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

spec-driven-auto规格驱动汽车

Agent Skill

spec-driven-auto 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

890

周安装

36

GitHub Stars

公开资料未说明

下载量

279
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-auto(规格驱动汽车)
来源仓库:https://github.com/kw12121212/auto-spec-driven
仓库路径:skills/spec-driven-auto
安装命令:
npx skills add https://github.com/kw12121212/auto-spec-driven --skill spec-driven-auto
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/auto-spec-driven --skill spec-driven-auto

简介

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、任务场景或来源线索快速定位候选结果。

  • 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。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装 spec-driven-auto 技能。
  • 当前无额外说明,需参考原始 SKILL.md 获取完整功能细节。

SKILL.md

You are running the full spec-driven workflow end-to-end for a single change.

This Skill's Commands

If you cannot remember the exact command used by this skill, look it up here before running anything. Do not guess.

propose: node {{SKILL_DIR}}/scripts/spec-driven.js propose <name>
apply: node {{SKILL_DIR}}/scripts/spec-driven.js apply <name>
verify: node {{SKILL_DIR}}/scripts/spec-driven.js verify <name>
audit-unmapped-spec-evidence: node {{SKILL_DIR}}/scripts/spec-driven.js audit-unmapped-spec-evidence [--implementation <repo-path> ...] [--tests <repo-path> ...]
verify-spec-mappings: node {{SKILL_DIR}}/scripts/spec-driven.js verify-spec-mappings
archive: node {{SKILL_DIR}}/scripts/spec-driven.js archive <name>

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. Load context — rebuild working context from the current files before doing anything:

- You MUST treat all prior conversational context as stale, unreliable, and non-authoritative. - You MUST NOT use prior chat context as a source of truth for requirements, task state, implementation details, or completion status. - You MUST rebuild working context from the current change artifacts, relevant base specs, and the current repository state before taking any workflow action. - If prior chat context differs from the files or repository state in any way, you MUST discard the prior chat context and follow the files and repository state only. - Do not use prior chat context unless it has been explicitly re-validated against the current files and repository state.

  1. Assess complexity — before doing anything else, evaluate the change using a two-tier model:

- Read .spec-driven/config.yaml for project context - Read .spec-driven/specs/INDEX.md and relevant spec files to understand the current system - Read the codebase files that the change will likely touch — estimate the number of files, modules, and cross-cutting concerns involved - Classify the change into one of two tiers: - Green (proceed): clear scope and a concrete definition of done within a single repository, including changes that touch up to 15 modules or packages, modify up to 50 files, involve schema migrations with data transformation, modify existing auth/authz/payment logic, or make cross-cutting changes across multiple subsystems — proceed automatically - Red (suggest brainstorm): requires coordinating across multiple services or repositories, scope is vague or open-ended (e.g. "refactor the codebase", "improve performance"), or has no clear definition of done — explain why and suggest running /spec-driven-brainstorm first to converge the idea, then entering /spec-driven-auto to execute the resulting proposal - If Red, stop and suggest brainstorm - If Green, proceed

  1. Propose — run /spec-driven-propose:

- Run node {{SKILL_DIR}}/scripts/spec-driven.js propose <name> - Fill all artifacts: proposal.md (with Unchanged Behavior), specs/ delta files, design.md, tasks.md (with ## Testing), questions.md (open questions) - Show the user a summary: scope, key decisions, task count, unchanged behaviors, and any open questions - If questions.md has open questions, list them and stop for user resolution before proceeding — do not continue until every open question is explicitly resolved - If there are no open questions, proceed directly to Step 4 without waiting for confirmation

  1. Apply — implement all tasks:

- Run node {{SKILL_DIR}}/scripts/spec-driven.js apply <name> to show task summary - Check questions.md for open - [] Q: entries — if any, present each unresolved question using: - Question - Explanation - Impact - Recommendation - Explanation must clarify why the question is still unresolved after reading the current change artifacts, relevant main specs, and repository state - Impact must describe what implementation choice, task, behavior, or unchanged-behavior guarantee depends on the answer - Recommendation may suggest a preferred answer, but only as a suggestion - After presenting those blocks, ask the user to answer or confirm the decision needed, and stop until the user explicitly resolves every open question - You MAY recommend a preferred answer, but only as a suggestion; you MUST NOT treat your own recommendation as a resolved answer or continue implementation until the user explicitly confirms it - Work through each - [] task in order: read code, implement, verify Unchanged Behavior, mark - [x] - For ## Testing tasks: actually run the tests and confirm they pass - Run node {{SKILL_DIR}}/scripts/spec-driven.js apply <name> to confirm remaining === 0

