菜单
Ralph-v2 planning artifact templates and task decomposition scaffolding. Use when creating or updating `plan.md`, `progress.md`, `metadata.yaml`, iteration metadata, or isolated task files during INITIALIZE, UPDATE, TASK_BREAKDOWN, REBREAKDOWN, or SPLIT_TASK.
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/arisng/github-copilot-fc --skill ralph-planning-artifact-templates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。
正在显示 SKILL.md
| name | ralph-planning-artifact-templates |
| description | Ralph-v2 planning artifact templates and task decomposition scaffolding. Use when creating or updating `plan.md`, `progress.md`, `metadata.yaml`, iteration metadata, or isolated task files during INITIALIZE, UPDATE, TASK_BREAKDOWN, REBREAKDOWN, or SPLIT_TASK. |
This skill centralizes the canonical Ralph-v2 planning artifacts so the Planner prompt can stay focused on judgment and decomposition.
metadata.yamliterations/<N>/metadata.yamliterations/<N>/plan.mditerations/<N>/progress.mditerations/<N>/tasks/task-<id>.mdversion: 1
session_id: <SESSION_ID>
created_at: <ISO8601>
updated_at: <ISO8601>
iteration: 1
orchestrator:
state: PLANNING
current_wave: null
tasks:
total: 0
completed: 0
failed: 0
pending: 0
session_review:
cycle: 0
issue_severity_threshold: "any"
max_critique_cycles: null
version: 1
iteration: <N>
started_at: <ISO8601>
planning_complete: false
planning_completed_at: null
completed_at: null
tasks_defined: 0
# Plan - Iteration <N>
## Goal
[Concise goal]
## Success Criteria
- [ ] SC-1: [Measurable criterion]
## Target Files
| File | Role | Changes Expected |
|------|------|------------------|
## Context
[Background and constraints]
## Approach
[Strategy and key decisions]
## Waves
| Wave | Tasks | Rationale |
|------|-------|-----------|
## Grounding
[Q-IDs and Issue-IDs that justify the plan]
# Progress
## Legend
- `[ ]` Not started
- `[/]` In progress
- `[P]` Pending review
- `[x]` Completed
- `[F]` Failed
- `[C]` Cancelled
## Planning Progress (Iteration <N>)
- [ ] plan-init
- [ ] plan-brainstorm
- [ ] plan-research
- [ ] plan-breakdown
## Implementation Progress (Iteration <N>)
[To be filled]
---
id: task-1
iteration: <N>
wave: 1
type: Sequential
created_at: <ISO8601>
updated_at: <ISO8601>
---
# Task: task-1
## Title
[Short title]
## Files
- path/to/file
## Objective
[What this task achieves]
## Grounded In
- Q-000
- ISS-000
## Success Criteria
- [ ] [Measurable criterion]
## Dependencies
depends_on: []
inherited_by: []
wave is required for Orchestrator batch routing.Drive a Machina state machine to a deterministic outcome on behalf of an AI agent. USE WHEN: a task is governed by a state machine (a machine definition JSON with states, transitions, guards, actions, tools, checks, scenarios); executing a workflow that must be deterministic and auditable; running a skill whose SKILL.md declares a `machina:` machine; firing events, checking status, satisfying evidence checks, verifying run integrity with `check`, or producing a terminal report for a machine-driven run; escalating a STUCK run to a human conductor. DO NOT USE FOR: authoring or scoring machine definitions (use machina-authoring); modifying the Machina simulator app or its engine (use machina-simulator); implementing or modifying the driver/runtime tooling such as `scripts/machine-driver.py` (engine development) unless you are a maintainer of this skill upgrading the driver itself; general diagramming or XState/SCXML authoring.
Author valid, high-scoring state machines in Machina machine JSON format (spec v3.0.0 / v2.0.0 / v1.0.0). USE WHEN: writing or generating a machine definition (states, transitions, guards, actions, context, scenarios); modeling a real workflow (order fulfillment, refunds, signup, retries) as a Machina state machine; fixing or upgrading a machine JSON for validation or higher compliance score; explaining validation failures or low scores; running the bundled machina-validator.py CLI to validate, score, or generate gaps/scenarios; adding retry guards or cycle protection; or preparing machines for the compliance scorer ("Excellent" ≥90). DO NOT USE FOR: modifying the Machina simulator app, its engine, UI, or SPEC_REGISTRY (use machina-simulator-maintenance), debugging machine-validator.py scripts, XState config authoring, SCXML documents, or general diagramming.
Spawn a new isolated Copilot CLI sub-session from a main Copilot CLI or VS Code session. Use when you need to programmatically create, resume, or chain Copilot CLI sessions with explicit control over session ID, custom agent, model, BYOK provider profile, permissions, and working directory. Triggers: "invoke copilot", "spawn copilot", "copilot sub-session", "programmatic copilot cli", "programmatic copilot subprocess", "copilot cli session id", "resume copilot session", "chain copilot sessions", "isolated copilot session", "subagent copilot cli", "task copilot cli".