Agent安装

Name: Agent安装
Author: 0-CODE

工程开发已审计 v0.1.1

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: 工程开发
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 · v0.1.1 · 未声明 license
Token 消耗评级: 低消耗
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-pause.preview

---
name: vp-pause
description: Pause work with context preservation to resume later Output this banner as the first thing on ev…
category: 工程开发
runtime: Node.js
---

# vp-pause 输出预览

## PART A: 任务判断
- 适用问题：代码实现、重构、调试或代码审查。
- 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代码实现、重构、调试或代码审查，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-pause
description: Pause work with context preservation to resume later Output this banner as the first thing on ev…
category: 工程开发
source: 0-CODE/viepilot
---

# vp-pause

## 什么时候使用
- vp-pause 是一个工程开发方向的技能，扩展 Agent 在写代码、做 review、跑测试这类场景下的能力 适合处理工程开发场景下的代码实现、调试、重构、测试或代码审查，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…
- 面向代码实现、重构、调试或代码审查，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-pause" {
  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-pause 是一个工程开发方向的技能，扩展 Agent 在写代码、做 review、跑测试这类场景下的能力适合处理工程开发场景下的代码实现、调试、重构、测试或代码审查，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…
适用任务：更适合工程开发场景下的代码实现、调试、重构、测试或代码审查，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-PAUSE  v0.1.1 (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-pause`, `/vp-pause`, "pause", "dừng", "tạm nghỉ" - Treat all user text after the skill mention as `{{VP_ARGS}}`

B. User Prompting

Prompt user conversationally to gather state info.

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)

Handoff state — does not implement shipping; resume with /vp-resume then /vp-auto per plan. See workflows/request.md.

Save complete work state so it can be resumed from any context.

Creates/Updates:

.viepilot/HANDOFF.json - Machine-readable state
.viepilot/phases/{current}/.continue-here.md - Human-readable context
Git WIP commit

After: Safe to close session. Resume with /vp-resume

@$HOME/{envToolDir}/workflows/pause-work.md Execute workflow from `@$HOME/{envToolDir}/workflows/pause-work.md`

Step 1: Detect Current Position

# Find current phase from TRACKER.md or recent files
Read TRACKER.md → current_phase, current_task
Check PHASE-STATE.md → task status

Step 2: Gather State

Collect:

Current position: Phase, task, line
Work completed: What got done this session
Work remaining: What's left
Decisions made: Key decisions and rationale
Blockers/issues: Anything stuck
Human actions pending: Manual interventions needed
Background processes: Running servers/watchers
Uncommitted files: Changes not yet committed

Ask user for clarifications if needed.

Step 3: Write HANDOFF.json

{
  "version": "1.0",
  "timestamp": "{ISO8601}",
  "phase": "{phase_number}",
  "phase_name": "{phase_name}",
  "task": "{current_task}",
  "total_tasks": "{total}",
  "status": "paused",
  "completed_tasks": [...],
  "remaining_tasks": [...],
  "blockers": [...],
  "human_actions_pending": [...],
  "decisions": [...],
  "uncommitted_files": [...],
  "next_action": "{specific first action when resuming}",
  "context_notes": "{mental state, approach}"
}

Step 4: Write .continue-here.md

---
phase: {phase}
task: {task}
total_tasks: {total}
status: in_progress
last_updated: {timestamp}
---

<current_state>
[Where exactly are we? Immediate context]
</current_state>

<completed_work>
- Task 1: [name] - Done
- Task 2: [name] - In progress, [what's done]
</completed_work>

<remaining_work>
- Task 2: [what's left]
- Task 3: Not started
</remaining_work>

<decisions_made>
- Decided [X] because [reason]
</decisions_made>

<blockers>
- [Blocker]: [status/workaround]
</blockers>

<context>
[Mental state, what were you thinking]
</context>

<next_action>
Start with: [specific first action when resuming]
</next_action>

Step 5: Git Commit

git add -A
git commit -m "wip({phase}): paused at task {task}/{total}"

Step 6: Confirm

✓ Work paused successfully

Current state:
- Phase: {phase_name}
- Task: {task} of {total}
- Status: {status}
- Blockers: {count}

Files saved:
- .viepilot/HANDOFF.json
- .viepilot/phases/{phase}/.continue-here.md

To resume: /vp-resume

- [ ] HANDOFF.json created with complete state - [ ] .continue-here.md created in phase directory - [ ] All sections filled with specific content - [ ] Uncommitted changes identified - [ ] Git WIP commit created - [ ] User knows how to resume

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-pause -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: 0.1.1
English

@0-CODE 的其他技能

分类与标签

分类工程开发

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 Position

Step 2: Gather State

Step 3: Write HANDOFF.json

Step 4: Write .continue-here.md

Step 5: Git Commit

Step 6: Confirm

讨论