Away-From-Keyboard autonomous execution for AI coding agents — hand over a scoped set of issues and get back PR-ready work that an independe...
#ai-agents
3666 posts
The structure behind AI-native development. Skills, Specs, Threads and deterministic execution for Codex.
Evidence-led ingredient feasibility and B2B customer discovery skill with audited case studies
Spec-driven pipeline for coding agents: nine skills and gates the agent cannot skip. OpenSpec artifacts + superpowers discipline, enforced b...
Canonical Agent Skill for auditing and safely reorganizing shared project folders used by multiple AI agents.
Debug a machine you cannot log into, through an operator who cannot debug it - for air-gapped, client-owned and change-controlled estates. G...
Claude Code skill for award-site motion pages — Three.js worlds, liquid-glass shaders, springy poster walls. Single-file, screenshot-verifie...
对抗模型输出不良表达习惯的 Agent Skill
Your agent reads the few skills a task needs, not forty. Picks none, one, or a small bounded set, and leaves the rest on disk.
Turn goals and existing Agent tools into readable, reviewable, reusable workflow Skills.
Local, revision-safe Blender VSE control for AI agents: typed timeline edits, four MCP tools, bounded context, and fresh-process persistence...
Stop your coding agent from stalling real work on self-invented bookkeeping - receipts, hashes, locks, certification rituals. Ship first, th...