Token导航 LogoToken导航TokenDH.com
开发只读github未标认证来源可访问许可证需确认审计通过

spec-driven-verify规范驱动验证

Agent Skill

spec-driven-verify 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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

329

周安装

14

GitHub Stars

公开资料未说明

下载量

115
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-driven-verify(规范驱动验证)
来源仓库:https://github.com/kw12121212/slim-spec-driven
仓库路径:skills/spec-driven-verify
安装命令:
npx skills add https://github.com/kw12121212/slim-spec-driven --skill spec-driven-verify
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/kw12121212/slim-spec-driven --skill spec-driven-verify

简介

spec-driven-verify 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。

  • 它可结合来源仓库、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。
  • 适用于需要围绕仓库状态、代码变更或协作事项进行整理的场景。
  • GitHub 仓库、Issue、Pull Request 和代码协作信息处理。

SKILL.md

You are helping the user verify a spec-driven change before archiving.

Prerequisites

The .spec-driven/ directory must exist at the project root. Before proceeding, verify:

ls .spec-driven/

If this fails, the project is not initialized. Run /spec-driven-init first.

Steps

  1. Select the change — run node {{SKILL_DIR}}/scripts/spec-driven.js modify to list active changes. Ask which change to verify. If already specified, use it.
  2. Format check — run: node {{SKILL_DIR}}/scripts/spec-driven.js verify <name> Report any errors (blocking) or warnings (non-blocking).

- If the script warns that tasks.md has no ## Testing section, promote that to a CRITICAL — every change must include test tasks

  1. Task completion check — run: node {{SKILL_DIR}}/scripts/spec-driven.js apply <name> If remaining > 0, list the incomplete tasks. These are CRITICAL issues.
  2. Open questions check — read .spec-driven/changes/<name>/questions.md and scan for - [] Q: entries:

- Any open (unanswered) question is a CRITICAL — implementation cannot be verified with unresolved ambiguity - The script also reports these as errors; treat them as CRITICALs here

  1. Implementation evidence check — for each completed task in tasks.md:

- Identify what code or files the task should have changed - Verify the change actually exists (read relevant files) - Note any tasks with no visible evidence as WARNINGs

  1. Spec alignment check — read .spec-driven/specs/, .spec-driven/config.yaml, .spec-driven/changes/<name>/proposal.md, and all files in .spec-driven/changes/<name>/specs/:

- Does the implementation match what was proposed? - Do the delta files in changes/<name>/specs/ accurately describe what was implemented? Empty specs/ with real behavior changes is a CRITICAL. - Does each delta file mirror its corresponding main spec file path? Mismatched paths mean the merge will fail. - Do the delta files use the standard format (### Requirement: <name>, RFC 2119 keywords, #### Scenario: blocks)? Non-conforming format is a CRITICAL — the spec format is mandatory. - If config.yaml has a rules field (including any fileMatch entries), check whether the implementation and artifacts comply — violations are WARNINGs - If proposal.md has an Unchanged Behavior section with content, verify the implementation has not violated any listed behaviors — violations are CRITICALs - Flag misalignments as WARNINGs or CRITICALs

  1. Output a tiered report: CRITICAL (blocks archive): - [list or "none"] WARNING (should address): - [list or "none"] SUGGESTION (optional improvements): - [list or "none"]
  2. Recommend next step:

- If CRITICAL issues: address them before archiving - If only WARNINGs: ask user if they want to address them or proceed - If clean: suggest /spec-driven-review <name>

Rules

  • Be honest — don't pass a change just because tasks are checked off
  • CRITICALs are things that would make the change incorrect or incomplete
  • WARNINGs are things that reduce confidence but don't necessarily block
  • SUGGESTIONs are optional quality improvements

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

36.25%
按下载量换算42

Claude

32%
按下载量换算37

Cursor

17.07%
按下载量换算20

Gemini CLI

9.65%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。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