Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
This skill should be used when building production LLM applications in any language. It applies when implementing predictable AI features, creating structured interfaces for LLM operations, configurin…
Orchestrate multiple LLMs as a council, generating collective intelligence through peer review and chairman synthesis
Comprehensive LLM model evaluation and ranking system. Use when users ask to compare language models, find the best model for a specific task, understand model capabilities, get pricing information, o…
Local Compositionality Gadget
When the user provides location names, addresses, or landmarks that need to be converted to precise geographic coordinates. This skill uses mapping APIs to geocode locations, returning latitude/longit…
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond …
Record and share video messages with Loom - create screen recordings, manage video library, and track viewer engagement
Prepare for meetings by gathering context and creating comprehensive agendas
External LLM invocation. Triggered ONLY by @council,@probe,@crossref,@gpt,@gemini,@grok,@qwen.
Guide for using LLM utilities in speedy_utils, including memoized OpenAI clients and chat format transformations.
Design, operation, evaluation, and optimization of LLM applications. Includes prompt management, RAG construction, fine-tuning, evaluation pipeline, cost optimization, and production operation. To be …
local-finetune
Summarize noisy logs into likely causes and next steps. Use when a junior developer needs help interpreting logs.
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond …
Imported skill lora_ofl from anthropic
Use to maintain context across sessions - integrates episodic-memory for conversation recall and mcp__memory knowledge graph for persistent facts
Orchestrate multiple LLMs as a council, generating collective intelligence through peer review and chairman synthesis
Pydantic-AI agents, RAG, embeddings for Pulse Radar knowledge extraction.
LLMs, prompt engineering, RAG systems, LangChain, and AI application development
Look up the time zone of a given city and return the local time.
Multi-agent autonomous startup system. Triggers on "Loki Mode". Takes PRD to deployed product with zero human intervention. Requires --dangerously-skip-permissions flag.
Detect behavioral drift and alignment degradation over time.
Media processing = ffmpeg + imagemagick + sox.
Test, validate, and add new AI models to the eval suite. Use when user asks to add new models, test model access, check pricing, or update models.yml.