📡 AI skill that helps your coding agent discover, track, and prioritize what to build next.

Turns GitHub issues into merged PRs with zero human intervention. Powered by OpenClaw, supports Claude Code, Codex CLI, and Kiro CLI.

Persistent REPL scratchpad for coding agents — variables survive across turns, only print() enters context. Agent skill for Claude Code, Codex, Gemini CLI, and 14+ coding agents.

Templates and local preferences for AGENTS.md

Recursively rename images with dimensions so LLMs can see them.

Workspace layer for coding agents across polyrepos. Coordinated branches, tag-based filtering, zero dependencies.

Governance framework for AI coding agents — enforces task traceability, structural gates, session continuity, and audit trails for Claude Code, Cursor, and Copilot.

🧠 Benchmark Haiku 4.5 and MiniMax M2.1 on agentic tasks, revealing strengths in design thinking and operational skills for multi-turn workflows.

⚡ Master Claude Code with this complete guide and automation for quick, effective setup and comprehensive documentation.

A template to introduce students to github copilot coding agent

AccX Clocking Kiosk — offline-first tablet app for time tracking and fire safety. Humans: run .harness/harness.sh (pw: changeme)

Protect macOS AI agents from identity theft with shell scripts that secure configs, keys, tokens, and memory against autonomous proxy attacks.

Reproducible benchmark framework for testing hypotheses about AI coding agents

File-based task management framework for AI coding agents — markdown tasks with YAML frontmatter, git-native, zero infrastructure. Works with Claude Code, Gemini CLI, OpenCode, and Codex CLI.

The fastest way to start coding-agent projects without chaos: one-command kickoff, strict quality gates, and a production-ready workflow for both new and existing codebases.

Dead simple one-button local AI coder for prosumer mini PCs.

Specialized Agent Skills to automate GitHub workflows using the GitHub CLI

Personal AGENTS.md profile for AI coding agents used across my projects and tools.

Systematic benchmark comparing Claude Haiku 4.5 vs MiniMax M2.1 on agentic coding tasks. Includes full audit trails, LLM-as-judge evaluation, and path divergence analysis.