Total 56,869 skills, AI & Machine Learning has 9457 skills
Showing 12 of 9457 skills
Long-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, and practical patterns from DSV3, Qwen3, and Qwen3-Next long-context experiments.
MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.
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".
Use whenever the user mentions LLM prompt/prefix cache misses, cached_tokens=0, cache_read_input_tokens/cache_creation_input_tokens, prompt_cache_key, cache_control/cachePoint placement, stable prefixes, tool/schema stability, TTFT/prefill latency, OpenAI/Claude/Bedrock/OpenRouter routing, vLLM/SGLang KV reuse, or LLM cost/speed regressions on repeated long prompts. Use when reviewing LLM request shape changes: prompt text, message order, request builders, tools, schemas, response_format, provider API surface, model/router settings, agent loop structure, context compaction, or inference deployment. Use for speeding up agents only when prompt-cache stability, TTFT, or cache cost is central. Do not use for generic prompt writing, generic RAG design, token counting, or non-LLM performance.
ADBPG Knowledge Base Management: Create knowledge bases, upload documents, search, Q&A. Triggers: "knowledge base", "document library", "document upload", "knowledge search", "RAG", "Q&A", "embedding", "ADBPG", "AnalyticDB PostgreSQL"
Build a production-ready regression model on tabular data using XGBoost with conformalized quantile regression for prediction intervals. Use when the user needs to predict a continuous target from tabular features (price, sales, demand, time-to-event, score) and report uncertainty alongside the point estimate. Default to this for any tabular regression task.
Dynamic MCP server discovery and code-mode execution via central registry. Use for multiple MCP integrations, tool discovery, progressive disclosure, or encountering MCP context bloat, changing server sets, large tool sets.
Deploy and use an LLM-powered public opinion analytics assistant that crawls 26 hot lists from 15 platforms, performs sentiment analysis, topic clustering, and multi-channel alerting
Vectara integration. Manage data, records, and automate workflows. Use when the user wants to interact with Vectara data.
Forensic audit of the user's recent Claude Code sessions to surface step-change workflow improvements — not marginal ones. Use when the user asks to "audit my Claude Code sessions", "analyze how I use Claude Code", "find patterns in my usage", "improve my Claude Code workflow", "review my sessions", "find leverage in my setup", or wants to understand where their Claude Code setup is leaking time. Samples dozens of real transcripts, extracts quantitative signal via scripts, uses parallel subagents for deep reads, then synthesizes into a short prioritized report with drafted implementations (new skills, CLAUDE.md rules, hooks, settings diffs) that the user can install directly. Trigger even when the user doesn't say the word "audit" — if they're asking about improving or reviewing their Claude Code habits at scale, use this skill.
Use this skill when pricing, ranking, or researching X/Twitter KOLs for a creator marketing campaign, especially when the user provides handles, asks for batch KOL analysis, wants outreach recommendations, or wants an agent-native version of the KOL Pricing framework. Prefer UnifAPI MCP tools for public X data, then run the deterministic pricing workflow before drafting outreach.
Generate images with gpt-image-2 through an OpenAI-compatible Image API using the current OPENAI_API_KEY, OPENAI_BASE_URL, or CUSTOM_IMAGE_URL environment variables. Use when the user asks to call gpt-image-2 via API/CLI, /v1/images/generations, the prior /api/image/generate endpoint flow, or wants the faster API route instead of Codex CLI image_generation/session extraction.