上下文感知的\"下一步该做什么\"助手。读取工作流目录与已有产物,判断当前阶段并推荐下一步动作。
Scanned 9/9/2026
Install to Claude Code
npx -y skills add zls3434/Software-Engineering-Studios --skill help --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Help?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/zls3434-help-software-engineering-studios)More formats (shields.io, HTML) on the badges page.
---
name: help
description: "上下文感知的\"下一步该做什么\"助手。读取工作流目录与已有产物,判断当前阶段并推荐下一步动作。"
license: MIT
metadata:
model: haiku
argument-hint: ""
user-invocable: true
allowed-tools:
- Read
- Glob
- Grep
platforms:
claude-code: {enabled: true}
cursor: {enabled: true}
codex: {enabled: true}
windsurf: {enabled: true, trigger: /help}
trae: {enabled: true}
hermes: {enabled: true, platforms: [macos, linux, windows]}
workbuddy: {enabled: true}
---
# help — 上下文感知下一步助手
## 技能目的
根据当前项目状态、已有产物与工作流目录,智能判断项目所处阶段,并向用户推荐下一步应执行的动作或技能。
## 参数说明
本技能无参数。
## 分阶段工作流
### 阶段 1:读取工作流目录
- **输入**:`.claude/workflow-catalog.yaml`
- **处理**:解析工作流目录,获取所有阶段定义、必需产物列表、阶段间依赖关系
- **输出**:工作流定义对象
### 阶段 2:检测已有产物
- **输入**:工作流定义 + 项目目录
- **处理**:
1. 使用 Glob 扫描各阶段期望产物(product-concept.md、systems-index.md、SRS、architecture-doc.md 等)
2. 使用 Grep 检查产物内容的完整度(是否仅占位、是否有实际内容)
3. 对照工作流目录标记每个阶段的完成度:未开始/进行中/已完成
- **输出**:阶段完成度矩阵
### 阶段 3:定位当前阶段
- **输入**:阶段完成度矩阵
- **处理**:找到第一个未完成阶段作为当前阶段,识别该阶段缺失的关键产物
- **输出**:当前阶段名称 + 缺失产物清单
### 阶段 4:推荐下一步
- **输入**:当前阶段 + 缺失产物
- **处理**:匹配当前阶段对应的技能,生成推荐动作列表(按优先级排序)
- **输出**:推荐下一步消息,包含技能名、简要说明、建议参数
## 协作协议引用
- 参考 `.claude/docs/templates/collaborative-protocols/design-agent-protocol.md` 中的阶段流转规则
## 推荐下一步
直接执行推荐的首选技能。若用户对推荐有异议,可使用 `/project-stage-detect` 获取更详细的阶段诊断报告。Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling