能力标签

💬

Prompt模板

OpenCode

基于 TypeScript · 专业级提示词模板，解锁 AI 的真实潜力

英文名：vv-opencode

⭐ 6 Stars 💻 TypeScript 📄 未公布协议 🏷 AI 7.5分

7.5AI 综合评分

promptagent-workflowai-agentbunclidev-toolstypescript

⚙️ 配置说明 🔍 查看原项目

✦ AI Skill Hub 推荐

AI Skill Hub 推荐使用：OpenCode 是一款优质的Prompt模板。AI 综合评分 7.5 分，在同类工具中表现稳健。如果你正在寻找可靠的Prompt模板解决方案，这是一个值得深入了解的选择。

📚 深度解析

OpenCode 是经过精心设计和实践验证的专业 Prompt 模板。Prompt 工程（Prompt Engineering）是充分发挥 Claude、ChatGPT 等大型语言模型潜力的关键技能，而一套经过优化的 Prompt 模板可以将 AI 输出质量提升数倍。

优质 Prompt 模板的核心价值在于其结构化设计：明确的角色设定、精确的任务描述、具体的输出格式要求和必要的边界条件，这些要素共同构成了一个能够持续产出高质量结果的 Prompt 框架。OpenCode 提供的模板经过反复迭代和用户验证，能够有效减少 AI 的"幻觉"（Hallucination）和输出不稳定问题。

无论你使用 Claude 3.5 Sonnet、GPT-4、Gemini 还是国内的文心一言、智谱 AI，优质的 Prompt 设计都能跨模型复用。AI Skill Hub 建议将本模板保存为个人 Prompt 库的标准组件，根据具体场景调整参数后反复使用，形成自己的 AI 提效工作流。

📋 工具概览

OpenCode是一款开源Prompt模板，提供了6个插件、管理代理、工作项流程和Bun等功能，值得关注。

OpenCode 是经过精心设计和反复验证的专业 Prompt 模板集合。这些 Prompt 框架能够有效激活 Claude、ChatGPT 等大型语言模型的深层能力，让 AI 生成更准确、更有价值的输出结果。无需任何安装，直接复制模板内容到 AI 对话框即可使用。

GitHub Stars

⭐ 6

开发语言

TypeScript

支持平台

Windows / macOS / Linux

维护状态

轻量级项目，按需更新

开源协议

未公布

AI 综合评分

7.5 分

工具类型

Prompt模板

Forks

—

📖 中文文档

以下内容由 AI Skill Hub 根据项目信息自动整理，如需查看完整原始文档请访问底部「原始来源」。

OpenCode是一款开源Prompt模板，提供了6个插件、管理代理、工作项流程和Bun等功能，值得关注。

📌 核心特色

精心设计的 Prompt 框架，快速激活 AI 的深层能力
支持参数化替换，灵活适配多种业务场景
经过反复验证的指令结构，显著提升 AI 输出质量和一致性
适用于 Claude、ChatGPT 等主流大语言模型
可作为团队标准 Prompt 模板复用和二次开发

🎯 主要使用场景

快速生成高质量的专业文案、分析报告或结构化内容
利用 Prompt 框架引导 AI 解决特定领域的复杂问题
在不同 AI 工具间复用经过验证的提示词模板

以下安装命令基于项目开发语言和类型自动生成，实际以官方 README 为准。

安装命令

# Prompt 无需安装，直接复制使用
# 支持：Claude / ChatGPT / Gemini / 通义千问 等主流模型

# 使用步骤
# 1. 复制 Prompt 模板内容
# 2. 粘贴到 AI 对话框
# 3. 替换 [占位符] 为实际内容
# 4. 发送后获取结构化输出

# 获取原始文件
git clone https://github.com/osovv/vv-opencode

📋 安装步骤说明

复制本工具的 Prompt 模板内容
打开 Claude、ChatGPT 或其他 AI 对话工具
将 Prompt 粘贴到对话框开头
根据实际需求替换 [占位符] 中的内容
发送后 AI 将按照模板格式执行，获得结构化输出

以下用法示例由 AI Skill Hub 整理，涵盖最常见的使用场景。

常用命令 / 代码示例

# 粘贴到 Claude/ChatGPT 使用
# 示例 Prompt 结构：

你是一位 [角色]，擅长 [领域]。
请根据以下要求完成任务：

任务背景：[描述背景]
具体要求：[详细说明]
输出格式：[期望格式]

# 将 [] 内内容替换为实际需求

以下配置示例基于典型使用场景生成，具体参数请参照官方文档调整。

配置示例

# vv-opencode 配置说明
# 查看配置选项
vv-opencode --config-example > config.yml

# 常见配置项
# output_dir: ./output
# log_level: info
# workers: 4

# 环境变量（覆盖配置文件）
export VV_OPENCODE_CONFIG="/path/to/config.yml"

📑 README 深度解析真实文档完整度 70/100 查看 GitHub 原文 →

以下内容由系统直接从 GitHub README 解析整理，保留代码块、表格与列表结构。

@osovv/vv-opencode

Portable OpenCode workflow toolkit — one command bootstraps a managed agent ecosystem, skill-driven spec-to-code pipeline, security-and-productivity plugins, and a unified CLI.

---

Features

Area	What you get
Plugins	6 plugins in one pinned package entry — workflow orchestration, model roles, guardian, hashline edit, system context injection, secrets redaction
Agent System	`vv-controller` routes work: direct for small changes, `investigator` for bugs, implementer+reviewer loop for risky work, analyst+architect for large features
Skills	`vv-spec` interviews you and writes an XML spec; `vv-plan` maps the spec to interface contracts and acceptance criteria; `vv-review` runs a review-only workflow; `vv-reflect` preserves reusable session findings as repository memory — all auto-triggered
Spec-to-Code Pipeline	`vv-spec` → spec review → `vv-plan` → plan review → `vv-implementer` → code review. Three independent review gates cover requirements, contracts, and implementation
One-Click Setup	`vvoc install` or `vvoc sync` bootstraps everything — config, agents, skills, prompts, presets
CLI Tooling	15+ commands: install, sync, status, doctor, role management, presets, guardian config, shell completion, upgrade
Security	GuardianPlugin reviews shell-permission requests; SecretsRedactionPlugin strips tokens before LLM requests; both configurable via `vvoc.json`
Model Roles	Assign provider/model/variant to roles (`default`, `smart`, `fast`, `vision`, custom); switch between `vv-openai`, `vv-zai`, `vv-deepseek`, `vv-minimax` presets
Workflow Tracking	Work items with open/list/close for tracked implementation-to-review pipelines

---

Extract dependency graph

grep '<depends-on>task-' .vvoc/plans/*.xml

Quick Start

bun add -g @osovv/vv-opencode
vvoc install

That's it. vvoc install pins the package, scaffolds managed agents and skills, writes canonical config, and sets vv-controller as your default OpenCode agent with auto-triggered spec, planning, review, and reflection skills.

To scope everything to the current project instead of the global OpenCode config:

vvoc install --scope project

Already installed? Run vvoc sync anytime to refresh plugins, prompts, skills, and presets.

---

Config & Data Layout

OpenCode config          → OpenCode-managed paths (global or project)
vvoc.json (canonical)    → $XDG_CONFIG_HOME/vvoc/vvoc.json
Managed agent prompts    → $XDG_CONFIG_HOME/vvoc/agents/*.md  (global)
                           ./.vvoc/agents/*.md                 (project)
Managed skills           → $XDG_CONFIG_HOME/vvoc/skills/*/SKILL.md  (global)
                           ./.vvoc/skills/*/SKILL.md               (project)
Spec documents           → ./.vvoc/specs/*
Planning artifacts       → ./.vvoc/plans/*
Persisted data           → $XDG_DATA_HOME/vvoc/
Repository memory       → ./.vvoc/lessons/*.xml              (lazy vv-reflect fallback)
                           ./.vvoc/runbooks/*.xml             (lazy vv-reflect fallback)

Schema is versioned and published with the package — source of truth at schemas/vvoc/v3.json.

