voice-mode
Offline-first voice I/O super-skill: speak via say, listen via listen, and run agent-orchestrated duplex dialogue.
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Offline-first voice I/O super-skill: speak via say, listen via listen, and run agent-orchestrated duplex dialogue.
Context-aware requirements analysis skill. Automatically triggered when users request "to complete specific requirements by reading existing AI documents or AI_CONTEXT documentation". The skill intell…
Download audio from YouTube and Twitter/X links
A smart YouTube video downloader with multiple strategies, auto-retry, intelligent cookie management, and subtitle support
Use when designing embedding strategies that fuse semantic and structural information for knowledge graphs. Invoke when user mentions node embeddings, structural embeddings, semantic embeddings, contr…
Use when you've identified candidate symmetries and need to map them to mathematical groups for architecture design. Invoke when user mentions cyclic groups, dihedral groups, Lie groups, SO(3), SE(3),…
Quick-reference for using external AI models in orchestration workflows. External models are invoked via Bash+claudish CLI (deterministic, 100% reliable). Use when confused about how to run external m…
Forensic style analysis of a writing sample. Measures sentence length, rhythm, punctuation DNA, vocabulary, tone, rhetorical devices, and verbal tics. Outputs a Style DNA report. Use when asked to ana…
Gives a balanced pros and cons analysis of any idea, decision, or topic. Type a subject and get both sides.
Request assistance from the assistant, suitable for task scenarios such as long text reading comprehension, web searching, web page reading, article translation, and web and front-end interface creati…
Generate dependency diagrams from code or architecture. Traces code-level dependencies (hooks, queries, providers, components) or maps high-level system architecture. Outputs Mermaid diagrams in markd…
Summarize Discord chat messages across servers. Use when user asks for chat summary, digest, highlights, recap, or overview of Discord conversations.
Use when prompts produce inconsistent or unreliable outputs, need explicit structure and constraints, require safety guardrails or quality checks, involve multi-step reasoning that needs decomposition…
Quantitative framework for detecting AI-generated "slop" in prose through systematic analysis of structural, lexical, rhetorical, and logical patterns. Use when analyzing text authenticity, evaluating…
Use when a user wants to generate a Mermaid diagram, visualize a system flow, or says "create a diagram", "mermaid", "visualize the flow", "diagram this". Also use when a design doc or implementation …
Automatically applies when choosing LLM models and providers. Ensures proper model comparison, provider selection, cost optimization, fallback patterns, and multi-model strategies.
Project fingerprinting, association rule mining (Apriori), and cosine-similarity plugin recommendations
Generate AI images, videos, audio and 3D content using fal.ai's 500+ models. Supports Kling V3, FLUX.2, Grok Imagine, Veo 3.1, MiniMax, Hunyuan 3D, OpenRouter LLMs and more via queue-based generation.
Make well-calibrated probability estimates using superforecasting methodology. Use when user asks about probability, likelihood, chance, odds, "will X happen", "when will X happen", "how much will X c…
Use when making predictions or judgments under uncertainty and need to explicitly update beliefs with new evidence. Invoke when forecasting outcomes, evaluating probabilities, testing hypotheses, cali…
Use when ML engineers need to identify symmetries in their data but don't know where to start. Invoke when user mentions data symmetry, invariance discovery, what transformations matter, or needs help…
Comprehensive guide for Tinker Cookbook supervised fine-tuning covering all patterns including high-level Cookbook abstractions, low-level API usage, streaming datasets, file-based data, Blueprint con…
Write a new article matching a specific author's voice using a Style DNA report as the blueprint. Takes a style-dna.md file and a topic, produces an article that hits the exact measured metrics. Use w…
Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus