菜单
Long-running iterative development loops with pacing control and verifiable progress. Use when tasks require multiple iterations, many discrete steps, or periodic reflection with clear checkpoints; avoid for simple one-shot tasks or quick fixes.
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。
Use ask_user as a decision, research, and requirements gate before ambiguous or high-stakes choices.
Versitile project planning skill for tracking ideas, defining detail and tracking progress on delivery. Use when you need to create, manage, or understand project planning artifacts like Epics, Stories, Tasks, Research, and Decisions. Follow the defined workflow phases and artifact relationships to ensure consistent and effective project planning. Results in well-structured project plans, clear traceability, and informed decision-making throughout the project lifecycle.
Use when understanding an unfamiliar code library, reusing cached local repo docs, or generating repo-native AGENTS.md and llms.txt navigation for cloned libraries.
Search local markdown knowledge bases, notes, docs, and wikis with QMD. Use when users ask to find notes, retrieve documents, inspect a wiki, answer from indexed markdown, or set up QMD access.
Working with Pi-Coding-Agent and modifying it via extensions. Use when you need to modify Pi-Coding-Agent's behavior or add new features to it. This skill routes you to the correct subskill.
Use when building system provisioning manifests, handling multi-OS setups, managing package manager conflicts, or designing team provisioning workflows - provides patterns and safety procedures for declarative system configuration; emphasizes validation, dry-run testing, and staged rollout to prevent broken user setups
| name | pi-ralph-wiggum |
| description | Long-running iterative development loops with pacing control and verifiable progress. Use when tasks require multiple iterations, many discrete steps, or periodic reflection with clear checkpoints; avoid for simple one-shot tasks or quick fixes. |
Use the ralph_start tool to begin a loop:
ralph_start({
name: "loop-name",
taskContent: "# Task\n\n## Goals\n- Goal 1\n\n## Checklist\n- [ ] Item 1\n- [ ] Item 2",
maxIterations: 50, // Default: 50
itemsPerIteration: 3, // Optional: suggest N items per turn
reflectEvery: 10 // Optional: reflect every N iterations
})
.ralph/<name>.md with the task content. The tool does NOT create this file—you must write it yourself using the Write tool.ralph_done to proceed to the next iteration.<promise>COMPLETE</promise> when finished./ralph start <name|path> - Start a new loop./ralph resume <name> - Resume loop./ralph stop - Pause loop (when agent idle)./ralph-stop - Stop active loop (idle only)./ralph status - Show loops./ralph list --archived - Show archived loops./ralph archive <name> - Move loop to archive./ralph clean [--all] - Clean completed loops./ralph cancel <name> - Delete loop./ralph nuke [--yes] - Delete all .ralph data.Press ESC to interrupt streaming, send a normal message to resume, and run /ralph-stop when idle to end the loop.
# Task Title
Brief description.
## Goals
- Goal 1
- Goal 2
## Checklist
- [ ] Item 1
- [ ] Item 2
- [x] Completed item
## Verification
- Evidence, commands run, or file paths
## Notes
(Update with progress, decisions, blockers)