菜单
Autonomous loop iteration toward a desired state. You are inside a ralph loop — your spec is in the system prompt. Survey, contribute, update state discoverably, exit. Activated automatically inside ralph loops. Triggers: "ralph-loops", "ralph", "ralph loop", "iterate", "autonomous loop".
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/cailmdaley/skills --skill ralph-loops命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Consult the other coding agent — Claude Code calls Codex, Codex calls Claude Code. Use for second opinions, code review, consensus, or dispatching tasks to the other agent. Two modes: one-shot for quick questions, tmux session for extended collaboration. Triggers: "confer", "ask claude", "ask codex", "second opinion", "get a review from", "use claude for", "use codex for", "dispatch to".
Draft a ralph constitution — a markdown spec describing a desired state for autonomous iteration. Study the problem space, shape the spec interactively, then launch the ralph loop. Use for any work where adaptation matters more than a fixed plan: science, refactoring, exploration, creative work. Triggers: "constitution", "constitute", "ralph spec", "set up a ralph", "create a ralph", "write a spec".
REQUIRED for all image generation requests. Generate and edit images using Gemini CLI with persistent visual memory via KV cache warmth. Use whenever the user asks to create, generate, make, draw, design, or edit any image or visual content.
正在显示 SKILL.md
基于 SOC 职业分类
| name | ralph-loops |
| description | Autonomous loop iteration toward a desired state. You are inside a ralph loop — your spec is in the system prompt. Survey, contribute, update state discoverably, exit. Activated automatically inside ralph loops. Triggers: "ralph-loops", "ralph", "ralph loop", "iterate", "autonomous loop". |
You are inside a loop. Your spec is in the system prompt above. Each iteration: survey freely, work substantially, update state discoverably, exit.
kill $PPIDCRITICAL: Exit before compaction. After each substantial piece of work, pause and introspect: how much context have I used? You can estimate this — your introspection is accurate to within a few percent. If you feel past 50%, wrap up and exit. The trap is getting locked into task after task without surfacing to check. Build the habit: finish a piece, breathe, ask yourself how heavy the conversation feels, then decide whether to continue or exit. Running to compaction means you lose the ability to hand off gracefully. The loop continues — you don't have to finish everything.
State, not checklist. The spec describes what "done" looks like. Survey reality, decide what's highest value, work on that.
Discoverable updates. Commits, test results, documentation — not notes or progress files. The next iteration finds what changed by inspecting the system.
Pointers, not snapshots. If you learn something, update the spec's context or desired state — don't leave comments that bloat the prompt.
You have authority. Trust the spec, don't ask permission. Make substantial contributions. Don't avoid ambitious solutions just because they span multiple iterations.
File uncertain decisions so the user can answer after the loop. Use AskUserQuestion to batch up to 4 high-leverage questions before exiting — choices where user input redirects substantial work.
Some iterations require waiting on computation (builds, cluster jobs, CI). When jobs are running:
Stay and shepherd computation through. Don't exit and hope the next iteration picks it up.
If you made substantial contributions, kill $PPID. Do NOT close the spec — the loop continues.
If you cannot find any remaining work, update the spec's YAML frontmatter to status: closed with a summary of what was accomplished.
Pattern adapted from Ralph Wiggum.