Total 56,326 skills, AI & Machine Learning has 9380 skills
Showing 12 of 9380 skills
Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现实验", "implement experiments", "bridge", "从计划到跑实验", "deploy the plan", or has an experiment plan ready to execute.
Use when the user wants to configure, create, or update a SecondMe Skill/MCP integration from a local project, or needs help exposing existing project capabilities through MCP.
用于创建或更新技能包的完整指南。适用于用户希望将对话中的方法、经验、偏好沉淀为可复用技能，或对已有技能进行结构化优化的场景（含脚本、工作流、资源组织与打包发布）。
Use when decisions could affect groups differently and need to anticipate harms/benefits, assess fairness and safety concerns, identify vulnerable populations, propose risk mitigations, define monitoring metrics, or when user mentions ethical review, impact assessment, differential harm, safety analysis, vulnerable groups, bias audit, or responsible AI/tech.
Encodes a continuous improvement loop for goal-seeking agents: EVAL, ANALYZE, RESEARCH (hypothesis + evidence + counter-arguments), IMPROVE, RE-EVAL, DECIDE. Auto-commits improvements (+2% net, no regression >5%) and reverts failures. Works with all 4 SDK implementations. Auto-activates on "improve agent", "self-improving loop", "agent eval loop", "benchmark agents", "run improvement cycle".
INVOKE THIS SKILL for LLM-as-judge evaluation workflows on Arize: creating/updating evaluators, running evaluations on spans or experiments, tasks, trigger-run, column mapping, and continuous monitoring. Use when the user says: create an evaluator, LLM judge, hallucination/faithfulness/correctness/relevance, run eval, score my spans or experiment, ax tasks, trigger-run, trigger eval, column mapping, continuous monitoring, query filter for evals, evaluator version, or improve an evaluator prompt.
CLI-based image generation from text prompts using Google Gemini APIs via Python. Use when user needs "generate image", "create image with AI", "gemini image", "text to image", "create sprite", or "generate character art". Supports model selection, batch generation, watermark removal, and background transparency. Do NOT use for web app image features (use nano-banana-builder), video/audio generation, or non-Gemini models.
Conversational discovery — adapts from quick scoping (3-5 questions) to deep interviews (multi-round). Talk until we're clear, then build. Produces inline decisions; optionally saves spec.md or scope contract. Not for multi-perspective debate (use agent-room). Not for decomposing work (use task-breakdown).
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.
Auto-activates when working with implementation plans. Triggers on "continue the plan", "next task", "what's the plan status", "run task 2.1", or when user references plans/*.plan.md files. Not for creating plans - use /superplan command for that.
[BETA] Execute work with external delegate support. Same as ce-work but includes experimental Codex delegation mode for token-conserving code implementation.
Convin platform help — AI-powered contact center QA, coaching, and conversation intelligence. Use when setting up Convin automated QA scoring, Convin Real-Time Assist not surfacing prompts, Convin transcription missing speakers or inaccurate with accents, Convin audits hanging or calls delayed on dashboard, Convin AI Phone Call agent for outbound, Convin LMS agent training, or evaluating Convin vs Observe.AI vs Cresta vs Balto vs Enthu.AI for contact center QA. Do NOT use for CCaaS platform selection (use /sales-ccaas-selection) or building a coaching program (use /sales-coaching).