无对话状态）、简单的 prompt 模板（无路由逻辑）。当需求仅涉及"输出什么格式"而非"如何决定输出什么"时，应该用 output-formatting 而非本 Skill。AlteleFără avertismente★ 214↓ —
- team-buildermturac/everything-openai-codexInteractive agent picker for composing and dispatching parallel teamsAlteleFără avertismente★ 83↓ —
- voice-optimizationkangarooking/system-prompt-skills当系统提示面向语音交互场景（语音助手、语音搜索、有声回答、电话客服 AI）时调用。适用于需要将文本输出优化为口语表达的系统提示设计。不适用于纯文本聊天界面，不适用于语音合成（TTS）技术选型，不适用于图像/视频多模态场景。AlteleFără avertismente★ 214↓ —
- nextjs-turbopackmturac/everything-openai-codexNext.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.AlteleFără avertismente★ 83↓ —
- bun-runtimemturac/everything-openai-codexランタイムとしてのBun、パッケージマネージャー、バンドラー、テストランナー。Bun対Nodeを選択する場合、移行メモ、Vercelサポート。AlteleFără avertismente★ 83↓ —
- skill-scoutmturac/everything-openai-codex新しいスキルを作成する前に、ローカル・マーケットプレイス・GitHub・Webの既存スキルを検索する。スキルの作成・ビルド・フォーク・検索を行う際に使用。AlteleFără avertismente★ 83↓ —
- dmux-workflowsmturac/everything-openai-codexMulti-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across OpenAI Codex, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.AlteleFără avertismente★ 83↓ —
- agent-evalmturac/everything-openai-codex编码代理（OpenAI Codex、Aider、Codex等）在自定义任务上的直接比较，包含通过率、成本、时间和一致性指标AlteleFără avertismente★ 83↓ —
- exa-searchmturac/everything-openai-codex通过Exa MCP进行神经搜索，适用于网络、代码和公司研究。当用户需要网络搜索、代码示例、公司情报、人员查找，或使用Exa神经搜索引擎进行AI驱动的深度研究时使用。AlteleFără avertismente★ 83↓ —
- auditglebis/claude-skillsRun a corpus-scale, STATS-ONLY PII audit over a folder of session transcripts LOCALLY and produce an aggregate report — counts by type and by layer, the per-session redaction-rate distribution, document lengths, and a coarse residual proxy. Use when the user says "audit my sessions", "scan folder for PII", "how much PII across these transcripts", "PII stats for my corpus", "is my redaction holding at scale", or points at a directory of transcripts and asks how much personal data it contains. Fully local — raw text never leaves the machine; the report carries ZERO PII values, transcript substrings, or filenames (only anonymized own-NN ids and counts), so the aggregates are safe to surface. Run it on a RED (raw) corpus to size the PII, or on a GREEN (already-redacted) corpus to check residual leakage.AlteleFără avertismente★ 403↓ —
- continuous-agent-loopmturac/everything-openai-codexPatterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.AlteleFără avertismente★ 83↓ —
- vaultglebis/claude-skillsSet up and verify the CONFIDE THREE LOCKS for storing RED (real, identifiable) session data at rest — device FileVault, a dedicated encrypted store, and per-file sops/age encryption. Use when the user says "set up confide vault", "encrypt my session data", "three locks", "secure store for transcripts", "sops/age for RED data", or asks how to store real therapy/coaching transcripts safely. NON-DESTRUCTIVE: it CHECKS each lock's status and prints the EXACT command to fix any gap; it never moves, deletes, or encrypts data, and never runs `fdesetup enable`/`hdiutil`/`age-keygen` without an explicit flag and your confirmation. Probes are read-only (`fdesetup status`, which sops/age, key path).AlteleFără avertismente★ 403↓ —
- agent-sortmturac/everything-openai-codex通过将技能、命令、规则、钩子和额外内容并行进行仓库感知审查，为特定仓库构建基于证据的 ecc 安装计划，将其分为 DAILY 和 LIBRARY 两类。当 ecc 应精简为项目实际所需而非加载完整包时使用。AlteleFără avertismente★ 83↓ —
- agentic-osmturac/everything-openai-codexOpenAI Codex 上に永続的なマルチエージェントオペレーティングシステムを構築します。カーネルアーキテクチャ、スペシャリストエージェント、スラッシュコマンド、ファイルベースのメモリ、スケジュールされた自動化、外部データベースなしの状態管理をカバーします。AlteleFără avertismente★ 83↓ —