A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.

Hand Claude a PRD. Get a working feature back. One story per subagent, fresh context every time.

Loop until it's better — drop-in agentic loops (autoresearch, scientific writing, data analysis, code/SQL/prompt optimization, red-teaming) as open-standard Agent Skills. Verification-gated; native on Claude Code, portable across Codex, Cursor & other Skills hosts.

Portable Agent Skill for repository-native Spec programming, informed by public DeepSeek Harness engineering patterns.

Codebase harness + loop engineer

Long-horizon agent skill for Claude Code / Cursor / Codex / Grok Build — multi-task ledger loop, host-portable, clean-context supervisor, verified gates. Markdown library (loop-graph), not a framework.

Turn Claude Code into its own Meta-Harness — a skill that evolves the scaffolding around a fixed model (memory, retrieval, context, prompts) via a native propose→score→Pareto loop. Native reimplementation of Meta-Harness (Lee et al. 2026).

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

Agent skills and an AGENTS.md workflow template — isolate in worktrees, build to a service layer, prove with evidence, ship with before/after proof and Greptile review loops. For Claude Code, Cursor, and Codex.

Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-calibrated judges, gated self-update loop, pressure testing, 10 authoring principles grounded in empirical research.

Composable Agent Skills (Claude + OpenAI Codex) for taking an idea from fuzzy → validated → sequenced build → shipped — a manual tier (ideate, deep-dive, prompt-pack) and an autonomous tier (autopilot, build-loop, audit-and-fix).

Autoresearch ALL THE THINGS. RLVR for the masses.

Re-anchor long conversations that drift through repeated local corrections.

Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.

Autonomous multi-batch development skill for Claude Code and Codex. They work while you sleep.

Claude Code workflow skills — GitHub issue/PR/release automation and Fable-driven planning. Install via npx or as a Claude Code plugin.

Generate clean 2D game sprites & animation atlases — component-row pipeline: state rows, alpha cleanup, frame extraction, runtime atlases. Codex/Claude skill.

Astra Skill Optimizer for GPT-6/Astra project Skill and workflow adaptation

Local-first Agent Skills for safe social-web workflows—starting with Douyin and designed around reusable browser adapters.

Drop-in scientific plotting skill for Claude Code, Codex, Cursor, and other coding agents.

The solo founder's AI engineering stack. Fork of gstack, rebuilt for bootstrappers, indie hackers, and people who want to quit their day job. Pieter Levels energy. Ship fast, charge money, skip the pitch deck.

Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks.