config-export
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
Chineseconfig-export
config-export
Exports CLAUDE.md and ai-context/ to tool-native instruction files for GitHub Copilot, Google Gemini, and Cursor.
Triggers: , export config, copilot instructions, gemini config, cursor rules
/config-export将CLAUDE.md和ai-context/导出为适用于GitHub Copilot、Google Gemini和Cursor的工具原生指令文件。
触发词:/config-export、export config、copilot instructions、gemini config、cursor rules
Purpose
用途
config-exportCLAUDE.mdai-context/config-exportCLAUDE.mdai-context/Process
流程
Step 1 — Source collection
步骤1 — 源文件收集
Guard — no CLAUDE.md:
If no exists in the current working directory, present the user with two paths:
CLAUDE.mdNo CLAUDE.md found in the current directory.
Choose an option:
1. project-setup first — run /project-setup to scaffold CLAUDE.md + ai-context/ in this project,
then re-run /config-export (recommended for new projects with SDD workflow)
2. SDD bootstrap — generate a minimal .github/copilot-instructions.md from the global SDD
template only (no project-specific stack or conventions)
Enter 1 or 2 (or press Enter to cancel):- If the user selects 1: emit and stop. No files are written.
Run /project-setup, then re-run /config-export - If the user selects 2: proceed using the global SDD methodology as the sole source bundle (skip ai-context/ collection; note "No project CLAUDE.md — bootstrap mode" in transformation context).
- If the user cancels: emit and stop.
Export cancelled — no files written
Guard — no ai-context/:
If no directory is present, emit:
ai-context/WARNING: ai-context/ not found — export quality will be lower; only CLAUDE.md will be used as sourceContinue; alone is sufficient.
CLAUDE.mdRead and bundle source files in priority order:
| # | File | Required? | Behavior when absent |
|---|---|---|---|
| 1 | | Yes | Halt (see guard above) |
| 2 | | No | Skip; note "stack.md not available" in transformation context |
| 3 | | No | Skip; note "architecture.md not available" in transformation context |
| 4 | | No | Skip; note "conventions.md not available" in transformation context |
| 5 | | No | Skip silently if absent |
All present files are read into the in-context bundle before any transformation begins.
防护机制 - 无CLAUDE.md文件:
如果当前工作目录中不存在,则为用户提供两个选项:
CLAUDE.md当前目录未找到CLAUDE.md文件。
请选择一个选项:
1. 先执行project-setup — 运行/project-setup在当前项目中搭建CLAUDE.md + ai-context/,
然后重新运行/config-export(推荐给使用SDD工作流的新项目)
2. SDD引导模式 — 仅从全局SDD模板生成最小化的.github/copilot-instructions.md
(不包含项目专属的技术栈或约定)
输入1或2(或按回车键取消):- 如果用户选择1:输出并终止流程,不写入任何文件。
请运行/project-setup,然后重新运行/config-export - 如果用户选择2:使用全局SDD方法作为唯一源包继续执行(跳过ai-context/文件收集;在转换上下文中标注"无项目CLAUDE.md — 引导模式")。
- 如果用户取消:输出并终止流程。
导出已取消 — 未写入任何文件
防护机制 - 无ai-context/目录:
如果不存在目录,输出:
ai-context/警告:未找到ai-context/目录 — 导出质量会降低;仅将CLAUDE.md作为源文件使用继续执行;仅也可满足需求。
CLAUDE.md按优先级读取并打包源文件:
| 序号 | 文件路径 | 是否必填 | 文件不存在时的处理方式 |
|---|---|---|---|
| 1 | | 是 | 终止流程(见上述防护机制) |
| 2 | | 否 | 跳过;在转换上下文中标注"stack.md不可用" |
| 3 | | 否 | 跳过;在转换上下文中标注"architecture.md不可用" |
| 4 | | 否 | 跳过;在转换上下文中标注"conventions.md不可用" |
| 5 | | 否 | 若不存在则静默跳过 |
在开始任何转换之前,所有存在的文件都会被读取到上下文包中。
Step 2 — Target selection
步骤2 — 目标选择
If the user provided a target as a CLI argument (e.g., ), skip the interactive menu and proceed directly to Step 3 with that target.
/config-export copilotOtherwise, present the target menu:
Available export targets:
1. copilot → .github/copilot-instructions.md
2. gemini → GEMINI.md
3. cursor → .cursor/rules/conventions.mdc
→ .cursor/rules/stack.mdc
→ .cursor/rules/architecture.mdc
Enter targets (comma-separated numbers or names, or "all"):Claude target rejection:
If the user requests target or , respond with:
claudeCLAUDE.mdThe Claude target is not supported in V1 — use /project-update to refresh CLAUDE.mdDo not write any files; re-present the menu or halt based on user choice.
如果用户通过CLI参数指定了目标(例如),则跳过交互式菜单,直接使用该目标进入步骤3。
/config-export copilot否则,展示目标选择菜单:
可用导出目标:
1. copilot → .github/copilot-instructions.md
2. gemini → GEMINI.md
3. cursor → .cursor/rules/conventions.mdc
→ .cursor/rules/stack.mdc
→ .cursor/rules/architecture.mdc
请输入目标(以逗号分隔的数字或名称,或输入"all"选择全部):拒绝Claude目标:
如果用户请求或作为目标,回复:
claudeCLAUDE.mdV1版本不支持Claude目标 — 请使用/project-update来刷新CLAUDE.md不写入任何文件;根据用户选择重新展示菜单或终止流程。
Step 3 — Dry-run generation and confirmation
步骤3 — 预演生成与确认
For each selected target, apply the corresponding transformation prompt (see sub-sections below). Then:
- Display the full generated content for each file and its destination path.
- If a target output file already exists at its canonical path, emit a warning before the confirmation prompt:
WARNING: Overwriting existing file: <path> - Prompt the user:
Default is N.
Write these files? [y/N] - If the user responds with anything other than , exit cleanly:
yNo files are written.Export cancelled — no files written - If the user responds , proceed to Step 4.
y
These transformation prompts are self-instructions executed by the agent using its own in-context LLM reasoning. No external API call, subprocess, or tool invocation is required to apply them — the agent reads the prompt and generates the output directly.
对于每个选中的目标,应用对应的转换提示(见下方子章节)。然后:
- 展示每个文件的完整生成内容及其目标路径。
- 如果目标输出文件已存在于其标准路径中,在确认提示之前发出警告:
警告:将覆盖现有文件:<路径> - 提示用户:
默认选项为N。
是否写入这些文件?[y/N] - 如果用户回复不是,则干净退出:
y不写入任何文件。导出已取消 — 未写入任何文件 - 如果用户回复,进入步骤4。
y
这些转换提示是Agent使用自身上下文LLM推理执行的自指令。应用这些提示无需调用外部API、子进程或工具 — Agent直接读取提示并生成输出。
Shared STRIP Preamble
通用剥离规则(Shared STRIP Preamble)
The following items MUST be stripped from ALL target outputs. Each transformation prompt below references this block — apply it in addition to any target-specific delta listed in that prompt.
- All slash commands used as executable triggers (any pattern that is a Claude Code meta-tool or SDD phase command)
/<word> - Task tool references and sub-agent delegation patterns (,
"Task tool:","subagent_type:","Launch sub-agent")"Sub-agent launch pattern" - install.sh and sync.sh references
- Claude Code-specific identity statements ("I am an expert development assistant…")
- The section of
## Skills Registry(lines beginning withCLAUDE.mdor~/.claude/skills/).claude/skills/ - Any section whose content is enclosed between and
<!-- [auto-updated]comment markers in<!-- [/auto-updated] -->filesai-context/
以下内容必须从所有目标输出中剥离。下方每个转换提示都会引用此规则块 — 除了目标专属的增量规则外,还需应用此通用规则。
- 所有用作可执行触发词的斜杠命令(任何属于Claude Code元工具或SDD阶段命令的模式)
/<单词> - 任务工具引用和子Agent委托模式(、
"Task tool:"、"subagent_type:"、"Launch sub-agent")"Sub-agent launch pattern" - install.sh和sync.sh的引用
- Claude Code专属的身份声明("我是专业开发助手…")
- 中的
CLAUDE.md章节(以## Skills Registry或~/.claude/skills/开头的行).claude/skills/ - 文件中位于
ai-context/和<!-- [auto-updated]注释标记之间的任何章节内容<!-- [/auto-updated] -->
Copilot transformation prompt
Copilot转换提示
Apply the following prompt to the source bundle to generate :
.github/copilot-instructions.mdYou are transforming a Claude Code project configuration into a GitHub Copilot instruction file.
Source bundle: CLAUDE.md + any available ai-context/ files provided above.
