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.
20.857 de skill-uri din 756 de depozite · actualizat acum 5 minute
4.073 de skill-uri
- nowait-reasoning-optimizerforyourhealth111-pixel/Vibe-SkillsImplements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.AlteleFără avertismente★ 3,8 K↓ —
- skill-installerforyourhealth111-pixel/Vibe-SkillsInstall Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).AlteleFără avertismente★ 3,8 K↓ —
- neuropixels-analysisforyourhealth111-pixel/Vibe-SkillsNeuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.AlteleFără avertismente★ 3,8 K↓ —
- nw-continuenWave-ai/nWaveDetects current wave progress for a feature and resumes at the next step. Scans docs/feature/ for artifacts.AlteleFără avertismente★ 622↓ —
- flashrag-evidenceforyourhealth111-pixel/Vibe-SkillsLocal evidence retrieval (FlashRAG-style) for VCO/vibe: search protocols/config/skills docs and return citeable snippets with file+line anchors.AlteleFără avertismente★ 3,8 K↓ —
- torch-geometricforyourhealth111-pixel/Vibe-SkillsGraph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.AlteleFără avertismente★ 3,8 K↓ —
- local-vco-rolesforyourhealth111-pixel/Vibe-SkillsCodex-local role pack for dialectic multi-agent reviews, designed to be compatible with the local vibe skill.AlteleFără avertismente★ 3,8 K↓ —
- cancel-ralphforyourhealth111-pixel/Vibe-SkillsCodex-compatible cancel command for Ralph loop state, preserving the original command name.AlteleFără avertismente★ 3,8 K↓ —
- ralph-loopforyourhealth111-pixel/Vibe-SkillsCodex-compatible Ralph loop runner with dual engines (compat local state loop + optional open-ralph-wiggum backend).AlteleFără avertismente★ 3,8 K↓ —
- math-toolsforyourhealth111-pixel/Vibe-SkillsDeterministic mathematical computation using SymPy. Use for ANY math operation requiring exact/verified results - basic arithmetic, algebra (simplify, expand, factor, solve equations), calculus (derivatives, integrals, limits, series), linear algebra (matrices, determinants, eigenvalues), trigonometry, number theory (primes, GCD/LCM, factorization), and statistics. Ensures mathematical accuracy by using symbolic computation rather than LLM estimation.AlteleFără avertismente★ 3,8 K↓ —
- datavisforyourhealth111-pixel/Vibe-SkillsComprehensive data visualization toolkit for creating beautiful, mathematically elegant visualizations with D3.js, Chart.js, and custom SVG. Use when (1) building interactive data visualizations, (2) designing color palettes for charts, (3) choosing scales and visual encodings, (4) creating data pipelines from Census/SEC/Wikipedia APIs, (5) crafting narrative-driven data stories, (6) making perceptually accurate charts, or (7) implementing force-directed networks, timelines, or geographic maps.AlteleFără avertismente★ 3,8 K↓ —
