From thought to skill. From signal to structure.
-
Updated
Jun 30, 2026 - Python
From thought to skill. From signal to structure.
[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Record desktop workflows once and compile them into reusable AI-agent skills for reliable replay.
University for AI agents. 92 courses, 4400+ scenarios, any model via OpenRouter. Auto-training loops generate per-model SKILL.md documents. Works with Claude Code, OpenClaw, Cursor, Windsurf. No fine-tuning required.
AI assistant that learns your workflows — auto-generates skills, routes to the cheapest LLM, and replays every execution. Telegram · Slack · Discord · Matrix. One Rust binary, zero setup.
ARCHIVED — Skill generation tool. Absorbed into Gravity-Omega tool ecosystem.
Create custom domain expert skills through interactive dialogue — hire, summon, and manage your expert team for Claude Code
Turn development lessons into reusable skills — automatically. Analyze patterns, propose skills, sync improvements, check health.
Progressive-disclosure reflector for OpenCode — automatically analyzes conversations to discover reusable patterns and generate skills/rules
The skill that writes skills — a secure compiler pipeline that auto-generates OpenClaw skills from observed user patterns
Build self-updating skill trees for AI coding agents from codebases and PRDs to keep agents in sync with your code
The world's first skill-forging engine built for AI Agents in film & video production. 全球首个面向 AI Agent 的影视创作技能生成引擎。
Add a description, image, and links to the skill-generation topic page so that developers can more easily learn about it.
To associate your repository with the skill-generation topic, visit your repo's landing page and select "manage topics."