/pace-next
Use when user asks "下一步做什么", "接下来做什么", "该做什么", "什么最重要", "应该先做哪个", "最紧急", "优先级", "推荐做什么", "为什么推荐这个", "pace-next", or wants a recommendation for the most important next action across all domains. NOT for current progress overview (use /pace-status).
$ npx -y skills add arch-team/devpace --skill pace-next --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/pace-next
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use when user asks "下一步做什么", "接下来做什么", "该做什么", "什么最重要", "应该先做哪个", "最紧急", "优先级", "推荐做什么", "为什么推荐这个", "pace-next", or wants a recommendation for the most important next action across all domains. NOT for current progress overview (use /pace-status).
SKILL.md
pace-next.SKILL.mddescription: Use when user asks "下一步做什么", "接下来做什么", "该做什么", "什么最重要", "应该先做哪个", "最紧急", "优先级", "推荐做什么", "为什么推荐这个", "pace-next", or wants a recommendation for the most important next action across all domains. NOT for current progress overview (use /pace-status).
allowed-tools: Read, Glob, Grep
argument-hint: "[detail|why|journey <模板名>]"
model: haiku
context: fork
agent: pace-analyst
/pace-next — 下一步导航
跨域全局导航:综合 CR、迭代、Release、度量、风险、Epic/Opportunity 等多维信号,推荐当前最该做的 1 件事。
输入
$ARGUMENTS:
- (空)→ 最高优先级 1 条建议(默认,≤ 3 行)
- `detail` → 展开候选列表(≤ 8 行,含 top-3 建议)
- `why` → 展开推理链(2-5 行,信号扫描 + 优先级对比 + 角色影响 + 备选)
- `journey [模板名]` → 展示完整工作流路径:从当前状态到目标的分步引导
- 可选模板:`new-feature`(默认)、`iteration`、`hotfix`、`release`、`onboarding`
- 无模板名 → 根据当前项目状态自动选择最匹配的模板
执行路由
**重要**:根据 $ARGUMENTS 值,仅读取对应的输出规程文件,不加载全部规程。所有模式先加载 `skills/pace-next/next-procedures.md`(核心决策逻辑)。
| 参数 | 加载文件 | |------|---------| | (空) | `skills/pace-next/next-procedures.md` + `skills/pace-next/next-procedures-output-default.md` | | `detail` | `skills/pace-next/next-procedures.md` + `skills/pace-next/next-procedures-output-detail.md` | | `why` | `skills/pace-next/next-procedures.md` + `skills/pace-next/next-procedures-output-why.md` | | `journey` | `skills/pace-next/next-procedures.md` + `skills/pace-next/next-procedures-journey.md` |
流程
Step 1:检测项目状态
1. 检查项目根目录是否存在 `.devpace/state.md` 2. 不存在 → 输出未初始化引导(见 skills/pace-next/next-procedures.md),结束 3. 存在 → 继续
Step 2:采集信号
读取 `.devpace/` 下的数据源(目录/文件不存在时静默跳过):
| 数据源 | 读取内容 | |--------|---------| | `backlog/*.md` | CR 状态、类型 | | `state.md` | 当前工作摘要 | | `releases/*.md` | Release 状态 | | `risks/*.md` | 风险严重度 | | `iterations/current.md` | PF 完成率、周期 | | `metrics/dashboard.md` | 最近更新日期 | | `project.md` | MoS、PF/BR/OBJ 映射 | | `integrations/sync-mapping.md` | 同步状态(存在时) | | `epics/*.md` | Epic 状态、BR 列表 | | `opportunities.md` | Opportunity 状态 |
提取关键状态字段(不全量读取)。额外采集 CR→PF→BR→Epic→OPP 价值链映射。
Step 3:优先级决策
从高到低遍历信号分组,取首个命中(判断细节见 skills/pace-next/next-procedures.md):
| 组 | 信号 | |----|------| | Blocking | S1 审批阻塞(in_review > 0)· S2 高风险阻塞(High 且 open) | | In Progress | S3 继续开发(developing CR)· S4 恢复暂停(paused 阻塞解除) | | Delivery | S5 Release 待验证 · S6 风险积压(open > 3)· S7 迭代紧迫(< 2 天且 < 50%)· S8 迭代接近完成(> 80%) | | Strategic | S9 回顾提醒(> 7 天 + merged)· S10 缺陷占比(> 30%)· S11 同步滞后(> 24h)· S12 MoS 达成(> 80%) | | Growth | S13 功能未开始 · S14 规划新迭代 · S15 全部完成 · S16 Epic 需分解 · S17 未评估机会 · S18 功能树稀疏 · S19 范围未定义 · S21 依赖阻塞 · S22 技术债积压 · S24 首次循环引导 | | Idle | S20 无信号 |
Step 3b:旅程路径生成(仅 journey 模式)
journey 模式跳过 Step 3 的信号优先级决策,改为按旅程模板生成分步路径。详见 `skills/pace-next/next-procedures-journey.md`。
Step 4:经验增强
匹配历史经验 pattern(`.devpace/metrics/insights.md`,如存在),在建议中附加 ≤1 行经验参考。
Step 5:角色适配
根据当前角色(Dev/PM/Biz/Tester/Ops)调整建议措辞维度和信号组内排序。
Step 6:输出
按路由表加载的输出规程文件格式化输出。
输出
≤ 3 行(默认)或 ≤ 8 行(detail)或 2-5 行推理链(why)。自然语言为主,不暴露 ID。建议体现价值链上下文。
<!-- 信号摘要同步自 knowledge/_signals/signal-priority.md + knowledge/_signals/signal-collection.md,修改信号时须同步 -->
Read more
description: Use when user asks "下一步做什么", "接下来做什么", "该做什么", "什么最重要", "应该先做哪个", "最紧急", "优先级", "推荐做什么", "为什么推荐这个", "pace-next", or wants a recommendation for the most important next action across all domains. NOT for current progress overview (use /pace-status). allowed-tools: Read, Glob, Grep argument-hint: "[detail|why|journey <模板名>]" model: haiku context: fork agent: pace-analyst
/pace-next — 下一步导航
跨域全局导航:综合 CR、迭代、Release、度量、风险、Epic/Opportunity 等多维信号,推荐当前最该做的 1 件事。
输入
$ARGUMENTS:
- (空)→ 最高优先级 1 条建议(默认,≤ 3 行)
- `detail` → 展开候选列表(≤ 8 行,含 top-3 建议)
- `why` → 展开推理链(2-5 行,信号扫描 + 优先级对比 + 角色影响 + 备选)
- `journey [模板名]` → 展示完整工作流路径:从当前状态到目标的分步引导
- 可选模板:`new-feature`(默认)、`iteration`、`hotfix`、`release`、`onboarding`
- 无模板名 → 根据当前项目状态自动选择最匹配的模板
执行路由
**重要**:根据 $ARGUMENTS 值,仅读取对应的输出规程文件,不加载全部规程。所有模式先加载 `skills/pace-next/next-procedures.md`(核心决策逻辑)。
| 参数 | 加载文件 | |------|---------| | (空) | `skills/pace-next/next-procedures.md` + `skills/pace-next/next-procedures-output-default.md` | | `detail` | `skills/pace-next/next-procedures.md` + `skills/pace-next/next-procedures-output-detail.md` | | `why` | `skills/pace-next/next-procedures.md` + `skills/pace-next/next-procedures-output-why.md` | | `journey` | `skills/pace-next/next-procedures.md` + `skills/pace-next/next-procedures-journey.md` |
流程
Step 1:检测项目状态
1. 检查项目根目录是否存在 `.devpace/state.md` 2. 不存在 → 输出未初始化引导(见 skills/pace-next/next-procedures.md),结束 3. 存在 → 继续
Step 2:采集信号
读取 `.devpace/` 下的数据源(目录/文件不存在时静默跳过):
| 数据源 | 读取内容 | |--------|---------| | `backlog/*.md` | CR 状态、类型 | | `state.md` | 当前工作摘要 | | `releases/*.md` | Release 状态 | | `risks/*.md` | 风险严重度 | | `iterations/current.md` | PF 完成率、周期 | | `metrics/dashboard.md` | 最近更新日期 | | `project.md` | MoS、PF/BR/OBJ 映射 | | `integrations/sync-mapping.md` | 同步状态(存在时) | | `epics/*.md` | Epic 状态、BR 列表 | | `opportunities.md` | Opportunity 状态 |
提取关键状态字段(不全量读取)。额外采集 CR→PF→BR→Epic→OPP 价值链映射。
Step 3:优先级决策
从高到低遍历信号分组,取首个命中(判断细节见 skills/pace-next/next-procedures.md):
