to-prd

审查 · 52
已收录

Use when the user wants to write, draft, or generate a PRD after finishing work, or from a ticket, a PR, or a feature description. Triggers on /to-prd, "write a PRD", "generate a PRD", "draft a PRD", or "spec this work". Don't use for RFCs, implementation plans, or Team EEP Linea

Verified installs0
Stars39
版本1.0.0
质量57/100 · 有潜力
信任52/100 · Do not auto-install
审计68/100 · 需审查

供给资产档案

研究与知识工作

Deep research, source comparison, literature review, RAG, knowledge search, and reports.

浏览赛道

场景

研究 Agent

I need my agent to research a topic, compare sources, and produce a concise report.

适配 Agent

Claude Code + CLI + Codex

适用于 Codex、Claude Code、Cursor、CLI 或自定义 Agent。

安装

就绪

npx skills add AlemTuzlak/skills --skill to-prd

维护状态

新鲜

距上次推送 4 天

风险

需审查

许可证不清晰

GitHub 质量

39

57/100 质量 · 60/100 信任

覆盖标签

研究研究 Agentagent-skill

审查说明

许可证不清晰 · Dependency or permission surface needs review

Agent 采用评分卡

一眼查看信任、审计与安装准备度

这些分数综合公开仓库元数据、OpenAgentSkill 审查信号、维护新鲜度与安装准备度。它用于候选筛选,不替代人工审查。

质量

有潜力
57

有用的候选项,但采用前应与替代方案比较。

信任

Do not auto-install
52

Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.

审计

需审查
68

对安装准备度、安全元数据、维护情况与采用风险的机器可读审查。

OpenAgentSkill 信任评分 v5

安装前需人工审查

Choose a stronger alternative or inspect the source manually before any install attempt.

CodexClaude CodeCursorOpenAgentSkill CLI

Stars

39 个 GitHub Stars

仓库活跃度

39 个 Star,0 个 Fork

维护状态

距上次推送 4 天

许可证

未知

安装

npx skills add AlemTuzlak/skills --skill to-prd

安装安全性

标准软件包或运行时安装路径

权限范围

secrets or environment access, shell or command execution

Agent 结果

暂未有 Agent 结果数据

文档

README/SKILL.md 上下文充分

风险摘要

生产前审查

  • Repository has no detected license, so licensing clarity and permission to reuse the CopilotKit EEP template are unclear.
  • 许可证不清晰
  • Low GitHub adoption signal
  • Quality score needs review

安装准备度

安装路径可用

  • 安装路径可用
  • 仓库证据可用
  • 许可证不清晰
  • 暂无 Agent 验证结果证据

Agent 可读元数据

这个 Skill 的机器可读决策数据。

使用此区块或内嵌 JSON 判断 Agent 是否应安装该 Skill、选择替代方案,或先请求人工审查。

打开 JSON

适用任务

  • 编程 Agent 工作流
  • Claude Code 团队
  • builders willing to evaluate younger projects
  • Inspect source files

适用 Agent

CodexClaude CodeCursorOpenAgentSkill CLICLI

安装决策

命令
npx skills add AlemTuzlak/skills --skill to-prd
策略
阻止
人工审查

信任与风险

信任
52/100
审计
68/100
风险级别
需审查

结果闭环

端点
/api/agent/outcome
事件 ID
resolve
结果
5

安装命令

npx skills add AlemTuzlak/skills --skill to-prd

不适用场景

  • 需要厂商支持 SLA 的团队
  • production agents without a repository review
  • Low GitHub adoption signal
  • Repository has no detected license, so licensing clarity and permission to reuse the CopilotKit EEP template are unclear.
  • 暂未有 OpenAgentSkill 使用反馈数据

Agent 安全 v2

24/100 · 避免自动安装

Blocked for auto-install阻止

This skill should not be selected by an agent without explicit human security review.

Do not auto-install. Inspect the source, dependencies, and permission surface first.

