Agent安装

Name: Agent安装
Author: 0-CODE

其他已审计 v0.3.0

作者仓库星标 13
作者更新于实时读取
作者仓库 viepilot

流狐档案事实层信息：领域、Agent、信任分、运行环境、权限与网络

领域: 通用
兼容 Agent: Claude Code
Cursor
Cline
Codex
Windsurf
Gemini CLI

+20
信任分: 92 / 100 · 已通过审计
作者 / 版本 / 许可: @0-CODE · v0.3.0 · 未声明 license
Token 消耗评级: 较高消耗
接入复杂程度: 需简单配置
是否需要外部 API Key: 不需要
兼容的系统: macOS · Linux · Windows
底层运行要求: Node.js
文件与系统权限: 只读
允许写入 / 修改
Shell 执行
网络行为: 仅限本地
安装命令数: 26 条

档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。

需要注意： 未限定 allowed-tools，默认拥有全部工具权限。

输出预览 vp-evolve.preview

---
name: vp-evolve
description: Upgrade, add features, or start a new milestone Output this banner as the first thing on every i…
category: 通用
runtime: Node.js
---

# vp-evolve 输出预览

## PART A: 任务判断
- 适用问题：通用任务拆解、检查和交付。
- 输入要求：目标材料、限制条件、期望输出和验收方式。
- 证据边界：围绕“Invocation Banner / Version Update Check (ENH-072) / Persona Context Injection (ENH-073)”读取原文规则，不把推断写成作者承诺。

## PART B: 执行结果
- **01** 任务判断：确认你的需求是否属于通用任务拆解、检查和交付，并标出输入、限制和预期结果。
- **02** 执行计划：优先按“Invocation Banner / Version Update Check (ENH-072) / Persona Context Injection (ENH-073)”拆成步骤，说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果：给出可复制的命令、文件改动、检查清单或内容草稿，并说明如何继续迭代。
- **04** 风险边界：结合 读取文件、写入/修改文件、执行终端命令、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。

## Running Rules
- 读取文件、写入/修改文件、执行终端命令；主要在本地完成；通常不需要额外 API Key。
- 先小样例验证，再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。

SKILL.md SKILL.md

---
name: vp-evolve
description: Upgrade, add features, or start a new milestone Output this banner as the first thing on every i…
category: 通用
source: 0-CODE/viepilot
---

# vp-evolve

## 什么时候使用
- vp-evolve 是一个通用扩展技能，按 SKILL 适合处理通用任务拆解、检查、交付和复盘，核心价值是把输入、判断、执行、验证和交付边界固定下来，避免 Agent 泛泛回答。 把任务拆成可执行、可检查、可继续迭代的步骤；通常不需要额…
- 面向通用任务拆解、检查和交付，优先处理能明确输入、步骤和验收标准的工作。

## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。

## 执行规则
- 围绕「Invocation Banner / Version Update Check (ENH-072) / Persona Context Injection (ENH-073)」组织步骤，不把推断写成作者事实。
- 读取文件、写入/修改文件、执行终端命令；主要在本地完成；通常不需要额外 API Key。
- 先跑小样例，确认结果可检查后再扩大任务范围。

## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown，不编造命令、平台或依赖。

证据边界与执行链路

作者原文负责流程事实；仓库文件负责来源和命令；流狐只补充适用场景、限制和质量判断。

skill "vp-evolve" {
  输入层     -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
  上下文层   -> Invocation Banner / Version Update Check (ENH-072) / Persona Context Injection (ENH-073)
  规则层     -> SKILL.md 触发条件 / 执行顺序 / 输出格式
  运行层     -> Node.js | 读取文件、写入/修改文件、执行终端命令 | 主要在本地完成
  安全层     -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
  输出层     -> 可复制结果 + 检查清单 + 下一步迭代
}

解读按原文结构重写，命令、链接、术语均保留；右侧可核对作者原始 SKILL.md

先判断是否适合

核心用途：vp-evolve 是一个通用扩展技能，按 SKILL 适合处理通用任务拆解、检查、交付和复盘，核心价值是把输入、判断、执行、验证和交付边界固定下来，避免 Agent 泛泛回答。把任务拆成可执行、可检查、可继续迭代的步骤；通常不需要额外 API Key…
适用任务：更适合通用任务拆解、检查、交付和复盘，尤其是输入、步骤、验收口径可以反复复用的场景。
不宜硬套：如果任务只有一次性问答、来源材料很少，或需要作者没有说明的命令和外部服务，应先降级为普通对话。

作者设计意图

触发依据：使用时机、上下文收集、输出格式和失败处理共同决定它是否适合当前任务。
来源边界：作者原文负责事实，仓库文件负责命令和文件证据；Fluxly 只补充用途、限制和使用判断。

作者的方法与取舍

执行主线：任务围绕「Invocation Banner / Version Update Check (ENH-072) / Persona Context Injection (ENH-073)」组织，把触发条件、必要上下文、执行规则和交付标准连成一条可复核的链路。
设计重点：重点不在重复教程，而在解释作者为什么规定这些步骤、哪些条件不可省略，以及结果偏离时应回到哪一层检查。
使用判断：先确认任务与原文边界一致，再决定是否启用；来源没有说明的命令、平台和依赖保持未知，不由 Fluxly 补写。

边界和复核

依赖条件：通常不需要额外 API Key，适合先用小任务验证触发是否稳定。
权限提醒：会涉及 read / write / shell-exec 权限，执行前要说明可读写范围、命令边界和回退方式。
质量标准：结果应包含明确产物、必要证据和下一步动作；如果只是泛泛解释，需要补充输入和验收条件后重跑。

## 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)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

## Version Update Check (ENH-072)

After displaying the greeting banner, run:

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)

## 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. ## 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)

## 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

## 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.

## 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

## 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

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.

## 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.

Upgrade or expand the project after completing a milestone or when new features are needed.

Modes:

Add Feature - Add a feature to the current milestone
New Milestone - Start a new milestone
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

@$HOME/{envToolDir}/workflows/evolve.md 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)".

Step 1: Detect Current State

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

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

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

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

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)

- [ ] 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

安装命令

一键复制安装选择包管理器,点击右侧复制,粘贴到终端回车即可

npx skills add 0-CODE/viepilot/skills/vp-evolve -y

查看通用安装教程

查看 Skill 原文

兼容工具

Claude Code
Cursor
Cline
Codex
Windsurf
Gemini
OpenCode
Roo Code
AAide
+Augment
GitHub Copilot
OpenClaw
KKiro
Junie
WWarp
Goose
Trae
Kilo Code
OpenHands
Amp
Zencoder
CContinue
AIAider
CodeBuddy
CodeGeeX
Replit Agent

安全审计

92 / 100

已审计

未声明 license/许可。
未限定 allowed-tools，默认拥有全部工具权限。

元信息

来源: github
0-CODE/viepilot
版本: 0.3.0
English

@0-CODE 的其他技能

分类与标签

分类其他

先判断是否适合

作者设计意图

作者的方法与取舍

边界和复核

B. User Prompting

C. Tool Usage

C. Tool Usage

C. Tool Usage

C. Tool Usage

C. Tool Usage

ViePilot Namespace Guard (BUG-004)

Step 1: Detect Current State

Step 2: Ask User Intent

Step 3A: Add Feature Mode

Step 3B: New Milestone Mode

Step 3C: Refactor Mode

Step 4: Update Version

Step 5: Confirm & Suggest Next

Adapter Compatibility

AskUserQuestion Tool (ENH-048 + ENH-055)

讨论