| 组 | 信号 | |----|------| | Blocking | S1 审批阻塞(in_review > 0)· S2 高风险阻塞(High 且 open) | | In Progress | S3 继续开发(developing CR)· S4 恢复暂停(paused 阻塞解除) | | Delivery | S5 Release 待验证 · S6 风险积压(open > 3)· S7 迭代紧迫(< 2 天且 < 50%)· S8 迭代接近完成(> 80%) | | Strategic | S9 回顾提醒(> 7 天 + merged)· S10 缺陷占比(> 30%)· S11 同步滞后(> 24h)· S12 MoS 达成(> 80%) | | Growth | S13 功能未开始 · S14 规划新迭代 · S15 全部完成 · S16 Epic 需分解 · S17 未评估机会 · S18 功能树稀疏 · S19 范围未定义 · S21 依赖阻塞 · S22 技术债积压 · S24 首次循环引导 | | Idle | S20 无信号 |
Step 3b:旅程路径生成(仅 journey 模式)
journey 模式跳过 Step 3 的信号优先级决策,改为按旅程模板生成分步路径。详见 `skills/pace-next/next-procedures-journey.md`。
Step 4:经验增强
匹配历史经验 pattern(`.devpace/metrics/insights.md`,如存在),在建议中附加 ≤1 行经验参考。
Step 5:角色适配
根据当前角色(Dev/PM/Biz/Tester/Ops)调整建议措辞维度和信号组内排序。
Step 6:输出
按路由表加载的输出规程文件格式化输出。
输出
≤ 3 行(默认)或 ≤ 8 行(detail)或 2-5 行推理链(why)。自然语言为主,不暴露 ID。建议体现价值链上下文。
<!-- 信号摘要同步自 knowledge/_signals/signal-priority.md + knowledge/_signals/signal-collection.md,修改信号时须同步 -->
Give your Claude Code projects a steady development pace — requirements change, rhythm stays. A development harness for Claude Code — rules, schemas, gates, and feedback loops that keep AI-assisted development traceable and measurable.
Repo: arch-team/devpace
Other skills on devpace.
- /pace-biz
Use when user says "业务机会/OPP", "专题/Epic", "分解需求/decompose", "精炼/refine", "战略对齐/align", "业务全景/view", "需求发现/brainstorm/discover", "导入/import", "技术债务/infer", "pace-biz", or wants to plan requirements. NOT for /pace-dev, -change, -plan, -init.
Open skill - /pace-change
Use when user says "不做了", "搁置", "停掉", "加一个", "加需求", "追加", "改需求", "需求变了", "范围变了", "优先级调", "延后", "提前", "砍掉", "先做这个", "排到前面", "恢复", "捡回来", "pace-change", or wants to add, pause, resume, reprioritize, modify, undo, batch change, or query change history. NOT for code implementation
Open skill - /pace-dev
Use when user says "开始做", "帮我改", "实现", "修复", "继续推进", "编码", "写代码", "开发", "重构", "做个", "coding", "implement", "fix", "refactor", "build", /pace-dev, or explicitly requests to start/continue/resume coding work. "帮我改" only when target is code/UI/config. NOT for requirement changes
Open skill - /pace-feedback
Use when user reports issues, shares feedback, or receives production alerts — "用户反馈", "线上问题", "生产问题", "告警", "改进建议", "新需求", "体验问题", "功能请求", "线上bug", "运维", "事件", "incident", "故障", "P0", "P1", "严重故障", "postmortem", "事后复盘". NOT for code implementation or development (use
Open skill - /pace-guard
Use when user wants to assess risks before development, check current risk status, analyze risk trends, or says "风险/预检/预分析/guard/risk/隐患/安全检查". Also auto-invoked during advance mode intent checkpoint for L/XL CRs. NOT for /pace-dev (implementation), NOT for /pace-review (quality
Open skill - /pace-help
Use when user says "帮助", "help", "怎么用", "使用说明", "用法", "有哪些命令", "能做什么", "命令列表", "怎么入门", "quickstart", "FAQ", "常见问题", "pace-help", or wants help with how to use devpace commands and features. NOT for concept deep dive or methodology (use /pace-theory). NOT for next-step
Open skill

