Total 56,633 skills, AI & Machine Learning has 9429 skills
Showing 12 of 9429 skills
Log a workflow mistake, fix its root cause, and graduate the lesson to learned memory. Use when the agent makes an error you want to prevent recurring.
Architect/CR agent role. Receives git diff, task spec, ADRs, design doc, and project conventions. Reviews code and returns APPROVED or CHANGES_REQUIRED. Do NOT invoke directly — dispatched by team-execute.
Active knowledge intelligence. Runs Mine → Grow → Defrag cycle. Mine extracts signal from git/.agents/code. Grow validates existing learnings against current reality, synthesizes cross-domain insights, traces provenance chains, and identifies knowledge gaps. Defrag cleans up. Triggers: "athena", "knowledge cycle", "mine and grow", "knowledge defrag", "clean flywheel", "grow knowledge".
Recursive codebase analysis using the RLM paradigm. Use when: analyzing large codebases (100+ files), investigating cross-cutting patterns, recursive decomposition of complex code questions, scanning for issues across entire repos. Triggers: analyze this codebase, how does X work across the codebase, scan all files for Y, recursive analysis, RLM.
OpenClaw stock analysis skill for US/HK/CN markets. Combines QVeris data sources (THS, Caidazi, Alpha Vantage, Finnhub, X sentiment) for quote, fundamentals, technicals, news radar, morning/evening brief, and actionable investment insights.
Bulk AI image generation via the BulkGen API. Use whenever users ask to generate one or many AI images — even simple requests like "generate an image", "edit this image", "make variations", or "create AI art" should trigger this skill. Handles single images, grids, batches, variations, reference-image editing, expiring result downloads, and HTML preview handoff pages. Works for English and Chinese requests like "生成图片", "批量生成", "图生图", "做一个 3x3 宫格", or "给我做九宫格变体".
Use Chanjing Avatar API for lip-syncing video generation
Multi-agent orchestration layer for OpenAI Codex CLI. Provides 30 specialized agents, 40+ workflow skills, team orchestration in tmux, persistent MCP servers, and staged pipeline execution.
Integration patterns for Mapbox MCP Server in AI applications and agent frameworks. Covers runtime integration with pydantic-ai, mastra, LangChain, and custom agents. Use when building AI-powered applications that need geospatial capabilities.
Use when designing custom voices with Alibaba Cloud Model Studio CosyVoice customization models, especially cosyvoice-v3.5-plus or cosyvoice-v3.5-flash, from a voice prompt plus preview text before using the returned voice_id in TTS.
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
Keep Codex skills aligned with durable feedback by distilling comments, corrections, and repeated guidance into the narrowest existing skill. Use on every turn, and especially when feedback reveals a reusable rule, a repeated miss, or a better abstraction that should replace a task-specific example.