Total 55,837 skills, AI & Machine Learning has 9269 skills
Showing 12 of 9269 skills
Use when the user needs prompt design, optimization, few-shot examples, chain-of-thought patterns, structured output, evaluation metrics, or prompt versioning. Triggers: new prompt creation, prompt optimization, few-shot example design, structured output specification, A/B testing prompts, evaluation framework setup.
Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants voice consistency without generic AI writing tropes.
Use when generating talking, singing, or presentation videos from a single character image and audio with Alibaba Cloud Model Studio digital-human model `wan2.2-s2v`. Use when creating narrated avatar videos, singing portraits, or broadcast-style talking-head clips.
Prepare datasets and configure LoRA training for character consistency. Covers FLUX (AI-Toolkit, SimpleTuner, FluxGym) and SDXL (Kohya_ss) training with step-by-step guidance. Use when training custom character LoRAs.
Use when the user asks about finding people, managing their network, creating signals/intents, discovering opportunities, or anything related to Index Network. Always active when the Index Network plugin is loaded.
Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases. Triggers on: new/empty project setup for AI agents, AGENTS.md or CLAUDE.md creation, harness engineering questions, making agents work better on a codebase. ALSO triggers when users are frustrated or complaining about agent quality — e.g. 'the agent keeps ignoring conventions', 'it never follows instructions', 'why does it keep doing X', 'the agent is broken' — because poor agent output almost always signals harness gaps, not model problems. Covers: context engineering, architectural constraints, multi-agent coordination, evaluation, long-running agent harness, and diagnosis of agent quality issues.
Team-orchestrated implement → verify → fix → archive cycle
This skill should be used when the user asks to "wrap up session", "end session", "session wrap", "/wrap", "document learnings", "what should I commit", or wants to analyze completed work before ending a coding session.
LLM inference via paid API: OpenAI-compatible chat completions proxied through x402 providers. Supports Kimi K2.5, MiniMax M2.5. Uses x_payment tool for automatic USDC micropayments ($0.001-$0.003/call). Use when: (1) generating text with a specific model, (2) running chat completions through a pay-per-request LLM endpoint, (3) comparing outputs across models.
Operate OpenWord end-to-end for live adventure sessions. Use when Codex needs to download/install/start OpenWord, guide a human player in the browser, or play autonomously through REST API (create/load game, do_action loop, state/image retrieval), including configuring GEMINI_API_KEY and sharing interesting scenes and choices during play.
AI pair programming with real-time screen and audio context. Use when the user wants to record their screen, start/stop recording, or get context from what they're doing.
Analyze finance text sentiment using FinBERT or LLM. Use when the user needs to determine the sentiment (positive/negative/neutral) and score of financial text markets.