Total 50,681 skills, AI & Machine Learning has 8495 skills
Showing 12 of 8495 skills
Optimize and structure context for agents and LLMs by reducing noise, prioritizing relevance, organizing memory, defining constraints, and managing token budgets.
Root cause analysis on production LLM traces. Diagnoses why an LLM application is failing — works from eval judge verdicts, runtime errors, or structural anomalies depending on what signals are present. Walks the span tree from symptom to root cause. Use when user says "what's wrong with my app", "why is my eval failing", "analyze errors", "root cause analysis", "diagnose failures", or wants to understand production failure patterns.
Refresh AI's understanding of code. Use this skill when the user mentions terms like "refresh", "re-understand", "refresh cache", "reload", etc. This skill compares all modified files, re-reads and understands the code that may have been modified by humans, ensuring that the AI's context is synchronized with the latest code state.
Install cuOpt for Python, C, or as a server (pip, conda, Docker) — system requirements, install commands, and verification. Use when the user wants to install or verify cuOpt for any user-facing interface. For building cuOpt from source or contributing to cuOpt, see cuopt-developer.
Summarize a video by calling the VLM NIM or the Long Video Summarization (LVS) microservice directly. For short videos (under 60s) call the VLM's OpenAI-compatible chat completions endpoint; for long videos (60s or longer) call the LVS microservice. Use when asked to summarize a video, describe what happens in a video, analyze a recording, call or debug LVS summarize/model/health/recommended-config/metrics endpoints, or configure and troubleshoot the LVS service that backs long-video summarization.
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integrating TileGym kernels into `transformers` models.
Structured framework for verifying numerical parity of HF<->MCore weight conversions. References existing tools and the add-model-support skill.
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.
Use when debugging a Nemo Gym run or reward profiling job. Covers rollout collection failures, empty or partial JSONL outputs, stale materialized inputs, verifier/schema errors, Ray or Slurm issues, vLLM readiness, judge failures, tool/sandbox failures, cache problems, and throughput bottlenecks.
Use when the user has a video + a target-language SRT and wants the video to actually speak that language — generates a time-aligned TTS voice dub. Routes by voice ID — Volcano (豆包) TTS for Chinese, edge-tts neural for any language. Defaults to one voice (single-speaker); opt-in multi-speaker via visual diarization. Outputs `*_<lang>_dub.mp4` with the dub audio in place of the original. Final mixing (audio bed + burn-in) is handed off to `/wjs-burning-subtitles`. Triggers — "配音", "中文配音", "Chinese dub", "voice over this", "dub the video", "TTS this SRT", "different voice for each speaker".
INTERNAL sub-agent for blind 9-dimensional rubric scoring. **NOT a user-facing skill — do NOT invoke from the main conversation.** It is called via the Task tool by cheat-score / cheat-predict / cheat-bump to generate a context-isolated score for a script. It ONLY accepts script_path + rubric_notes_path; any other input will be refused. It outputs strict JSON: 9 dimensions × {score 0-5, confidence enum, one-line reason}. **It strictly refuses to read** .cheat-state.json, predictions/*, retro sections, or any content that may leak post-publish data. This is Channel B in the 3-channel calibration model (A=main, B=blind sub-agent, C=cross-model).
Terminal AI agent CLI for Google Gemini and Antigravity models with slash commands, MCP server support, and coding assistance