STRIP:
Apply the Shared STRIP Preamble above, then additionally strip:
- Plan Mode rules section (Claude Code-specific)
ADAPT — do NOT strip; rewrite for Copilot:
-
SDD phase DAG and workflow → Convert to asection written in declarative prose:
## SDD Development Workflow- Describe each phase (explore, propose, spec, design, tasks, apply, verify, archive) and its artifacts
- Include the artifact types (proposal, spec, design, tasks, verify-report, archive-report) and explain they are persisted to engram
- Do NOT include any slash command syntax — describe the phases as steps the developer initiates
-
SDD available commands table → Replace with asection containing Copilot behavioral instructions:
## Active SDD Coaching InstructionsWhen a developer mentions implementing a new feature, change, or fix: - Proactively ask: "Would you like to follow the SDD workflow for this change?" - If yes, guide them step by step: propose → (spec + design in parallel) → tasks → apply → verify → archive - Before starting apply, confirm that proposal, design, and tasks artifacts exist in the project's engram - Remind the developer to run verify after implementation and archive once confirmedAdapt the phrasing to be Copilot-idiomatic (imperative instructions telling Copilot how to behave). -
Project memory layer (ai-context/) → Retain the table and description verbatim; it applies directly to projects using Copilot too.
RETAIN and adapt:
- Tech stack (language, framework, key tools, versions)
- Coding conventions (naming, style, patterns) — rephrase as direct instructions to the AI assistant in imperative voice
- Architecture decisions and rationale
- Known issues and gotchas relevant to a developer working in the project
- Key working principles (clean code, no over-engineering, tests as first-class citizens, etc.)
- SDD artifact types and engram topic key patterns
FORMAT:
- Single flat Markdown file
- UTF-8, no BOM
- H2 sections (no YAML frontmatter)
- Start with a top-level heading:
# Project Instructions - Required H2 sections in this order:
- (if stack data available)
## Tech Stack - (if architecture data available)
## Architecture ## Conventions- ← always present, even in bootstrap mode
## SDD Development Workflow - ← always present
## Active SDD Coaching Instructions ## Working Principles- (if known-issues.md available)
## Known Issues - (only if any source file was absent)
## Source Notes
- Begin with the generated-file banner (verbatim, before the H1):
Replace
<!-- GENERATED BY config-export — DO NOT EDIT MANUALLY --> <!-- Source: CLAUDE.md + ai-context/ | Generated: YYYY-MM-DD --> <!-- Re-generate: run /config-export in your Claude Code session -->with today's date.YYYY-MM-DD - In bootstrap mode (no project CLAUDE.md), the and
## SDD Development Workflowsections MUST still be fully generated from the global SDD methodology; all project-specific sections are omitted and noted under## Active SDD Coaching Instructions.## Source Notes - Output path:
.github/copilot-instructions.md
对源包应用以下提示以生成:
.github/copilot-instructions.md你正在将Claude Code项目配置转换为GitHub Copilot指令文件。
源包: CLAUDE.md + 上方提供的所有可用ai-context/文件。
剥离规则:
先应用上述通用剥离规则,然后额外剥离:
- 计划模式规则章节(Claude Code专属)
适配规则 — 不要剥离;为Copilot重写:
-
SDD阶段DAG与工作流 → 转换为采用声明式 prose 编写的章节:
## SDD开发工作流- 描述每个阶段(探索、提议、规格、设计、任务、实施、验证、归档)及其产物
- 包含产物类型(提议、规格、设计、任务、验证报告、归档报告)并说明它们会被持久化到engram
- 不要包含任何斜杠命令语法 — 将阶段描述为开发者发起的步骤
-
SDD可用命令表 → 替换为包含Copilot行为指令的章节:
