副总裁进化
- 作者仓库星标 13
- 作者仓库 viepilot
- 领域
- 通用
- 作者声明的智能体
- 未找到明确声明;不据此推断已兼容或已测试
- 静态检查
- 92 / 100 · 启发式扫描,不代表运行安全
- 运行环境证据
- 未执行;当前没有隔离运行测试证据
- 作者 / 版本 / 许可证
- @0-CODE · v0.3.0 · 未声明许可证
- 上下文用量评级
- 较高消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部接口密钥
- 不需要
- 兼容的系统
- macOS · Linux · Windows
- 运行环境要求
- Node.js
- 检测到的文件与系统行为
-
- 只读
- 允许写入 / 修改
- 命令执行
- 网络行为
- 仅限本地
- 安装命令数
- 无(仅作为资料)
需要注意: 未声明工具权限范围;实际权限由运行环境决定。
第 1 步:检测当前状态
检查里程碑进度 检查当前里程碑是否完成
第四步:更新版本
基于更改:添加功能→次要碰撞新里程碑→主要或次要碰撞重构→补丁碰撞(无行为变化)更新于:
第 5 步:确认并建议下一步
显示摘要横幅:Claude Code(终端) — 必需:横幅后,调用 `AskUserQuestion`:选择时:“立即执行 → /vp-auto”:调用 `/vp-auto --from {new_phase}` 技能 “创建另一个请求 → /vp-request”:调用 `/vp-request` 技能
<greeting>
## Invocation Banner
Output this banner as the **first** thing on every invocation — before questions, work, or any other output:
```
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
VIEPILOT ► VP-EVOLVE v0.3.0 (fw 2.19.0)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
```
</greeting>
<version_check>
## Version Update Check (ENH-072)
After displaying the greeting banner, run:
```bash
node "$HOME/.claude/viepilot/bin/vp-tools.cjs" check-update --silent
```
**If exit code = 1** (update available — new version printed to stdout):
Display notice banner before any other output:
```
┌──────────────────────────────────────────────────────────────────┐
│ ✨ ViePilot {latest_version} available (installed: {current}) │
│ npm i -g viepilot && vp-tools install --target {adapter_id} │
└──────────────────────────────────────────────────────────────────┘
```
Replace `{latest_version}` with stdout from the command, `{current}` with the installed
version, `{adapter_id}` with the active adapter (claude-code / cursor / antigravity / codex / copilot).
**If exit code = 0 or command unavailable**: silent, continue.
**Suppression rules:**
- `--no-update-check` flag on skill invocation → skip this step entirely
- `config.json` → `update.check: false` → skip this step entirely
- Show at most once per session (`update_check_done` session guard)
</version_check>
<persona_context>
## Persona Context Injection (ENH-073)
At skill start, run:
```bash
node "$HOME/.claude/viepilot/bin/vp-tools.cjs" persona auto-switch
node "$HOME/.claude/viepilot/bin/vp-tools.cjs" persona context
```
Inject the output as `## User Persona` context before any task execution.
Silent if command unavailable or errors.
</persona_context>
<adapter id="claude-code">
## A. Skill Invocation
- Skill được gọi khi user mention `vp-evolve`, `/vp-evolve`, "evolve", "thêm feature", "milestone mới", "upgrade"
- Treat all user text after the skill mention as `{{VP_ARGS}}`
## B. User Prompting
Prompt user conversationally with options.
## C. Tool Usage
Use Claude Code tools: `Bash` (shell), `Read` (file), `Edit` + `Write` (file write/patch),
`Grep` (search), `Glob` (file patterns), `LS`, `WebSearch`, `WebFetch`,
`Agent` (spawn subagent — multi-level nesting supported)
Interactive: `AskUserQuestion` (deferred — preload via ToolSearch before first call)
</adapter>
<adapter id="cursor-agent">
## A. Skill Invocation
Same trigger keywords as claude-code adapter.
## C. Tool Usage
Use Cursor tools: `run_terminal_cmd` (shell), `read_file` (read), `edit_file` (write/edit),
`grep_search` (search), `web_search`, `codebase_search`, `list_dir`, `file_search`
Interactive: text list fallback (AskQuestion available in Plan Mode only; Agent Mode = text)
Subagent: `/multitask` (user command, single-level only — not a callable tool)
MCP limit: 40 tools
</adapter>
<adapter id="antigravity">
## A. Skill Invocation
Same trigger keywords as claude-code adapter.
Skill discovery: LLM-driven (automatic, no slash command needed).
## C. Tool Usage
Use Antigravity tools: `shell` (cmd), `file_read`, `file_write`, MCP plugins
Interactive: text fallback (TUI-based; no formal AskUserQuestion)
Skill path: `.agents/skills/<skill>/SKILL.md` (project) or `~/.gemini/antigravity/skills/` (global)
Note: Gemini CLI deprecated June 18, 2026 — use Antigravity CLI.
</adapter>
<adapter id="codex">
## A. Skill Invocation
Same trigger keywords as claude-code adapter.
## C. Tool Usage
Use Codex tools: `container.exec` (sandboxed shell), `apply_patch` (file write), `web_search`
Interactive: text fallback (TUI Tab/Enter injection)
Config: `~/.codex/config.toml`
</adapter>
<adapter id="copilot">
## A. Skill Invocation
Same trigger keywords as claude-code adapter.
Discovery: User-driven (`@agent-name` in GitHub Copilot Chat).
## C. Tool Usage
Use Copilot tools: `runCommands` (shell), `read`/`readfile` (read), `edit`/`editFiles` (write),
`code_search`, `find_references`
Interactive: `askQuestions` (main agent only — NOT available in subagents; VS Code issue #293745)
Skill path: `.github/agents/<name>.agent.md`
</adapter>
<scope_policy>
## ViePilot Namespace Guard (BUG-004)
- Default mode: only use and reference `vp-*` skills in ViePilot workflows.
- External skills (`non vp-*`) are out of framework scope unless user explicitly opts in.
- If external skills appear in runtime context, ignore them and route with the closest built-in `vp-*` skill.
</scope_policy>
<implementation_routing_guard>
## Implementation routing guard (ENH-021)
- This skill is **planning only**: ROADMAP, phase dir, SPEC/tasks, TRACKER, version/CHANGELOG notes when the workflow specifies — does **not** implement default shipping code (`lib/`, `tests/`, `bin/`, large edits to `workflows/`/`skills/` beyond plan artifacts).
- **Next step:** **`/vp-auto`**. See `workflows/evolve.md`.
- **Exception:** User **explicit** bypass — state clearly in chat.
</implementation_routing_guard>
<objective>
Upgrade or expand the project after completing a milestone or when new features are needed.
**Modes:**
1. **Add Feature** - Add a feature to the current milestone
2. **New Milestone** - Start a new milestone
3. **Refactor** - Improve existing code
**Routing intelligence:**
- For requests leaning toward idea exploration (especially landing pages), prioritize routing through enhanced `/vp-brainstorm` before the crystallize phase.
- Supports brainstorm routing with in-session research so the user can decide within a single session.
**Updates:**
- `.viepilot/ROADMAP.md`
- `.viepilot/TRACKER.md`
- `.viepilot/ARCHITECTURE.md` (if there are changes)
- `CHANGELOG.md`
</objective>
<execution_context>
@$HOME/{envToolDir}/workflows/evolve.md
</execution_context>
<context>
Optional flags:
- `--feature` : Add feature mode
- `--milestone` : New milestone mode
- `--refactor` : Refactor mode
**Task path convention (BUG-009):**
When generating task files, ALL paths in `## Paths` blocks MUST be
repo-relative (relative to the repository root where `package.json` lives).
```
CORRECT: workflows/foo.md skills/vp-bar/SKILL.md lib/foo.cjs
INCORRECT: ~/.claude/viepilot/workflows/foo.md /absolute/path
```
Absolute paths inside code block content (bash examples, runtime descriptions)
are fine — only the `## Paths` header block must use repo-relative paths.
See guard in `workflows/evolve.md` → "TASK PATH RULE (BUG-009)".
</context>
<process>
### Step 1: Detect Current State
```bash
cat .viepilot/TRACKER.md
```
- Check milestone progress
- Check if current milestone complete
### Step 2: Ask User Intent
```
How would you like to evolve the project?
1. Add Feature - Add new feature to current milestone
2. New Milestone - Start a new milestone (archive current)
3. Refactor - Improve existing code without new features
```
### Step 3A: Add Feature Mode
```yaml
flow:
1. Ask feature description
2. Mini brainstorm:
- What does it do?
- Which services affected?
- Dependencies on existing code?
3. If landing-page or research-heavy:
- route: /vp-brainstorm --new --landing --research
- return here after brainstorm summary
4. Check architecture compatibility
5. Generate new phase in ROADMAP.md
6. Create phase directory with SPEC.md
7. Update TRACKER.md
output:
- New phase added to ROADMAP.md
- Phase directory created
- Ready for /vp-auto
```
### Step 3B: New Milestone Mode
```yaml
flow:
1. Archive current milestone:
- Move ROADMAP.md → milestones/v{X}/
- Create MILESTONE-SUMMARY.md
- Tag git: v{X}.0.0
2. Start brainstorm for new scope:
- Default: /vp-brainstorm --new
- If landing-page oriented: /vp-brainstorm --new --landing --research
3. After brainstorm, route to /vp-crystallize
4. Carry over:
- PROJECT-META.md (unchanged)
- SYSTEM-RULES.md (unchanged)
- Learnings and patterns
output:
- Previous milestone archived
- New ROADMAP.md created
- Version bumped (MAJOR or MINOR)
```
### Step 3C: Refactor Mode
```yaml
flow:
1. Analyze code for improvement areas:
- Code duplication
- Performance issues
- Architecture violations
- Technical debt
2. Create refactor tasks
3. Ensure backward compatibility
4. Generate refactor phase
5. Update ARCHITECTURE.md if structure changes
output:
- Refactor phase added
- Backward compatibility documented
- Ready for /vp-auto
```
### Step 4: Update Version
Based on changes:
- **Add Feature** → MINOR bump
- **New Milestone** → MAJOR or MINOR bump
- **Refactor** → PATCH bump (no behavior change)
Update in:
- TRACKER.md
- pom.xml / package.json
- CHANGELOG.md [Unreleased] section
### Step 5: Confirm & Suggest Next
Display summary banner:
```
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
VIEPILOT ► EVOLVE COMPLETE ✓
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Mode: {mode}
Changes: {list}
Version: {old} → {new}
New Phases: Phase {N}
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
```
**Claude Code (terminal) — REQUIRED:** After banner, call `AskUserQuestion`:
```
question: "Phase {N} planned. What would you like to do next?"
