1 774 machine learning skills from 282 authors. They train and fine-tune models, build embeddings, run RAG and measure quality. Half of them fit into 2 253 tokens or less — that is what one costs your context window when the agent loads it. 422 ship runnable scripts rather than instructions alone. 10 of them cannot work without an MCP server, most often rube. We also found 363 copies of these same skills sitting in other people's repositories — counted once here, not 363 times.
1 774 unique 282 authors 905 updated this month 182 from vendors
> Build a webinar or live event registration page as a self-contained HTML file with countdown "create a webinar sign-up page", "event registration landing page", "live training registration page", "workshop sign-up page", "create a webinar page", "build an event page", "free webinar landing page", "live demo registration page", "online event page", "create a registration page for my webinar", "build a training event page".
数学建模的题目理解、模型选择和算法设计阶段。输出题目分析报告与术语表格。
Shopify/DTC profit margin calculator for sellers. Calculate cost breakdowns including ad spend, CAC, payment processing fees, and 3PL costs. Includes LTV/CAC analysis and DTC-specific benchmarks. No API key required.
Supply Chain Bottleneck Analyzer for Shopify/DTC stores. Diagnose cash flow, inventory, shipping costs, and customer acquisition efficiency. Includes CAC/LTV analysis, 3PL cost optimization, and ad spend benchmarks. No API key required for basic analysis.
Accepts a product description and URL to algorithmically identify relevant Venture Capital investors targeting exactly that stage, industry, and niche based on a curated static dataset.
Build the game for its approved target runtime. Compress GAME_DESIGN and ART_DIRECTION into a minimal BUILD_BRIEF, hand it to the current coding agent or another strong model to implement a fully playable build, and iterate against real runs and captured evidence. Use for implement the approved game design, build the game prototype, turn this design into a running game. 游戏构建执行。把批准后的 GAME_DESIGN 与 ART_DIRECTION 压缩成最小 BUILD_BRIEF，交给当前编码智能体或其他强模型，在选定的目标运行环境中实现可完整游玩的版本，并通过真实运行和证据迭代。用于把批准的游戏方案实现成可运行游戏。
OWASP LLM Top 10 (2025) audit checklist for AI applications, agent tools, RAG pipelines, and prompt construction. Use when performing any security review touching LLM client code, prompt templates, agent tools, or vector stores.
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.
Optimize Android app startup, UI rendering, frame stability, and benchmark performance with Baseline Profiles, Macrobenchmark, and lazy initialization. Use when reducing startup time, diagnosing jank, or measuring rendering; defer Compose state API and test-only questions.
Use when calling the app's AI gateway from agent tools — chat completions, embeddings, listing models, configuring defaults or BYOK, reading token/cost usage
Use as the AI build stage of the Butterbase journey. Implements the AI section of 02-plan.md by delegating to the ai skill. Calls manage_ai (update_config) to set defaults and optionally BYOK. Skipped if the plan has no LLM/embeddings usage.
Use as stage 2 of the Butterbase journey, after journey-idea has written 01-idea.md. Translates the idea + capability map into a concrete Butterbase plan — tables (with columns/types/RLS shape), auth providers, function list (name + trigger), storage buckets, AI/RAG/realtime/durable usage, and the chosen frontend stack. In hackathon mode, ruthlessly cuts scope into a "ship now" vs "post-hackathon" split. Produces docs/butterbase/02-plan.md.
Use as the RAG build stage of the Butterbase journey. Implements the RAG section of 02-plan.md by delegating to rag-dev. Calls manage_rag_content (create_collection, ingest_document). Skipped if the plan has no knowledge-base feature.
Use when building knowledge bases, ingesting documents, running semantic search, or adding LLM-synthesized Q&A over private content with Butterbase RAG
Compares tools or implementations through reproducible A/B workloads, correctness oracles, and controlled measurements. Use to choose alternatives; not to optimize a known bottleneck.
Design discipline-specific critical thinking tasks grounded in knowledge-contingent reasoning rather than generic skills. Use when embedding higher-order thinking into subject content.
Design a structured outdoor learning sequence embedding curriculum objectives in an available outdoor space. Use when planning lessons in school grounds, parks, or local natural environments.
Design a critical thinking task targeting specific skills like evaluating evidence, identifying bias, or analysing arguments. Use when embedding critical analysis into subject lessons.