## 主动SDD指导指令当开发者提及要实现新功能、变更或修复时: - 主动询问:"是否要为此次变更遵循SDD工作流?" - 如果是,逐步引导他们:提议 → (规格 + 设计并行)→ 任务 → 实施 → 验证 → 归档 - 在开始实施前,确认项目的engram中已存在提议、设计和任务产物 - 提醒开发者在实施后运行验证,并在确认完成后进行归档调整措辞以符合Copilot的惯用风格(使用 imperative 指令告知Copilot如何表现)。
保留并适配:
- 技术栈(语言、框架、关键工具、版本)
- 编码约定(命名、风格、模式) — 改写为对AI助手的直接imperative指令
- 架构决策与理由
- 与项目开发者相关的已知问题与注意事项
- 核心工作原则(整洁代码、不过度设计、测试优先等)
- SDD产物类型和engram主题键模式
格式要求:
- 单个扁平化Markdown文件
- UTF-8编码,无BOM
- 使用H2章节(无YAML前置元数据)
- 以顶级标题开头:
# 项目指令 - 按以下顺序包含必填H2章节:
- (如果有栈数据可用)
## 技术栈 - (如果有架构数据可用)
## 架构 ## 约定- ← 始终存在,即使在引导模式下
## SDD开发工作流 - ← 始终存在
## 主动SDD指导指令 ## 工作原则- (如果有known-issues.md可用)
## 已知问题 - (仅当有源文件缺失时)
## 源文件说明
- 在H1标题前开头添加生成文件横幅(原文保留):
将
<!-- GENERATED BY config-export — DO NOT EDIT MANUALLY --> <!-- Source: CLAUDE.md + ai-context/ | Generated: YYYY-MM-DD --> <!-- Re-generate: run /config-export in your Claude Code session -->替换为当前日期。YYYY-MM-DD - 在引导模式(无项目CLAUDE.md)下,和
## SDD开发工作流章节仍必须完全从全局SDD方法生成;所有项目专属章节需省略并在## 主动SDD指导指令中注明。## 源文件说明 - 输出路径:
.github/copilot-instructions.md
Gemini transformation prompt
Gemini转换提示
Apply the following prompt to the source bundle to generate :
GEMINI.mdYou are transforming a Claude Code project configuration into a Google Gemini instruction file (GEMINI.md).
Source bundle: CLAUDE.md + any available ai-context/ files provided above.
STRIP:
Apply the Shared STRIP Preamble above, then additionally strip:
- SDD phase DAG diagram
- SDD artifact storage details specific to Claude Code
ADAPT (do not strip wholesale):
- SDD command tables: remove the command table verbatim; you MAY include an adapted prose paragraph describing a structured development workflow if it adds value for Gemini users — but no slash commands
- Claude-specific section headers (e.g., "How I Execute Commands", "SDD Orchestrator — Delegation Pattern"): rename to Gemini equivalents or remove if the content has no value outside Claude Code
RETAIN:
- Tech stack, coding conventions, architecture decisions, known issues
- Working principles and development philosophy
- Project memory layer description (ai-context/ structure)
FORMAT:
- Single Markdown file at project root
- UTF-8, no BOM
- Structure similar to CLAUDE.md (not flat — preserve H2/H3 hierarchy where content warrants it)
- Start with a top-level heading (e.g., )
# Gemini — Project Configuration - Begin with the generated-file banner (verbatim, before the H1):
Replace
<!-- GENERATED BY config-export — DO NOT EDIT MANUALLY --> <!-- Source: CLAUDE.md + ai-context/ | Generated: YYYY-MM-DD --> <!-- Re-generate: run /config-export in your Claude Code session -->with today's date.YYYY-MM-DD - Output path:
GEMINI.md
对源包应用以下提示以生成:
GEMINI.md你正在将Claude Code项目配置转换为Google Gemini指令文件(GEMINI.md)。
源包: CLAUDE.md + 上方提供的所有可用ai-context/文件。
剥离规则:
先应用上述通用剥离规则,然后额外剥离:
- SDD阶段DAG图
- 专属于Claude Code的SDD产物存储细节
适配规则(不要完全剥离):
- SDD命令表:直接移除命令表;如果对Gemini用户有价值,可添加一段适配后的prose段落描述结构化开发工作流 — 但不要包含斜杠命令
- Claude专属章节标题(例如"我如何执行命令"、"SDD编排器 — 委托模式"):重命名为Gemini等效标题,或如果内容在Claude Code之外无价值则移除
保留:
- 技术栈、编码约定、架构决策、已知问题
- 工作原则与开发理念
- 项目记忆层描述(ai-context/结构)
格式要求:
- 单个Markdown文件,位于项目根目录
- UTF-8编码,无BOM
- 结构与CLAUDE.md类似(非扁平化 — 在内容需要时保留H2/H3层级)
- 以顶级标题开头(例如)
# Gemini — 项目配置 - 在H1标题前开头添加生成文件横幅(原文保留):
将
<!-- GENERATED BY config-export — DO NOT EDIT MANUALLY --> <!-- Source: CLAUDE.md + ai-context/ | Generated: YYYY-MM-DD --> <!-- Re-generate: run /config-export in your Claude Code session -->替换为当前日期。YYYY-MM-DD - 输出路径:
GEMINI.md
Cursor transformation prompt
Cursor转换提示
Apply the following prompt to the source bundle to generate files:
.cursor/rules/*.mdcYou are transforming a Claude Code project configuration into Cursor MDC rule files.
