Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问许可证需确认审计提醒

spec-generator规格生成器

Agent Skill

spec-generator 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

815

周安装

35

GitHub Stars

20

下载量

286
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:spec-generator(规格生成器)
来源仓库:https://github.com/unlearndev/skills
仓库路径:skills/spec-generator
安装命令:
npx skills add https://github.com/unlearndev/skills --skill spec-generator
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/unlearndev/skills --skill spec-generator

简介

spec-generator 用于查找、检索和筛选相关信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词或任务线索快速定位候选结果。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装,需结合原始 README 了解具体用法。
  • 安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写操作。
  • 当前归类为研究检索类技能,适用于信息探索与筛选场景。

SKILL.md

Spec Generator Skill

Turn a vague product idea — possibly supported by sketches, screenshots, notes, or other documents — into a clear, well-structured product specification document that a development team can act on.

This always produces a product spec. That covers customer-facing products, internal tools, and staff-facing systems — they're all products. Never produce a feature spec, API spec, or integration spec.

What "good" looks like

A good output spec should:

  • Be concise but complete — no padding, no gaps
  • Use plain language, not corporate jargon
  • Be opinionated where needed (e.g. suggest a sensible default stack or behaviour) while flagging where the team still needs to decide
  • Surface implicit assumptions and make them explicit
  • Feel like it was written by a thoughtful senior PM or tech lead who has thought through the edges

Process

Step 1: Gather and understand inputs

Take stock of everything the user has provided:

  • Verbal description — even one sentence is enough to start
  • Uploaded files — read all of them: notes, existing docs, data models, wireframes, screenshots, mockups
  • Images — examine carefully; extract implied features, flows, and constraints

Before drafting, review everything the user has provided and identify any gaps that would meaningfully affect the spec. Always ask about the intended technical stack if it hasn't been provided — this can influence the direction of the project and its features. Ask any other questions that cannot be reasonably inferred from the available inputs — don't ask about things that are already clear or can be decided with a sensible default. Keep the questions concise and grouped in one go, not spread across multiple turns.

Step 2: Draft the spec

Use the template below. Adapt sections as needed — not every section is required for every spec. Use your judgment. Omit sections that don't apply rather than filling them with placeholder text.


Spec Template

# [Product Name] — Specification

> **Context:** [1–2 sentences on why this is being built and what informed this spec — e.g. team discussions, user research, a UI sketch.]

## Overview

[2–4 sentences. What is this? Who uses it? What problem does it solve? What is it NOT?]

---

## Goals

- [Concrete, measurable goal]
- [Another goal]
- [Keep this list short — 3–6 items]

---

## User Roles

### [Role Name]
- [What they can do]
- [What they cannot do / what they see or don't see]
- [How they authenticate or access the system]

[Repeat for each role]

---

## Core Features

### 1. [Feature Name]

[Description. Be specific — what does the user do, what happens, what are the constraints? Mention edge cases where relevant.]

### 2. [Feature Name]

[...]

[Continue for all major features, numbered.]

---

## Technical Stack

- **[Layer]** — [Technology]
- **[Layer]** — [Technology]

Writing Guidelines

Be specific, not vague. Instead of "users can manage their account", write "users can update their email address and reset their password via a link sent to their registered email."

Resolve ambiguity with a sensible default. If the user hasn't specified something (e.g. pagination limit), pick a reasonable value and note it. Don't leave blanks.

Separate customer-facing from internal. If there are two audiences (e.g. end users + staff), make this structurally clear — separate sections, separate role descriptions.

Flag implicit constraints. If something in the inputs implies a constraint (e.g. a sketch shows no search bar → search is probably out of scope), surface it in the relevant feature description.

Technical Stack is optional. Only include it if the stack is known or strongly implied. If unknown, omit the section entirely. When suggesting technologies, web search first to ensure recommendations are current and still the standard choice — avoid packages or libraries that have been superseded or fallen out of common use.

Never include an "Out of Scope" section. The spec template is the only structure — do not add any sections beyond what is in the template.


Output Format

Produce the spec as a .md file saved to /mnt/user-data/outputs/spec.md. Present it to the user using present_files.

After presenting the file, give a brief summary (1–2 sentences max) noting any significant assumptions you made.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.86%
按下载量换算97

Claude

32.01%
按下载量换算92

Cursor

21.49%
按下载量换算61

Gemini CLI

10.08%
按下载量换算29

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills