3676 posts
Architecture patterns for multi-agent systems with orchestrators, sub-agents, and tool coordination
A middleweight workflow for serious AI-coded features: less ceremony than BMAD, more accountability than Superpowers. Source : Trust Me Bro.
Dispatch panels of specialized subagents to review projects — expert audits, first-impression personas, task-completion flows, and pedantic...
Teach your coding agent — Claude Code, Cursor, or any AGENTS.md agent — your project's conventions, and turn every correction into a team-sh...
Neo Skills 是專為現代 AI Agent 設計的全方位能力擴充套件。本專案透過標準化的通訊架構，為 AI 代理安裝可插拔的「技能模組 (Skills)」，使其不僅僅...
A multi-agent context, rules, and hooks boilerplate generator. With a single command, it scaffolds conventions, namespaced skills, stack-app...
RFC v0.8 + implementación de referencia para publicar Agent Skills a través de llms.txt. Incluye parser, validador, schema JSON y skills de...
A "trust, but verify" workflow of AI-agent skills: prompt to verified code, every step trackable and deviations logged — plus an autonomous...
Practical Agent Skills — English-for-engineers coaching, Pi Agent setup, and more. Install via npx skills add.
Systematic worldview articulation - surface beliefs, identify tensions, generate narrative outputs for personal philosophy documentation
Blockchain skills you can use with your coding agent, such as Claude Code, OpenCode, Codex, Cursor and more.
Agents that learn by doing — and remember how they did it. A methodology for AI agents to create, evolve, and share reusable skills.