- smart-ralphtzachbon/smart-ralphCore Smart Ralph skill defining common arguments, execution modes, and shared behaviors across all Ralph plugins.AlteleFără avertismente★ 561↓ —
- delegation-principletzachbon/smart-ralphCore principle that the main agent is a coordinator, not an implementer. All work must be delegated to subagents.AlteleFără avertismente★ 561↓ —
- nw-sd-patternsnWave-ai/nWaveCore distributed systems patterns - load balancing, caching, sharding, consistent hashing, message queues, rate limiting, CDN, Bloom filters, ID generation, replication, conflict resolution, CAP theoremAlteleFără avertismente★ 622↓ —Apare și în 1 alt depozit
- nw-fp-principlesnWave-ai/nWaveCore functional programming thinking patterns and type system foundations, language-agnosticAlteleFără avertismente★ 622↓ —Apare și în 1 alt depozit
- skill-cross-platform-publishZJU-REAL/Easel跨平台一键发布：一份内容适配并发布到多个平台（小红书/抖音/B站/公众号/快手/视频号/知乎）。 按各平台格式约束（字数/比例/标签/内容类型）适配内容，再逐个委派对应平台发布 SKILL。 当用户说"一键发布""同时发到多个平台""多平台发布""一稿多发""全平台发""发到抖音+小红书+B站" "分发到各平台"时使用。适配由 LLM 做，路由与约束检查由 scripts/publish_dispatch.py。AlteleFără avertismente★ 4 K↓ —
- skill-content-postmortemZJU-REAL/Easel内容复盘与爆款规律提炼。两种模式：(A) 单条复盘 — 分析一条已发布内容为什么爆/扑， 从 Hook、结构、选题、时间、平台适配等维度拆解原因；(B) 规律提炼 — 从多条内容中 提炼爆款共同特征、总结可复制的爆款公式。当用户说"这条为什么火了"、"为什么扑了"、 "复盘"、"分析数据"、"爆款规律"、"总结规律"、"爆款公式"、"内容复盘"、"什么规律"时触发。AlteleFără avertismente★ 4 K↓ —
- skill-publish-schedulerZJU-REAL/Easel批量定时发布排期：管理"内容 × 平台 × 发布时间"的排期表，导入排期、查看队列、计算到期项、 到期派发给各平台发布 SKILL、回填状态。当用户说"定时发布""批量发布""排期发布""发布队列" "按计划发""这几条按时间自动发""发布排期表""到点发布"时使用。调度逻辑纯脚本，实际发布委派平台 SKILL。AlteleFără avertismente★ 4 K↓ —
- skill-news-intelligenceZJU-REAL/Easel聚合中文行业媒体、垂类资讯和平台商业动态，按创作者赛道过滤，生成结构化情报简报与可执行选题。 当用户说“行业资讯/深度情报、最近行业动态、每日简报、选题情报、财经/科技/AI 动态”时使用。 本 SKILL 做日级深度资讯；分钟级实时热搜与快速二创选题用 skill-trending-topics。AlteleFără avertismente★ 4 K↓ —
- skill-wechat-publisherZJU-REAL/Easel微信公众号文章自动创作与发布工具。给定参考文章、文字或文档，自动搜索整理全网相关信息、生成图文并茂的公众号文章，并发布到微信公众号草稿箱。特别强调反 AI 检测写作。 触发场景（沾边就用）：用户提到"公众号 / 微信文章 / 推文 / 公号 / 发文 / mp / 草稿箱 / 群发"，或要求把话题/文档/笔记写成公众号文章并发布到微信。AlteleFără avertismente★ 4 K↓ —
- skill-comment-insightsZJU-REAL/Easel评论区量化分析：对一批评论做情感分析（正/中/负占比 + 代表评论）、高频词与短语提取、 以及需求/吐槽/提问的诉求挖掘，为内容复盘和选题反哺提供数据。当用户说"评论情感分析" "评论区分析""用户在说什么""评论正负面比例""评论高频词""评论关键词""口碑分析""评论词云" "用户诉求""评论区吐槽"时使用。基于 jieba（分词）+ SnowNLP（情感）+ 社媒情感词典。AlteleFără avertismente★ 4 K↓ —
- skill-publish-notifyZJU-REAL/Easel发布通知推送：内容发布成功/失败后，把结果推送到飞书/钉钉/企业微信群机器人、 Telegram、Slack 或任意 webhook。当用户说"发布通知""发到飞书群""通知钉钉""推送到企微" "发布成功提醒""webhook 通知""发布完通知我""群机器人"时使用。纯脚本无第三方依赖。AlteleFără avertismente★ 4 K↓ —
- skill-data-trackerZJU-REAL/Easel社媒数据记录与趋势分析。三种模式：(A) 记录快照 — 记录当日粉丝数、互动量等指标快照； (B) 增长趋势 — 分析粉丝增长率、增速变化、里程碑预测；(C) 内容生命周期 — 追踪单条内容 从发布到衰减的数据变化，判断速爆型/稳增型/长尾型。当用户说"记录数据"、"今天粉丝数"、 "增长趋势"、"粉丝增长"、"内容生命周期"、"这条笔记数据变化"、"数据快照"时触发。AlteleFără avertismente★ 4 K↓ —
- skill-publish-logZJU-REAL/Easel发布记录管理。当用户提到"记一下刚发的"、"发布记录"、"这个月发了多少"、"发布历史"、 "记录一下"、"发布日志"、"上次发了什么"时触发。支持记录每次发布的内容信息（平台、标题、 链接、时间、初始数据），并提供查询和统计功能，方便后续复盘。AlteleFără avertismente★ 4 K↓ —