Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
19,358 skills from 699 repositories · updated 4 minutes ago
1,308 skills
- recallvibeeval/vibecosystemQuery the memory system for relevant learnings from past sessions using semantic search.ProductivityNo warnings★ 540↓ —
- layered-recallvibeeval/vibecosystemProgressive memory recall with 4 scope layers AND 3 depth layers. Scope: identity > project > room > deep. Depth: IDs only > summary > full. 10-50x token savings through fetch-on-confirmation pattern.ProductivityNo warnings★ 540↓ —
- notepad-systemvibeeval/vibecosystemUse this skill when context compression is imminent, when resuming a session, or when preserving critical decisions across long tasks. Provides a durable notepad that survives compaction and lets any agent pick up exactly where the previous context left off.ProductivityNo warnings★ 540↓ —
- skill-event-calendarZJU-REAL/Easel查询未来 N 天的节日、纪念日、电商节点、行业事件，为创作者提供内容蹭点。 覆盖中国节假日、国际节日、电商大促、行业展会、考试节点、体育赛事等。 当用户说"未来有什么节日"、"下个月有什么可以蹭"、"节点日历"、"营销日历"、 "有什么热点可以提前准备"、"内容日历节点"、"最近有什么节日"、 "什么时候有大促"、"节日营销"时触发。 和 skill-content-calendar 的区别：content-calendar 排内容发布日程， event-calendar 提供节日和事件的数据查询，是选题灵感的上游数据源。ProductivityNo warnings★ 4K↓ —
- xhs-note-creatorZJU-REAL/Easel小红书内容总入口：生成标题、正文、caption、hashtags，以及 3-9 张图文卡片或短视频分镜，覆盖素材分析、卖点评估、去 AI 味和质检。 当用户说“写/做小红书笔记、小红书图文/种草/文案、出一套卡片、小红书视频”时使用。 整套笔记用本 SKILL；仅渲染卡片用 card-xiaohongshu；其他平台的通用文案用 social-content。ProductivityNo warnings★ 4K↓ —
- knowledge-graphvibeeval/vibecosystemKnowledge graph integration for token-efficient codebase understanding. Uses codebase-memory MCP for AST indexing, dependency graphs, and smart context selection. 6-71x token savings vs raw file reading.ProductivityNo warnings★ 540↓ —
- workflow-routervibeeval/vibecosystemGoal-based workflow orchestration - routes tasks to specialist agents based on user goalsProductivityNo warnings★ 540↓ —
- harvest-adaptivevibeeval/vibecosystemAdaptive content summarization - auto-detect content type and produce relevant summaryProductivityNo warnings★ 540↓ —
- nw-agent-creation-workflownWave-ai/nWaveDetailed 5-phase workflow for creating agents - from requirements analysis through validation and iterative refinementProductivityNo warnings★ 622↓ —Also in 1 other repo
- tracing-patternsvibeeval/vibecosystemOpenTelemetry setup, span context propagation, sampling strategies, Jaeger queriesProductivityNo warnings★ 540↓ —
- remembervibeeval/vibecosystemStore a learning, pattern, or decision in the memory system for future recall.ProductivityNo warnings★ 540↓ —
- nw-ddd-strategicnWave-ai/nWaveStrategic DDD — bounded context discovery, context mapping patterns, subdomain classification, ubiquitous language, and organizational alignmentProductivityNo warnings★ 622↓ —Also in 1 other repo
- ctrl-clipdavepoon/buildwithclaude⧉ Copy a message to the system clipboard cleanly formatted — no blockquote pipes, no terminal bars, no Claude commentary. Use whenever you draft a message the user will paste (Slack, Teams, PR comment, email) to add a clickable "⧉ ctrl + click" copy link under it, and when the user says "/ctrl-clip", "copy that", "put it on the clipboard" (in any language). Optional argument picks the target format: slack (default), md, plain.ProductivityNo warnings★ 3.7K↓ —
- tao-analyze-detection-kpiNVIDIA/skillsRun TAO Data Services KPI analysis for object detection, comparing inference annotations against ground truth to compute per-class TP/FP/FN/TN, precision, recall, accuracy, and AP at a fixed IoU. Use when an object detection workflow needs per-class mAP reported after inference, or when the user asks to "run KPI analyze", "compute detection mAP", or "score my OD predictions against ground truth".ProductivityNo warnings★ 3.7K↓ —
- jetson-inference-mem-tuneNVIDIA/skillsPick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.ProductivityNo warnings★ 3.7K↓ —
- file-guarda5c-ai/babysitterBabysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestrationProductivityNo warnings★ 1.9K↓ —
- iterative-retrievalvibeeval/vibecosystemPattern for progressively refining context retrieval to solve the subagent context problemProductivityNo warnings★ 540↓ —
- session-compressionvibeeval/vibecosystemLossless session context compression for token efficiency. Extracts entities, decisions, and state into compact format before context window fills. 10-30x reduction in context size while preserving all actionable information.ProductivityNo warnings★ 540↓ —
- smart-model-routingvibeeval/vibecosystemDynamic model selection based on task complexity scoring. Replaces static model mappings with a weighted signal system that picks Opus, Sonnet, or Haiku-class speed per task. Works with agent-assignment-matrix.md.ProductivityNo warnings★ 540↓ —
- knowledge-stewardforyourhealth111-pixel/Vibe-SkillsAI工作经验知识库管理。适用于用户明确要求'保存到Obsidian'、'记录这个'、'save this insight'、'memo this'、'capture this'等知识沉淀场景。将对话中的提示词、模式、问题修复、想法和效率优化保存到Obsidian知识库，并自动同步到GitHub。ProductivityNo warnings★ 3.8K↓ —
- explaining-machine-learning-modelsforyourhealth111-pixel/Vibe-SkillsExplain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.ProductivityNo warnings★ 3.8K↓ —
- pufferlibforyourhealth111-pixel/Vibe-SkillsThis skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this skill for implementing PPO training, creating PufferEnv environments, optimizing RL performance, or developing policies with CNNs/LSTMs.ProductivityNo warnings★ 3.8K↓ —
- tao-analyze-gaps-vlm-bcqNVIDIA/skillsExtract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions. Use when the user asks to "analyze VLM BCQ gaps", "extract VLM false positives and false negatives", or identify failure cases from a predictions JSON for DEFT root-cause analysis on a binary-classification VLM workflow.ProductivityNo warnings★ 3.7K↓ —
- knowledge-managementvibeeval/vibecosystemProje bilgisini 4 katmanli yapida organize et. Aktif projeler, sorumluluk alanlari, referans kaynaklar ve arsiv. Progressive summarization ile bilgiyi katman katman ozumse. Second brain pattern'i ile codebase bilgisini yapilandir.ProductivityNo warnings★ 540↓ —