Total 50,661 skills, AI & Machine Learning has 8492 skills
Showing 12 of 8492 skills
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
Real-time investment context from Primary Logic — LLM-ranked relevance and impact signals from podcasts, articles, X/Twitter, Kalshi, Polymarket, earnings calls, filings, and other monitored sources across public and private companies.
Use when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task decomposition, progress tracking, and autonomous execution using Codex non-interactive mode with auto-continuation. Trigger phrases include autonomous, long-running task, multi-session, 自主执行, 长时任务, autonomous skill.
Generate images using Google's Gemini API — hero backgrounds, OG images, placeholder photos, textures, and style-matched variants. Uses free-tier models for drafts, paid for finals. No dependencies beyond Python 3. Trigger with 'generate image', 'gemini image', 'make a hero background', 'create placeholder photo', 'generate OG image', 'AI image', or 'need an image for'.
Voice design workflows with Alibaba Cloud Model Studio Qwen TTS VD models. Use when creating custom synthetic voices from text descriptions and using them for speech synthesis.
Create and manage Alibaba Cloud IMS video translation jobs via OpenAPI (subtitle/voice/face). Use when you need API-based video translation, status polling, and job management.
Fetches Andrej Karpathy's curated RSS feed, reads ALL original articles, and generates a themed daily briefing document with citation links. This skill should be used when the user asks to generate a Karpathy RSS daily report, fetch Karpathy's curated RSS updates, or create an AI/tech daily briefing based on Karpathy's sources. Trigger phrases include "Karpathy Daily Report", "Karpathy RSS", "Generate Daily Report", "RSS Briefing", "Karpathy Daily".
Request judgment from random humans when uncertain about subjective decisions. Crowdsourced opinions on tone, style, ethics, and reality checks. CRITICAL - Responses take minutes to hours (or may never arrive).
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
Structured error classification and recovery during autonomous operation. Classify runtime errors, apply retry strategies with backoff, maintain error logs, and escalate intelligently. Activate when encountering API failures, build tool crashes, file permission issues, or unexpected runtime errors during autonomous work. Triggers on: "error recovery", "retry", "API failure", "crash recovery", "service unavailable".
Skills retrospective and improvement. Use when: - User asks to "review", "retrospect", "summarize" or "复盘" skills - User wants to analyze skills issues from the conversation - User requests skills optimization or improvement - End of conversation or after significant skill usage
Scaffold a new integration-type "seed skill" — a SKILL.md with reference assets and prompts.jsonl entries that teach an agent to generate working, testable integration code from scratch. - Use when: developer wants to create a new skill for an SDK or framework integration that agents should be able to implement and test - Ask first: Is this an integration skill (code generation + tests) or a tool skill (CLI wrapper with no tests)? Only proceed with this skill for integration-type skills.