通过 API 解析

Shell 或命令执行

Skill 元数据引用了终端、CLI、Shell、子进程或命令执行工作流。

网络访问

Skill 可能访问远程页面、API、仓库或外部服务。

文件系统访问

Skill 可能读取或写入项目文件、文档、生成产物或本地工作区状态。

Secrets or environment access

Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.

  • 高风险权限提示:Shell or command execution, Secrets or environment access
  • 许可证不清晰

安装目标

在你的 Agent 工作流中安装此 Skill

通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。

skill install

OpenAgentSkill CLI

Resolve policy, run the source installer safely, and report a verified install receipt.

$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install alemtuzlak-to-prd

Agent 解析计划

让 Agent 在安装前验证匹配度。

Resolve API 返回首选 Skill、替代方案、安全策略、审计说明、安装目标和可直接执行的提示词,无需抓取此页面。

打开文本计划

Agent 应检查

  • 从 Resolve API 检查任务匹配与替代方案。
  • 检查审计评分、信任评分和安全策略警告。
  • 检查 Codex、Claude Code、Cursor 或 CLI 的安装目标兼容性。

复制提示词

Task: Use to-prd in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20to-prd%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/alemtuzlak-to-prd/install
Install command: npx skills add AlemTuzlak/skills --skill to-prd
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Agent 交接

把安装路径交给 Agent,而不是再给一个目录页。

通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。

打开安装 API

Agent 提示词

Use to-prd for this task. Review https://www.openagentskill.com/api/skills/alemtuzlak-to-prd/install, then install with: npx skills add AlemTuzlak/skills --skill to-prd

Registry 元数据

用于自动选择 Skill 的 Agent 可读档案。

本页通过 Registry API 提供相同的决策、信任、审计、场景和安装信号,让 Agent 无需抓取界面即可排序。

打开 Manifest

适配 Agent

56/100

编程 Agent

平台

Claude Code

审计报告

需审查 · 68/100

对安装准备度、安全元数据、维护情况与采用风险的机器可读审查。

查看审计报告查看评估报告

Agent 决策面板

Needs validation for Coding agents

在将它加入 Agent 工作流前先人工审查仓库。

56
就绪度
审查
阶段

栈中角色

需要验证

主要匹配

编程 Agent

信任标签

需要人工审查

安装路径

命令已就绪

适用场景

  • 编程 Agent 工作流
  • Claude Code 团队
  • builders willing to evaluate younger projects

证据

  • 仓库近期活跃
  • 已提供安装命令或 GitHub 仓库
  • 57/100 质量档案

先审查

  • Low GitHub adoption signal
  • Repository has no detected license, so licensing clarity and permission to reuse the CopilotKit EEP template are unclear.
  • 暂未有 OpenAgentSkill 使用反馈数据

实施路径

  1. 1在沙盒 Agent 中安装它,并端到端完成一次编程 Agent任务。
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

信任档案

Do not auto-install

Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.

52
OpenAgentSkill 信任评分

GitHub 采用度

检查

39 个 GitHub Stars

Star/Fork 活跃度

检查

39 个 Star,0 个 Fork; 当前元数据中没有议题活跃度信息

近期维护

通过

距上次推送 4 天

许可证清晰度

检查

未知

积极信号

  • AI 审查已通过
  • 安装路径可用
  • 仓库证据可用
  • 近期维护的仓库
  • 安装命令未发现明显高风险模式
  • 结果闭环已就绪,但需要首次真实 Agent 运行

安装前审查

  • Repository has no detected license, so licensing clarity and permission to reuse the CopilotKit EEP template are unclear.
  • 许可证不清晰
  • Low GitHub adoption signal
  • Quality score needs review
  • Permission surface needs review: secrets or environment access, shell or command execution
  • GitHub adoption: 39 GitHub stars
  • Stars/forks activity: 39 stars, 0 forks; issue activity unavailable in current metadata
  • License clarity: Unknown
  • Dependency/runtime risk: command execution surface, credential or environment access
  • Permission surface: secrets or environment access, shell or command execution
  • 暂未有真实 Agent 结果报告
  • 无人值守安装前需要人工审查

建议操作

Choose a stronger alternative or inspect the source manually before any install attempt.

质量档案

有潜力 适用于 Agent 工作流的候选

有用的候选项,但采用前应与替代方案比较。

57
GitHub Stars
39
新鲜度
4 天前
安装就绪
许可证
未知
安装前审查: Low GitHub adoption signal · Repository has no detected license, so licensing clarity and permission to reuse the CopilotKit EEP template are unclear.

工作流匹配

在这些场景使用此 Skill

工作流匹配

加入完整工作流

替代方案短名单

安装前对比

可能适合该任务的相近 Skill。

对比全部

概览

--- name: to-prd description: Use when the user wants to write, draft, or generate a PRD after finishing work, or from a ticket, a PR, or a feature description. Triggers on /to-prd, "write a PRD", "generate a PRD", "draft a PRD", or "spec this work". Don't use for RFCs, implementation plans, or Team EEP Linear status moves. ---

# To PRD

Turn finished work, or a planned feature, into a review-ready PRD using the CopilotKit EEP spec template.

This skill writes the product spec. It does not start implementation. It does not move Linear tickets.

## Principles

- The template is the source of truth. Read `assets/prd-template.md` in full before asking questions or writing. - Grill first. Do not fill the template until the user confirms a shared understanding. - User stories are long and complete. Cover every actor and path, including empty, error, and admin cases. - Implementation Decisions name modules, interfaces, schema, and API contracts. Do not include file paths or code snippets, except a short prototype snippet that encodes a decision better than prose. - Problem and Solution are from the user's point of view, not the engineer's. - Finding facts is the agent's job. Look in the repo, the PR, the ticket, and the current session. Ask the user only for decisions.

## Process

### Phase 1: Ground

1. Read `assets/prd-template.md` in full. 2. Resolve the input: finished work in this session, a PR, a Linear or GitHub ticket, a path, or a freeform description. 3. If inside a repo, scan the affected subsystem. Prefer the current diff, the latest commits, and any linked ticket. 4. Extract facts already known so the grill does not re-ask them.

### Phase 2: Grill

Load `grill-me` if present. If `batch-grill-me` is present, use that instead (one frontier round at a time).

Walk the template as the design tree. Each template heading is a branch:

1. Problem Statement 2. Solution 3. User Stories (actors, paths, edge cases) 4. Implementation Decisions (modules, interfaces, schema, APIs) 5. Testing Decisions 6. Manual Testing Plan 7. Out of Scope 8. Further Notes

For each question, recommend an answer from the grounded facts. Do not ask for facts the agent can look up.

The phase ends when the frontier is empty and the user confirms the shared understanding.

### Phase 3: Assemble

Fill every template section. Drop the `<spec-template>` wrapper and the `<user-story-example>` block. Keep the section headings exact.

User Stories stay numbered and use: `As an <actor>, I want a <feature>, so that <benefit>`.

Confirm the output path once:

- Repo with `docs/prds/`: `docs/prds/<slug>.md` - Repo without one: `docs/prds/<slug>.md` (create the folder) - Outside a repo: the current writable directory

Ask: `I'll write the PRD to <path>. Different location?`

If the user asks for Notion, create the page after the markdown is written. Do not create Notion by default.

### Phase 4: Self-critique

Before the user sees the draft:

- Problem and Solution are from the user's view - User stories are extensive and cover all actors - Implementation Decisions have no file paths (except a marked prototype snippet) - Testing Decisions say what a good test is, which modules, and prior art - Manual Testing Plan has human-readable production steps - Out of Scope is explicit

Report what was fixed and what still needs the user.

### Phase 5: Review and open

Write the file. Open it in Plannotator (non-blocking on Windows):

```powershell Start-Process -FilePath "$env:LOCALAPPDATA\plannotator\plannotator.exe" -ArgumentList @('annotate', '<absolute-path>') ```

Print title, one line, and both the relative path and the absolute path. Do not dump the full PRD in chat.

## Error Handling

- No input: grill from the current session and repo. Do not refuse. - Ticket or PR unreadable: say so and continue from what the user described. - User cannot answer a branch: put it under Further Notes as an open question. Do not invent it.

技术详情

版本
1.0.0
许可证
Unknown
最近更新
2026年8月19日
发布时间
2026年8月19日

决策摘要

需要验证

56
就绪
审查
阶段

仓库近期活跃

审计

安装审查

安装与采用审查

68
需审查
安全性
62/100
维护状态
100/100
安装
92/100
打开完整审计查看评估报告

Agent 验证证据

Agent 验证证据

来自解析、审查、安装和一次小范围运行后的结果报告。

0
已验证
Needs first agent run自动安装: 先审查最近: 未知
成功率
近期失败
结果
0
输出质量
失败
0
不相关
0
安装次数
0
风险拦截
0
需要配置
0
生产环境
0

暂时没有 Agent 结果数据。首次 Agent 执行可以通过 /api/agent/outcome 报告成功、需要设置、风险拦截、失败或不相关。

安装

加入 Agent 工作流

免费且开源. 在生产 Agent 中安装前请先审查报告。

增长闭环

分享工具包

X

为 to-prd 准备的场景化草稿,可手动发布到 X。

策展说明
to-prd: Use when the user wants to write, draft, or generate a PRD after finishing work, or from a ti...

39 stars

https://www.openagentskill.com/skills/alemtuzlak-to-prd?ref=x
打开 X 草稿
可选:带安装命令的回复
Listing + install path for to-prd:
https://www.openagentskill.com/skills/alemtuzlak-to-prd?ref=x

Install: npx skills add AlemTuzlak/skills --skill to-prd
打开回复草稿

收录来源

Registry 收录

可认领

此列表来自公开来源,维护者认领获批前不会标记为官方。

创作者
AlemTuzlak
收录方
OpenAgentSkill 社区索引

归属链接指向公开仓库或创作者主页。创作者可认领列表以更新所有权信号。

认领此 Skill

所有者认领

认领此 Skill 页面

这条 Registry 收录 列表归属于 AlemTuzlak,但尚未标记为官方。认领后可增加已验证所有者信号,使后续发布、安装和审计更新更值得信赖。

创作者外链工具包

将证据徽章加入你的 README

在开发者评估仓库的位置展示规范页面、当前信任与审计信号,以及真实的 Agent 验证证据。

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/alemtuzlak-to-prd?metric=listed&label=Listed)](https://www.openagentskill.com/skills/alemtuzlak-to-prd)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/alemtuzlak-to-prd?metric=trust&label=Trust)](https://www.openagentskill.com/skills/alemtuzlak-to-prd)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/alemtuzlak-to-prd?metric=audit&label=Audit)](https://www.openagentskill.com/skills/alemtuzlak-to-prd/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/alemtuzlak-to-prd?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/alemtuzlak-to-prd)

作者

A

AlemTuzlak

@alemtuzlak

平台适配

健康信号

GitHub Stars
39
质量评分
34/100
最近 GitHub 推送
2026年8月19日
框架提示
未知
OpenAgentSkill 浏览量
0
复制安装命令
0
跳转点击
0

社区信号

告诉我们这个 Skill 是否对你的 Agent 工作流有帮助。汇总反馈会持续改善排序。

信任与安全

Do not auto-install

52
  • GitHub 采用度39 个 GitHub Stars检查
  • Star/Fork 活跃度39 个 Star,0 个 Fork; 当前元数据中没有议题活跃度信息检查
  • 近期维护距上次推送 4 天通过
  • 许可证清晰度未知检查
  • README/SKILL.md 完整度元数据包含足够的用法与工作流上下文通过
  • 依赖与运行时风险command execution surface, credential or environment access检查