Slow down interpretation from observation to action. Use when students or adults need to examine assumptions in conflict, dialogue, or inquiry.
Framework for measuring and tracking agent response quality over time. Detects regressions before they reach production. Use when evaluating agent changes, auditing quality, or establishing performance baselines.
Competitive analysis - feature matrix, SWOT, market positioning, benchmark.
LLM Tuning Patterns
Diagnose marketing performance for global businesses — root cause analysis, 5-Whys, 48-hour action plan. Has 4 region variants for benchmarks (US/EU/SEA/LATAM). Reads `.agents/product-marketing-context-global.md`. INCLUDES Dropshipping KPI section (ROAS, BE-ROAS, profit margin, CAC). Trigger: 'performance review', 'ad performance', 'marketing diagnosis', 'KPI analysis', 'dropshipping ROAS'.
Phan tich doi thu canh tranh 3 tang (truc tiep, gian tiep, thu cap) — dinh vi, SWOT, content benchmark, tim khoang trong thi truong
>- Light 科研主线第 2 步·数据工程：**找得到且用得起的数据**（来源/许可/版本/大小/split）+ **提 idea 前先判数据可行性** （数据够不够支撑研究/统计功效）+ **防数据泄漏**（顶会拒稿高频雷）。何时用：用户要找/选/下载公开数据集，或给了数据问 "能不能做研究/够不够/质量行不行" / 要清洗·处理缺失异常·特征工程·划分数据集·数据增强 / 自建数据集（采集·标注规范· 隐私合规·发布） / 怀疑训练测试串了数据(泄漏) / 提 idea 前评数据基础。 触发词：数据够不够 / 数据可行性 / 数据质量 / 数据泄漏 / 防穿越 / train test 重叠 / 怎么划分 / 交叉验证 / 标注规范 / 一致性 IAA / 自建数据集 / 样本量够吗 / 统计功效 / 找数据集 / 数据许可 / dataset search / data leakage / feasibility / data split / annotation。核心纪律： **数据泄漏 = critical 一票否决**（标准化早于划分/时序穿越/实体重叠/目标编码穿越）；**数据不足以支撑 idea = 拦在 idea 前（回边 2⊣3，补数据/改 idea）**；功效是经验阈值非 power analysis；泄漏检测是启发式有边界，不吹"查全了"。
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when: keywords, file_patterns, code_patterns.
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. Orchestrates context across multi-agent workflows, enterprise AI systems, and long-running projects with 2024/2025 best practices. Use PROACTIVELY for complex AI orchestration.
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
| Extract per-subsection “anchor facts” (NO PROSE) from evidence packs so the writer is forced to include concrete numbers/benchmarks/limitations instead of generic summaries.
| 情商（EQ）训练专家系统——基于Mayer-Salovey能力模型与Goleman混合模型的 完整情商培养框架。涵盖自我意识、自我管理、社会意识、关系管理四大维度， 提供科学评估工具（MSCEIT/EQ-i 2.0/TEIQue）与实用训练方法。 触发词：「情商训练」「EQ提升」「情绪智力」「情绪管理」「情商测评」 适用场景：个人成长、职场发展、领导力培训、心理咨询辅助
| 机器之心/Synced（国内首家系统性AI科技媒体）的AI内容创作思维——论文级深度+量化驱动+学术与产业双线并跑+产品化媒体运营。 触发词：「机器之心视角」「像机器之心那样写」「Synced Review」「AI论文解读」「SOTA评测」「AI产业分析」「GMIS大会」。 擅长：顶会论文拆解报道（ICLR/NeurIPS/CVPR）、AI模型数据评测（SOTA平台）、产业趋势三层推演（技术→商业→生态）、AI中国年度评选、学术中立+产业判断、PRO会员通讯。
| 赛博禅心（大聪明，技术深度型AI博主）的AI科技自媒体创作思维——技术散文·反热潮·深度拆解·冷静旁观。 触发词：「赛博禅心视角」「像赛博禅心那样写」「AI技术深度解读」「AI论文解读」「AI行业大事记」「踏马的Agent」。 擅长：AI模型技术报告拆解、AI行业宏观分析、AI热点事件犀利点评、技术报告人话翻译、AI行业月刊/大事记、Agent/OpenClaw生态深度观察。
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Discover Civitai models with the BUILT-IN search_civitai_models tool and install/generate them locally — find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).
