Agent安装

Name: Agent安装
Author: 0-CODE

其他已审计 v0.2.0

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 · v0.2.0 · 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-request.preview

---
name: vp-request
description: Create new request: feature, bug fix, enhancement, or brainstorm continuation Output this banner…
category: 通用
runtime: Node.js
---

# vp-request 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-request
description: Create new request: feature, bug fix, enhancement, or brainstorm continuation Output this banner…
category: 通用
source: 0-CODE/viepilot
---

# vp-request

## 什么时候使用
- vp-request 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…
- 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-request" {
  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-request 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-REQUEST  v0.2.0 (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-request`, `/vp-request`, "request", "yêu cầu", "bug", "lỗi", "feature mới", "nâng cấp" - Treat all user text after the skill mention as `{{VP_ARGS}}`

B. User Prompting

Prompt user conversationally with numbered list 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 only creates requests, backlog, triage (.viepilot/requests/*, TRACKER, sometimes suggests ROADMAP) — does not implement default shipping code (lib/, tests/, bin/, workflows/, skills/ of the repo, etc.).
After request: /vp-evolve (ROADMAP + phase + tasks + plan) → /vp-auto (execute). See workflows/request.md.
Exception: User explicit (hotfix now, fix in this chat, bypass planning) — must state clearly the bypass in chat.
Do not suggest ”Start working now” as direct implementation in this thread; use evolve → auto instead.

Create and manage requests for the project under development: - Bug report and fix - Feature request - Enhancement/Improvement - Technical debt - Brainstorm continuation for new ideas

Creates/Updates:

.viepilot/requests/{TYPE}-{NUMBER}.md
.viepilot/TRACKER.md (add to backlog)
.viepilot/ROADMAP.md (if approved)

Routes to: /vp-auto or /vp-evolve depending on request type

@$HOME/{envToolDir}/workflows/request.md Optional flags: - `--bug` : Bug report mode - `--feature` : Feature request mode - `--enhance` : Enhancement mode - `--debt` : Technical debt mode - `--brainstorm` : Brainstorm continuation mode - `--list` : List pending requests - `--quick` : Quick mode (minimal questions)

URL Auto-Enrichment (ENH-093)

If your request originates from an existing issue tracker, pass the URL directly:

/vp-request https://github.com/org/repo/issues/123
/vp-request https://company.atlassian.net/browse/PROJ-456
/vp-request https://trello.com/c/cardId/card-title
/vp-request https://linear.app/team/issue/ENG-789
/vp-request https://notion.so/page-slug-abc123

ViePilot automatically extracts: title, type, description, priority — you confirm or edit. Requires: browser-intake-agent + vercel-labs/agent-browser (npx skills add vercel-labs/agent-browser).

Supported sources: GitHub Issues, Linear, Jira (Atlassian), Trello, Notion.

When extraction is unavailable (non-CC adapter or agent-browser not installed), the URL is stored as a related_url field in the request file and the normal question flow proceeds.

Execute workflow from `@$HOME/{envToolDir}/workflows/request.md`

Step 1: Detect Request Type

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 VIEPILOT ► REQUEST
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

What type of request?

1. 🐛 Bug Report - Something is broken
2. ✨ Feature Request - New functionality
3. 🔧 Enhancement - Improve existing feature
4. 🧹 Technical Debt - Code cleanup/refactor
5. 💡 Brainstorm - Explore new ideas
6. 📋 List Requests - View pending requests

Step 2: Gather Request Details

For Bug Report (🐛)

Bug Details:

1. Title/Summary?
2. What happened? (actual behavior)
3. What should happen? (expected behavior)
4. Steps to reproduce?
5. Which part of system? (service/module)
6. Severity? (critical/high/medium/low)
7. Any error messages/logs?

For Feature Request (✨)

Feature Details:

1. Title/Summary?
2. What problem does it solve?
3. Describe the feature
4. Who benefits from this?
5. Priority? (must-have/should-have/nice-to-have)
6. Any specific requirements?

Do you want to brainstorm this feature in detail? (y/n)
→ If yes: route to mini brainstorm session

For Enhancement (🔧)

Enhancement Details:

1. Title/Summary?
2. Which existing feature to enhance?
3. Current behavior
4. Desired improvement
5. Why is this valuable?
6. Breaking changes? (yes/no)

For Technical Debt (🧹)

Tech Debt Details:

1. Title/Summary?
2. What needs cleanup?
3. Current issues (performance/maintainability/etc)
4. Proposed solution
5. Effort estimate? (S/M/L/XL)
6. Risk if not addressed?

