Runtime-evidence debugging for coding agents: session-scoped probes, bounded logs/query CLI, and an agent skill.
Agents
Designing, evaluating, and shipping autonomous AI agents.
7515 posts
Portable, evidence-driven agent development harness for Codex, Claude Code, and generic Agent Skills. Active beta v0.1.2.
Visual alignment and explicit approval gates for complex Codex tasks
Router skill for Android agents: detects project surfaces, loads focused Android guidance, and enforces build/test/device verification.
Connect your AI to Reanthesis — MCP server, agent skills, and plugins so Claude, ChatGPT, and Copilot can build flashcards from your notes a...
Smart JSON-to-TOON conversion with pragmatic auto-gating for LLM prompts
A production full-stack engineering skill suite for AI coding agents—covering UI, UX, security, databases, auth, caching, testing, performan...
LLM-first SEO skill for safari & tour-operator sites — 15 sub-skills, 363 TZ keywords, TouristTrip schema. Grok, Cursor, Claude.
Agent skill engine for AI-tool affiliate catalogs, monetization audits, partnership workflows, and revenue loops.
本项目是 Socratopia(破卷)生态的衍生项目,是其"造书"环节的方法论沉淀,已固化为一个可复用的 skill。 让你具备亲手为自己造一本教材的能力——把一...
Headless Product Design skill for AI coding agents | Design how it works, verify what you ship.
Light as air, firm as law. Spec-driven AI coding with hooks.