Train custom LoRAs with ostris AI-Toolkit — covers WAN 2.2/2.1 (people, styles, video motion) and Z-Image (Turbo & Base, low-VRAM image LoRAs). Use when the user wants to train a WAN or Z-Image LoRA; covers local + RunPod setup, dataset prep, key params, and using the result in a ComfyUI workflow.
Train a custom anime LoRA on the ANIMA base model — Citron's local Gradio trainer (kohya sd-scripts), <6GB VRAM, character/style LoRAs; covers setup, dataset prep, training params, and using the result in the anima-base workflow
Run the ComfyUI agent locally for FREE — no subscription, no API key, fully offline — using our gemma4 models fine-tuned on the comfyui-mcp tool suite via Ollama. Use when the user asks about running locally, running for free, offline use, avoiding API costs, Ollama setup, or which local model to pick.
Train a character/identity LoRA locally on FLUX.1-dev via the comfyui-mcp train_* tools (GPU Docker + ostris ai-toolkit). Use when the user wants to train a LoRA of a person/character from their photos on the local GPU — covers dataset prep, launch, monitoring, and using the result in ComfyUI. For WAN/Z-Image training via the ai-toolkit UI see ai-toolkit-trainer.
Stand up and run a LinkedIn employee advocacy program for a marketing or sales team. Covers 14-day launch playbook, brand-guideline governance, per-post time budget, cadence benchmarks, and team ROI (reach, engagement, pipeline). Triggers on "employee advocacy", "get the team posting", "scale LinkedIn across team", "advocacy ROI".
Install, observe, tune, and enforce Sponsio: a runtime contract layer for LLM agents that blocks unsafe tool calls and scores output quality against declared rules. Use when the user wants to set up / add / install Sponsio, add guardrails or runtime safety to an LLM agent, generate or refine a sponsio.yaml, audit tool configurations for risks (data leaks, unguarded writes, missing confirmations), explain or review existing contracts, check what Sponsio would have blocked (`sponsio report`), move from observe to enforce mode, or debug why a contract is (or isn't) firing. Triggers on phrases like "set up sponsio", "add sponsio", "install sponsio", "add guardrails", "monitor my agent", "harden my agent", "audit my agent", "generate contracts", "explain my sponsio.yaml", "sponsio report", "flip to enforce", "false positive", "why is this rule firing".
Use this skill to explain why the Compose compiler classified a class or composable parameter as stable, runtime, unknown, or unstable. Covers the 12-phase inference algorithm, the five compiler-level stability types (Certain / Runtime / Unknown / Parameter / Combined), the generic bitmask encoding (Pair=0b11, ImmutableList=0b1), the Known Stable Constructs registry, and the runtime `$stable: Int` field generated by `@StabilityInferred`. Use when the developer asks "why is X classified as Y?", when a stability report shows a surprising `runtime stable`, `unknown`, or `unstable` verdict, when generics, inheritance, cycles, interfaces, or cross-module classes are involved, or when the user mentions `$stable`, `@StabilityInferred`, separate compilation, or "the compiler thinks my class is unstable but it looks fine".
Expert blueprint for educational games including gamification loops (learn/apply/feedback/adapt), progress tracking (student profiles, mastery %), adaptive difficulty (target 70% success rate), spaced repetition, curriculum trees (prerequisite system), and visual feedback (confetti, XP bars). Use for learning apps, training simulations, or edutainment. Trigger keywords: educational_game, gamification, adaptive_difficulty, spaced_repetition, student_profile, curriculum_tree, mastery_tracking.
> Context management engine for AI coding agents. Use when building agent memory systems, optimizing context windows, allocating token budgets, designing RAG pipelines for code, or managing persistent multi-session agent state.
> RAG system, selecting a chunking strategy, choosing a vector database, optimizing retrieval quality, or evaluating with RAGAS metrics.
> Computer vision engineering for object detection, segmentation, and visual AI, covering CNN and Vision Transformer architectures and ONNX/TensorRT deployment. Use when building detection pipelines, training models, or optimizing inference.
> ML engineering skill for productionizing models, building MLOps pipelines, and integrating LLMs. Covers model deployment, feature stores, drift monitoring, RAG systems, and cost optimization.
> Prompt engineering and LLM evaluation. Use when optimizing prompts, designing prompt templates, evaluating LLM outputs, building agentic systems, implementing RAG, creating few- shot examples, or designing structured-output workflows.