For Brainstorm (💡)

Brainstorm Topic:

1. What do you want to explore?
2. Related to existing feature or completely new?
3. Any initial ideas?

→ Route to full brainstorm session with context

Step 3: Create Request File

Create .viepilot/requests/{TYPE}-{NUMBER}.md:

# {TYPE}: {TITLE}

## Meta
- **ID**: {TYPE}-{NUMBER}
- **Type**: Bug | Feature | Enhancement | Tech Debt
- **Status**: new | triaged | in_progress | done | wont_fix
- **Priority**: critical | high | medium | low
- **Created**: {timestamp}
- **Reporter**: User
- **Assignee**: AI

## Summary
{SUMMARY}

## Details
{DETAILS_BASED_ON_TYPE}

## Acceptance Criteria
- [ ] {criteria_1}
- [ ] {criteria_2}

## Related
- Phase: {if linked to phase}
- Files: {affected files}
- Dependencies: {related requests}

## Discussion
{Any additional context from brainstorm}

## Resolution
{Filled when resolved}

Step 4: Triage & Route

Based on request type and priority:

Critical Bug:

⚠️ Critical bug detected!

Options:
1. Fix immediately (pause current work)
2. Add to top of current phase
3. Schedule for next available slot

Feature/Enhancement:

Request logged: {TYPE}-{NUMBER}

Options:
1. Add to current milestone backlog
2. Brainstorm in detail first
3. Schedule for next milestone
4. Plan then execute: `/vp-evolve` → `/vp-auto` (not direct implement here unless explicit override)

Tech Debt:

Tech debt logged: {TYPE}-{NUMBER}

Options:
1. Add to refactor backlog
2. Include in next phase
3. Create dedicated cleanup phase

Step 5: Update Tracking

Update .viepilot/TRACKER.md:

## Backlog

### Pending Requests
| ID | Type | Title | Priority | Status |
|----|------|-------|----------|--------|
| BUG-001 | 🐛 | Login timeout | high | new |
| FEAT-002 | ✨ | Export feature | medium | triaged |

Step 6: Confirm & Next Steps

Display confirmation banner:

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 VIEPILOT ► REQUEST CREATED ✓
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

 ID: {TYPE}-{NUMBER}
 Type: {TYPE}
 Title: {TITLE}
 Priority: {PRIORITY}
 Status: {STATUS}

 File: .viepilot/requests/{TYPE}-{NUMBER}.md
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Claude Code (terminal) — REQUIRED: After banner, call AskUserQuestion:

question: "Request {TYPE}-{N} logged. What would you like to do next?"
options:
  - label: "Plan phase + tasks → /vp-evolve"
    description: "Create ROADMAP entry, phase dir, and task files now (Recommended)"
  - label: "Create another request → /vp-request"
    description: "Log more requests before planning"
  - label: "Done for now"
    description: "Exit — request is saved in backlog"

On selection:

"Plan phase + tasks → /vp-evolve": invoke /vp-evolve skill
"Create another request → /vp-request": invoke /vp-request skill
"Done for now": print "Request {TYPE}-{N} saved in backlog." and exit

Text fallback (Cursor/Codex/Copilot/Antigravity):

Next actions:
  /vp-evolve    Plan phase/tasks + ROADMAP
  /vp-request   Create another request

- [ ] Request type identified - [ ] Details gathered appropriately - [ ] Request file created - [ ] TRACKER.md updated - [ ] Appropriate routing suggested

Adapter Compatibility

AskUserQuestion Tool (ENH-048)

This skill uses adapter-aware interactive prompts. Behavior depends on your adapter:

Adapter	Interactive Prompts	Notes
Claude Code (terminal)	✅ `AskUserQuestion` tool — REQUIRED	Must call AUQ; plain-text only if tool errors or is unavailable
Claude Code (VS Code ext)	⚠️ Partial	Terminal yes; VS Code UI pending anthropics/claude-code#12609
Cursor (Plan Mode)	⚠️ Partial	`AskQuestion` in Plan Mode only — not in Agent/Skills Mode
Cursor (Agent/Skills)	❌ Text fallback	AskQuestion not available in Agent Mode
Codex CLI	❌ Text fallback	Native tool N/A; community MCP available
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.

When AskUserQuestion is not available on other adapters, the skill automatically falls back to plain-text numbered list prompts — no configuration required.

Prompts using AskUserQuestion in this skill:

Request type detection (Bug / Feature / Enhancement / Tech Debt — Step 2)
Bug severity selection (Critical / High / Medium / Low — Step 4A)
Feature priority selection (Must-have / Should-have / Nice-to-have — Step 4B)
Workflow continuation (Step 6 — Plan /vp-evolve / Create another / Done)

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-request -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: 0.2.0
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)

URL Auto-Enrichment (ENH-093)

Step 1: Detect Request Type

Step 2: Gather Request Details

For Bug Report (🐛)

For Feature Request (✨)

For Enhancement (🔧)

For Technical Debt (🧹)

For Brainstorm (💡)

Step 3: Create Request File

Step 4: Triage & Route

Step 5: Update Tracking

Step 6: Confirm & Next Steps

Adapter Compatibility

AskUserQuestion Tool (ENH-048)

讨论