← All creators

stone16

User

Run AI coding agents unattended for hours and ship PRs worth merging. Cybernetics-based multi-agent orchestration + cross-LLM peer review for Claude Code, Codex, and Gemini. Engine-enforced gates, fresh agent per checkpoint, cross-vendor review before every PR.

2 indexed · 0 Featured · 26 stars · avg score 83
View on GitHub →

Categories

AI & Automation (1) Code & Development (1)

Indexed Skills (2)

AI & Automation Listed

harness

Cybernetics-based multi-agent orchestration for complex tasks. Coordinates a Planner → Generator → Evaluator → Retro pipeline with clean-context sub-agents, per-checkpoint drift prevention, and persistent retro learning. Recommended workflow: Claude Code plans the spec (Session 1), Codex executes autonomously (Session 2), Claude CLI reviews as cross-model peer. Use when: "harness this task", "use harness", "orchestrate this", "harness plan", "harness continue", "harness execute <task-id>", "harness <spec-name>", or when a task requires structured multi-agent coordination.

26 Updated 2 weeks ago
stone16
Code & Development Listed

review-loop

Cross-LLM iterative code review loop. Spawns a peer reviewer (Codex, Claude, or Gemini CLI) to review code changes, then iterates until both agents agree on the final code state. Code gets modified during the loop — the final output is improved code + consensus report. Use when: "review loop", "peer review", "cross review", "review with codex", "review with claude", "review with gemini", "让 codex review", "让 claude review", "交叉 review", "peer review 这段代码", "code review loop", "iterative review"

26 Updated 2 weeks ago
stone16

Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.