Total 50,523 skills, AI & Machine Learning has 8481 skills
Showing 12 of 8481 skills
Resolves a PostHog experiment reference from natural language to a concrete experiment ID by browsing `experiment-list` (not feature-flag tools), with disambiguation when multiple experiments match. Use when the user names or quotes an experiment ("split test demo", "the File engagement boost experiment", "onboarding retention test", "landing page hero experiment", "pricing experiment"), describes it loosely ("the signup experiment", "my pricing test", "the one with the new checkout"), uses a relative reference ("latest", "most recent", "the one I created yesterday"), filters by status (running, draft, stopped, archived), or otherwise refers to an experiment by anything other than its concrete ID.
Guides research engineering and science on LLM tokens—hypotheses about context use, tokenization, compression, and inference efficiency; rigorous benchmarks (tokens per task, quality–cost Pareto); ablation design; instrumentation and reproducible logs; and research memos that inform product decisions. Use when designing token-efficiency experiments, measuring context utilization, comparing compression or routing methods, analyzing tokenizer effects, or writing technical reports on token/cost trade-offs—not for phased cost roadmaps and owners (ai-token-improvement-plan-engineer), production context pipeline implementation (ai-context-engineer), single-prompt edits (prompt-engineer), general non-token AI research (ai-researcher), or shipping features (ai-engineer).
One-shot autopilot orchestrator — runs the full spark-video pipeline (screenwriter ↔ director per-scene parallel → render chain-DAG parallel + per-clip review → stitch). User confirms at 4 gates (+ 1 mode gate at start + 1 BGM gate when bgm/ folder detected). Use when the user wants "make me an episode" in one command.
Write ML papers for NeurIPS/ICML/ICLR: design→submit.
Horizontal session personality overlay — auto-detects conversation mode from density signals, defaults casual, upgrades to structured only on sustained signal. Includes CommitMono aesthetic preference and MoE/thinking-chain runtime awareness.
Generate structured video transcripts from local files or video URLs using Gemini Files API. Use when a GitHub or Linear tracker item, comment, or attachment includes a screen recording, .mov, .mp4, or tracker-hosted video and you need a <video-transcripts> block instead of hand-written notes.
Generates YAML signal configs for agent simulation experiments. Use when the user wants to define what signals to track, how to extract them from run artifacts, and how to aggregate them into experiment-level metrics. Trigger when users say: "generate a signal config", "create signals for my experiment", "I want to track [metric]", "write a signal YAML", "set up extraction for [thing]", "how do I measure [behavior] across runs", "configure signals for [experiment]", "create a signal config", "create signal config file", or "build a signal config".
Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.). Use when you need to generate code for calling Gemini or OpenMaaS models, authenticate with GenAI SDK, OpenAI SDK, or legacy Agent Platform SDK, configure base URLs and global/regional endpoints, or troubleshoot 429 Resource Exhausted (DSQ), 400 User Validation, or 404 Not Found errors. Don't use for deploying models to endpoints or for running model evaluations.
How agentmemory wires into host coding agents via the connect command. Use when installing agentmemory into a specific agent, when asked which agents are supported, or when a connect adapter writes the wrong config path.
Metric-learning recognition (ml-recog) for fine-grained visual recognition. Learns embeddings for retrieval-based matching (e.g., retail product recognition) using triplet / contrastive losses. Use when training, evaluating, exporting, or running inference for a TAO metric-learning recognition model. Trigger phrases include "train metric learning", "ml-recog", "retrieval embeddings", "triplet loss recognition", "fine-grained matching".
Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for classifying temporal actions in video clips. Use when training, evaluating, exporting, or running inference on a TAO action-recognition model. Trigger phrases include "train action recognition", "video action classification", "RGB + optical flow action model", "TAO ActionRecognition".
Real-time stereo depth estimation using FastFoundationStereo (FFS), the distilled bp2 commercial variant of FoundationStereo. Predicts disparity maps from stereo image pairs with ~10× lower latency than full FoundationStereo. Use when training, evaluating, exporting, or running inference for a TAO FastFoundationStereo (FFS) model. Trigger phrases include "train fast stereo", "real-time stereo disparity", "FastFoundationStereo", "distilled stereo depth".