Designing, evaluating, and shipping autonomous AI agents.
7618 posts
Agent skills for Spec Kit
A Claude Code skill that audits AI-generated frontend and rewrites it to remove generic AI-slop design patterns (purple gradients, Inter, de...
Remoet agent skills (agentskills.io). One SKILL.md served to Hermes, OpenClaw, and any MCP-capable harness.
Environment-adaptive orchestration skill for AI agents.
Mapping the Prompt (MTP) Is a Color-Grid Framework for Steering LLM Output
Local capability router for Codex, Claude Code, Cursor, MCP servers, skills, agents, and rules.
AI agents and Nix: parametrable skills/instructions and tools, packaged together in a reproducible and modular fashion
A public OpenClaw and ClawHub-ready bundle of game design skills for emotional direction, feature workflows, audits, FTUE, pitch decks, prot...
Claude Code / Codex skill: проверяет, что ваш продукт реально работает — находит баги и строит защиту от регрессий автотестами
Deterministic, auditable agent/skill dispatch for Claude Code. A typed seven-decision scoring kernel runs after the router has read the conv...
英译汉翻译润色 · English→Chinese translate & polish skill (英中对照)
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