---

Optional: RTK

RTK is a CLI proxy that reduces token usage for common developer commands. The interactive vvoc init flow recommends it after setup.

CLI at a Glance

Command	Purpose
`vvoc init`	Interactive bootstrap flow
`vvoc install`	Non-interactive setup and scaffolding
`vvoc sync`	Refresh plugin entry, agents, prompts, skills, config
`vvoc status`	Show current installation state
`vvoc doctor`	Diagnose setup problems (exits non-zero on issues)
`vvoc config validate`	Validate canonical `vvoc.json`
`vvoc role list\\|set\\|unset`	Manage model role assignments
`vvoc preset list\\|show\\|<name>`	Inspect or apply named presets
`vvoc guardian config`	Print or write guardian section
`vvoc plugin list`	List OpenCode plugin entries
`vvoc patch-provider stepfun-ai\\|zai\\|openai`	Patch a global OpenCode config preset
`vvoc completion`	Install shell completions
`vvoc upgrade`	Upgrade global package and run follow-up sync
`vvoc version`	Print installed version

---

Spec-to-Code Pipeline

The core workflow is a three-stage pipeline with independent review gates at each level:

User request
    │
    ▼ auto-trigger
vv-spec  ───────────────────────────────────────→  .vvoc/specs/*.xml
    │   Grill-me interview (one question at a time)
    │   Decision tree with recommended answers
    │   vv-analyst + vv-architect synthesis
    │
    ├── ① Spec review: requirements correct, complete, unambiguous?
    │
    ▼ auto-trigger (after approval)
vv-plan  ───────────────────────────────────────→  .vvoc/plans/*-plan.xml
    │   Interface contracts with JSDoc behavior descriptions
    │   Acceptance criteria per task (grep: `<criterion-N>`)
    │   Dependency ordering (grep: `<depends-on>`)
    │   Three-layer review model: spec → plan → code
    │
    ├── ② Plan review: every spec requirement → task? Contracts match spec?
    │
    ▼ auto-trigger (after approval)
vv-implementer → vv-spec-reviewer → vv-code-reviewer
    │   Workflow tracked loop with work items
    │   Spec review checks: code matches spec?
    │   Code review checks: implementation matches plan contracts?
    │
    ├── ③ Code review: interfaces correct? All AC pass?
    │
    ▼
Done

Extract all components from plan

grep '<component>' .vvoc/plans/*.xml ```

All four skills are auto-triggered by vv-controller via its built-in <skill_trigger_rule> — no slash commands needed. The controller checks whether vv-spec, vv-plan, vv-review, or vv-reflect applies before routing any request.

---

The Six Plugins

Plugin	What it does
WorkflowPlugin	Tracked orchestration around `task` for subagents; registers `work_item_open/list/close` tools for implementation-to-review pipelines with state-machine enforcement and round-limit gating
ModelRolesPlugin	Resolves `vv-role:*` references in OpenCode config at startup; translates `:variant` suffixes into native model+variant fields
GuardianPlugin	Reviews OpenCode permission requests with a constrained guardian agent and safe-deny defaults; configurable model, timeout, risk threshold
HashlineEditPlugin	Replaces OpenCode's `edit` with hash-anchored variant; rewrites `read` output to `line#hash` format; rejects stale snapshots to prevent drift bugs
SystemContextInjectionPlugin	Injects reusable system guidance into primary sessions without polluting subagent prompts; encourages proactive `explore` usage; registers vvoc skill directory for OpenCode skill discovery
SecretsRedactionPlugin	Redacts secrets (tokens, keys, emails, UUIDs, IPs) before LLM requests; restores placeholders afterward; configurable patterns

---

CI publish workflow

The workflow uses npm provenance/trusted publishing (id-token: write) and does not publish on normal branch pushes. Configure npm trusted publishing for this GitHub repository/package, or adapt the publish step to use an NPM_TOKEN secret if token-based publishing is required.

---

🎯 aiskill88 AI 点评 A 级 2026-06-12

OpenCode是一款开源Prompt模板，提供了6个插件、管理代理、工作项流程和Bun等功能，值得关注，但需要进一步优化和完善。