143 skills · sorted by relevance
Design loops that improve an agent’s own prompts, workflows, or execution code from failure records. Define bounded edits, preserve candidate histories, and accept changes through independent tests that check improvements and regressions.
Configure LLM inference and serving on NVIDIA GPUs with TensorRT-LLM. Covers quantization, which reduces numerical precision, batching requests during generation, and distributing models across GPUs to improve processing capacity and response times.
Audit whether a website can be found, crawled, and cited by AI answer engines such as ChatGPT Search, Perplexity, Google AI Overviews, and Microsoft Copilot. Use when someone asks why their brand is missing from AI answers, whether AI crawlers can read their site, how to get cited by ChatGPT or Perplexity, or asks for a GEO or AEO (generative / answer engine optimization) review. Produces a citation baseline across buyer-intent prompts, a crawler-access check, a citability review of named pages, and a ranked fix list. Not for keyword rank tracking, paid search, or pages behind a login.
The English summary is being prepared. Showing the original description.
Comet preset path: Non-bug small changes (tweak). Skip brainstorming and full plan, directly open → lightweight build → light verify → archive. Applicable for copy, configuration, documentation or prompt local optimization.
The English summary is being prepared. Showing the original description.
Auto-activate CCS CLI delegation for deterministic tasks. Parses user input, auto-selects optimal profile (glm/kimi/custom) from ~/.ccs/config.json, enhances prompts with context, executes via `ccs {profile} -p "task"` or `ccs {profile}:continue`, and reports results. Triggers on "use ccs [task]" patterns, typo/test/refactor keywords. Excludes complex architecture, security-critical code, performance optimization, breaking changes.
The English summary is being prepared. Showing the original description.
Full-lifecycle blog engine with 31 sub-skills, 12 content templates, 5-category 100-point scoring, and 5 specialized agents. Routes user requests to the right sub-skill: writing, rewriting, analysis, outlines, audits, schema, charts, images, repurposing, AI citation SEO, FLOW framework prompts, topic-cluster execution, and multilingual publishing. Optimized for Google rankings around the May 2026 Core Update, E-E-A-T, and AI citations as one SEO discipline. Supports any platform (WordPress, Next.js MDX, Hugo, Ghost, Astro, Jekyll, 11ty, Gatsby, HTML). Use when user says "blog", "write a blog", "blog post", "blog strategy", "content brief", "editorial calendar", "blog audit", "blog optimization", "topic cluster", "multilingual blog", "FLOW framework", or any /blog subcommand. Sub-skill descriptions cover narrower triggers.
The English summary is being prepared. Showing the original description.
Optimizes Simulink models for Embedded Coder generated code. Use when asked to optimize or improve generated code, or reduce code metrics for a Simulink model. Targets: execution time, memory footprint (RAM, ROM, stack, data copies), code size, MISRA compliance, or any semantically similar generated-code metric. Works iteratively — measures baseline, suggests changes, applies, and re-measures to confirm improvement. Triggers can be prompts similar to: optimize generated code runtime, reduce runtime, shrink code size, improve code efficiency, reduce memory usage, speed up generated code, follow MISRA compliance and so on. CAUTION: Do NOT attempt to optimize Simulink models for generated code efficiency without following this skill — the iterative measurement, gating, and rollback workflow is essential for safe optimization.
The English summary is being prepared. Showing the original description.
Reduce LLM API and infrastructure costs through model selection, prompt caching, batching, caching, quantization, and self-hosting strategies. Track spend by team and model, set budgets, and implement cost-aware routing.
The English summary is being prepared. Showing the original description.
This skill should be used when the user asks to "batch LLM requests", "should I use the batch API", "estimate batch vs realtime cost", "design a bulk LLM job", or "process thousands of prompts cheaply".
The English summary is being prepared. Showing the original description.
Use when optimizing Godot games — profiler, draw calls, physics tuning, memory management, and common bottlenecks
The English summary is being prepared. Showing the original description.
Manage context and prompt-cache costs without losing task state. Use for context management, orchestration cost, token budgets, large tool outputs, cache misses, or long-running conversations.
The English summary is being prepared. Showing the original description.
