Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
End-to-end AI system evaluation - model selection, benchmarks, cost/latency analysis, build vs buy decisions. Use when selecting models, designing eval pipelines, or making architecture decisions.
Collecting and using user feedback - explicit/implicit signals, feedback analysis, improvement loops, A/B testing. Use when improving AI systems, understanding user satisfaction, or iterating on quali…
ML development workflow covering experiment design, baseline establishment, iterative improvement, and experiment tracking best practices.
Generate text in your voice using your AUTHOR_VOICE.md document. Provide a topic or prompt as argument.
Generate and update HTML dashboards for LLM usage (Claude, Gemini, Kiro, VS code, Cline, etc). Use when the user wants to visualize their AI coding assistant usage statistics, view metrics in a web in…
Use when designing a Retrieval-Augmented Generation pipeline. Covers document processing, chunking strategy, embedding pipeline, vector database selection, retrieval optimization, and context assembly…
Coordinate with other AI agents on behalf of your human
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Dete…
Protecting AI applications - input/output guards, toxicity detection, PII protection, injection defense, constitutional AI. Use when securing AI systems, preventing misuse, or ensuring compliance.
ML framework best practices for PyTorch, TensorFlow, scikit-learn, and modern ML libraries including training patterns and optimization.
ML serving optimization techniques including batching, caching, model compilation, and latency reduction for production ML systems.
Captures writing style/voice into AUTHOR_VOICE.md so AI can write like the user. Use when asked to match tone, write like me, replicate voice, or capture writing style for content generation.
Unified writing system with intelligent model routing. Default: Claude. Options: GLM-4.7 (cheapest), GPT-4o/mini, Gemini, Grok. Includes browser automation for web interfaces. Cost-aware routing based…
Use this skill when scoring or comparing a generated diagram against a human reference. Triggers on "score this diagram", "evaluate my diagram", "compare to reference", or "how accurate is this". Appl…
Run AIMLAPI (OpenAI-compatible) LLM and reasoning workflows, including chat completions, tool-style prompts, and structured outputs. Use when Codex needs to craft prompts, run LLM calls, or script rea…
Give your agent persistent memory and real-time personal context via Dytto — the context API for AI agents. Use when you need to know about the user (who they are, what they care about, behavioral pat…
Optimizing AI inference - quantization, speculative decoding, KV cache, batching, caching strategies. Use when reducing latency, lowering costs, or scaling AI serving.
Core ML systems concepts including ML lifecycle, system architecture, requirements, and design principles for production ML.
Applies AI-first development patterns for 10-100x productivity through specification-driven generation and leverage multiplication. Use when developing features with AI assistance or optimizing develo…
Volume level (0-100, required when set)
Analyze YOUR video recordings before publishing. Evaluates voice (pace, pitch, volume), facial expressions (emotions, eye contact, smiles), and content (filler words, structure). Helps improve your Hi…
Use this skill when creating a methodology diagram from research text. Triggers on "make a diagram", "visualize this methodology", "diagram this process", or "generate a figure from this paper". Appli…
Implementation of the Dynamic Ethical Entity Personality (D.E.E.P.) v2 Framework. The cognitive architecture for agentic sovereignty and partnership.
Generate images using the Kusa.pics API.