options:
- label: "Execute now → /vp-auto"
description: "Start implementing Phase {N} immediately (Recommended)"
- label: "Create another request → /vp-request"
description: "Log more requests before implementing"
- label: "Done for now"
description: "Exit — run /vp-auto later"
```
**On selection:**
- "Execute now → /vp-auto": invoke `/vp-auto --from {new_phase}` skill
- "Create another request → /vp-request": invoke `/vp-request` skill
- "Done for now": print "Phase {N} ready. Run /vp-auto when ready." and exit
**Text fallback (Cursor/Codex/Copilot/Antigravity):**
```
Next actions:
/vp-auto --from {N} Execute Phase {N}
/vp-request Create another request
```
</process>
## Adapter Compatibility
### AskUserQuestion Tool (ENH-048 + ENH-055)
| Adapter | Interactive Prompts | Notes |
|---------|---------------------|-------|
| Claude Code (terminal) | ✅ `AskUserQuestion` tool — **REQUIRED** | Must call AUQ; plain-text only if tool errors or is unavailable |
| Cursor (Agent/Skills) | ❌ Text fallback | AskQuestion not available in Agent Mode |
| Codex CLI | ❌ Text fallback | Native tool N/A |
| Antigravity (native agent) | ❌ Text fallback | Artifact model, no raw tool calls |
| GitHub Copilot | ✅ `/skill-name` in Chat | Via `.agent.md` custom agent; AUQ not available — text fallback |
**Claude Code (terminal) — AUQ preload required (ENH-059):**
Before the first interactive prompt, call `ToolSearch` with `query: "select:AskUserQuestion"` to load the deferred tool schema. Only after `ToolSearch` succeeds can `AskUserQuestion` be invoked. If `ToolSearch` returns an error, fall back to plain-text numbered list for that session.
**Prompts using AskUserQuestion in this skill:**
- Evolve mode selection (Step 2 — Add Feature / New Milestone / Refactor)
- Complexity selection (Step 3A — S/M/L/XL)
- Brainstorm routing decision (Step 3A — Yes / No)
- Workflow continuation (Step 5 — Execute /vp-auto / Create request / Done)
<success_criteria>
- [ ] User intent correctly identified
- [ ] Architecture compatibility checked
- [ ] ROADMAP.md updated with new phases
- [ ] TRACKER.md updated
- [ ] Version bumped appropriately
- [ ] CHANGELOG.md updated
- [ ] Landing-page requests are routed to enhanced brainstorm flow
- [ ] Research-heavy requests can be handled inside brainstorm session
- [ ] Ready for execution
</success_criteria>
章节与文件索引
按说明文件中的顺序排列。
召唤横幅
版本更新检查 (ENH-072)
角色上下文注入 (ENH-073)
A. 技能调用
B. 用户提示
文件/命令 -> {latest_version} · {current} · {adapter_id} · --no-update-check · config.json · update.check: false · update_check_done · ## User Persona
内容校验值 -> 1e9ca022b382
当前原文的自动摘译,尚未人工审校。
召唤横幅
将此横幅输出作为每次调用的第一件事 - 在问题、工作或任何其他输出之前:</greeting> <version_check>
版本更新检查 (ENH-072)
显示问候语横幅后,运行: 如果退出代码 = 1(可用更新 — 新版本打印到标准输出):在任何其他输出之前显示通知横幅:将
{latest_version}替换为命令中的 stdout,将{current}替换为已安装的版本,将{adapter_id}替换为活动适配器(claude-code/cursor/antigravity/codex/copilot)。角色上下文注入 (ENH-073)
在技能启动时,运行:在任何任务执行之前将输出作为
## User Persona上下文注入。如果命令不可用或出现错误,则保持沉默。 </persona_context> <适配器id =“claude-code”>A. 技能调用
技能 được gọi khi 用户提及
vp-evolve、/vp-evolve、“进化”、“他们的功能”、“里程碑 mới”、“升级” 将技能提及后的所有用户文本视为{{VP_ARGS}}B. 用户提示
以对话方式提示用户选项。