Autonomous experiment loop: hypothesize > modify > test > evaluate > keep/discard > repeat. Run N experiments automatically with measurable metrics. Works for performance optimization, A/B testing, prompt engineering, and any measurable improvement task.
The English summary is being prepared. Showing the original description.
Operational skill hub for LLM system architecture, evaluation, deployment, and optimization (modern production standards). Links to specialized skills for prompts, RAG, agents, and safety. Integrates recent advances: PEFT/LoRA fine-tuning, hybrid RAG handoff (see dedicated skill), vLLM 24x throughput, multi-layered security (90%+ bypass for single-layer), automated drift detection (18-second response), and CI/CD-aligned evaluation.
The English summary is being prepared. Showing the original description.
Place trusted contextual information into prompts or agent state using explicit boundaries, provenance, and templates. Use when relevant context has already been selected and must be inserted safely; use context-retrieval to find it or context-optimization to choose and order it.
The English summary is being prepared. Showing the original description.
当系统提示面向移动端（手机、平板）场景时调用。适用于 iOS/Android 应用内 AI 助手、移动端聊天界面、响应式输出的系统提示设计。不适用于桌面端优先的场景，不适用于移动端 UI 开发（非提示层），不适用于语音场景（语音场景使用 voice-optimization）。
The English summary is being prepared. Showing the original description.
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。
The English summary is being prepared. Showing the original description.
Use this skill to turn generated, captured, scanned, or modeled 3D output into production-ready standalone assets for DCC, real-time engine, web, or interchange delivery. It covers requirements, topology repair, scale and axes, UVs, PBR baking, LODs, static and skeletal readiness, rig handoff, optimization, glTF/USD/FBX delivery, validation, QA, and rights/provenance. Do not use it for provider-specific generation prompts, full scene/world building, mocap operation, or exact CAD/manufacturing work.
The English summary is being prepared. Showing the original description.
World-class expertise in measuring, attributing, and optimizing AI-generated content performance. Combining data science rigor with content strategy intelligence to answer the questions traditional content analytics can't: Is AI content performing? Which AI variations convert? What's the true ROI of AI vs traditional content creation? This isn't vanity metrics for robots. This is the discipline of proving AI content drives business outcomes - and using that data to make AI content systems better, faster, and more profitable. Built on the principles of companies like Jasper, Copy.ai, and Notion who've scaled AI content operations with measurement as the foundation. Use when "ai content performance, ai content analytics, measure ai content, ai content roi, ai vs human content, ai content attribution, ai content testing, ai variation testing, ai content dashboard, ai content metrics, prompt performance, ai content conversion, ai content quality score, content velocity, ai content efficiency, ai-content, analytics, measurement, attribution, roi, ab-testing, performance, optimization, data-driven, content-analytics" mentioned.
The English summary is being prepared. Showing the original description.
Implement comprehensive observability for LLM applications including tracing (Langfuse/Helicone), cost tracking, token optimization, RAG evaluation metrics (RAGAS), hallucination detection, and production monitoring. Essential for debugging, optimizing costs, and ensuring AI output quality. Use when ", llm-monitoring, tracing, langfuse, helicone, cost-tracking, ragas, evaluation, hallucination-detection, prompt-caching" mentioned.
The English summary is being prepared. Showing the original description.
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, " mentioned.
The English summary is being prepared. Showing the original description.
Suede-affiliated onboarding and activation strategy for first-run sequencing, empty states, setup checklists, activation milestones, time to value, and retention-linked measurement. Use when users sign up but fail to reach first value or the product needs a new first-session flow. NOT FOR: registration optimization (use suede-signup), lifecycle email sequences (use suede-emails), or monetization prompts (use suede-paywalls).
The English summary is being prepared. Showing the original description.
Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, cost optimization. Use for AI pipelines or eval harnesses.
The English summary is being prepared. Showing the original description.
Run metric-driven optimization loops. Use when improving measurable outcomes such as search relevance, clustering quality, build performance, prompt quality, or scored behavior through experiments.
The English summary is being prepared. Showing the original description.
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.
The English summary is being prepared. Showing the original description.