  1. Verify — check completeness:

- Run node {{SKILL_DIR}}/scripts/spec-driven.js verify <name> - Then perform the rest of the /spec-driven-verify checks: task completion, open questions, implementation evidence, and spec alignment - If the change-local evidence set includes implementation files or directly verifying test files, run node {{SKILL_DIR}}/scripts/spec-driven.js audit-unmapped-spec-evidence [--implementation <repo-path>...] [--tests <repo-path>...] as part of this verify pass and treat its current-change blocking findings the same way /spec-driven-verify would - Treat script errors plus any CRITICAL findings from those checks as blockers - If there are blockers you can safely fix, fix them automatically, then rerun both node {{SKILL_DIR}}/scripts/spec-driven.js verify <name> and the verification pass - If any blocker cannot be auto-fixed: stop and ask the user - Re-read delta spec files and update them to match what was actually implemented - Ensure delta spec mapping frontmatter reflects the implementation and test files actually changed or relied on

  1. Review — check code quality:

- Read every file changed by this change - Review findings must be author-agnostic: do not trust or excuse code just because it was generated or edited earlier in this same auto run - Check: readability, security, error handling, performance, best practices, test quality - Reuse the verify-phase node {{SKILL_DIR}}/scripts/spec-driven.js audit-unmapped-spec-evidence [--implementation <repo-path>...] [--tests <repo-path>...] result unless review fixes changed the relevant implementation or direct test files; only rerun that same command when the reviewed evidence set materially changed - MUST FIX issues: fix them automatically, then re-review - If MUST FIX issues cannot be auto-fixed: stop and ask the user - SHOULD FIX and NITS: fix if straightforward, otherwise note in the final report

  1. Archive — close out the change:

- Confirm there are no incomplete tasks before archiving - List all delta files in specs/ and merge each into the corresponding main spec file - If changes/<name>/specs/ is empty, ask the user to confirm this change has no observable spec impact before continuing - Update .spec-driven/specs/INDEX.md if new spec files were created - Run node {{SKILL_DIR}}/scripts/spec-driven.js verify-spec-mappings after merging mapping frontmatter into main specs - Run node {{SKILL_DIR}}/scripts/spec-driven.js archive <name> - If .spec-driven/roadmap/ exists, treat any milestone declared status or roadmap index updates performed by the archive command as part of archive closeout - Report the final result: what was built, files changed, tests passing, archive location, and any roadmap status changes caused by archive - If the user wants to commit and push the completed archived change, offer /spec-driven-ship <name> as the next explicit handoff. Keep that handoff advisory only: do not stage files, inspect push eligibility, enter that workflow, commit, or push unless the user explicitly chooses it.

Rules

  • The context reset in Step 1 is mandatory — never skip it
  • The complexity check in Step 2 is mandatory — never skip it
  • The workflow runs fully automatically — do not pause for confirmation except when open questions in questions.md need user resolution
  • Additional confirmations are required whenever the workflow is blocked by unresolved questions or an empty delta-spec archive decision
  • All other steps run automatically unless blocked by an unresolvable issue
  • Follow all config.yaml rules (specs, change, code, test) throughout
  • If anything goes wrong mid-flow, stop and explain — do not silently continue
  • Mark tasks complete one at a time, not in bulk
  • Recommended answers do not count as question resolution without explicit user confirmation
  • Keep implementation and test mappings in frontmatter, not in requirement prose
  • Do not commit or push automatically. Shipping is handled only by the explicit /spec-driven-ship <name> workflow after successful archive closeout.

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

33.78%
按下载量换算94

Claude

31.71%
按下载量换算88

Cursor

17.21%
按下载量换算48

Gemini CLI

9.28%
按下载量换算26

安全审计

Gen Agent Trust Hub

可疑

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。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