Source bundle: CLAUDE.md + any available ai-context/ files provided above.
STRIP the following from all output files:
Apply the Shared STRIP Preamble above, then additionally strip:
- SDD phase DAG diagram
- SDD artifact storage details specific to Claude Code
OUTPUT STRUCTURE — split into exactly three domain files:
- — coding rules, naming conventions, style guidelines, error handling patterns
conventions.mdc - — tech stack, language versions, key frameworks and tools, package manager
stack.mdc - — architecture decisions, system design patterns, data flow, inter-component contracts
architecture.mdc
If source material is insufficient to produce meaningful content for a domain (e.g., no architecture.md and no architecture content in CLAUDE.md), produce a minimal file with the frontmatter and a one-line note rather than omitting the file.
MDC FRONTMATTER CONTRACT — every file MUST have:
yaml
---
description: "[one-line description of this rules domain]"
globs: "[glob pattern or empty string]"
alwaysApply: [true|false]
---Domain defaults:
| File | | |
|---|---|---|
| | |
| | |
| | |
CRITICAL — globs field: Use when no meaningful file-pattern can be inferred. NEVER guess at glob patterns. The field MUST be a string (not YAML null).
""globsFORMAT per file:
- UTF-8, no BOM
- YAML frontmatter block first (between delimiters)
--- - Generated-file banner immediately after the closing of the frontmatter:
---Replace<!-- GENERATED BY config-export — DO NOT EDIT MANUALLY --> <!-- Source: CLAUDE.md + ai-context/ | Generated: YYYY-MM-DD --> <!-- Re-generate: run /config-export in your Claude Code session -->with today's date.YYYY-MM-DD - File name: lowercase slug with extension (e.g.,
.mdc)conventions.mdc - If source material was only CLAUDE.md (no ai-context/), set to note it: e.g.,
description"Generated from CLAUDE.md — ai-context/ not found" - Output paths: ,
.cursor/rules/conventions.mdc,.cursor/rules/stack.mdc.cursor/rules/architecture.mdc
对源包应用以下提示以生成文件:
.cursor/rules/*.mdc你正在将Claude Code项目配置转换为Cursor MDC规则文件。
源包: CLAUDE.md + 上方提供的所有可用ai-context/文件。
从所有输出文件中剥离以下内容:
先应用上述通用剥离规则,然后额外剥离:
- SDD阶段DAG图
- 专属于Claude Code的SDD产物存储细节
输出结构 — 拆分为恰好三个领域文件:
- — 编码规则、命名约定、风格指南、错误处理模式
conventions.mdc - — 技术栈、语言版本、核心框架与工具、包管理器
stack.mdc - — 架构决策、系统设计模式、数据流、组件间契约
architecture.mdc
如果源材料不足以生成某个领域的有意义内容(例如无architecture.md且CLAUDE.md中无架构内容),则生成一个包含前置元数据和单行说明的最小化文件,不要省略该文件。
MDC前置元数据约定 — 每个文件必须包含:
yaml
---
description: "[该规则领域的单行描述]"
globs: "[glob模式或空字符串]"
alwaysApply: [true|false]
---领域默认值:
| 文件 | | |
|---|---|---|
| | |
| | |
| | |
关键要求 — globs字段: 当无法推断出有意义的文件模式时使用。绝不猜测glob模式。字段必须是字符串(不能是YAML null)。
""globs单个文件格式要求:
- UTF-8编码,无BOM
- 开头为YAML前置元数据块(位于分隔符之间)
--- - 前置元数据的闭合之后立即添加生成文件横幅:
---将<!-- GENERATED BY config-export — DO NOT EDIT MANUALLY --> <!-- Source: CLAUDE.md + ai-context/ | Generated: YYYY-MM-DD --> <!-- Re-generate: run /config-export in your Claude Code session -->替换为当前日期。YYYY-MM-DD - 文件名:小写短横线格式,带扩展名(例如
.mdc)conventions.mdc - 如果源材料仅为CLAUDE.md(无ai-context/),将设置为说明:例如
description"Generated from CLAUDE.md — ai-context/ not found" - 输出路径:、
.cursor/rules/conventions.mdc、.cursor/rules/stack.mdc.cursor/rules/architecture.mdc
Step 4 — File writing
步骤4 — 文件写入
For each confirmed target:
-
Create required directories silently if they do not exist:
- Copilot:
.github/ - Cursor:
.cursor/rules/ - Gemini: no directory required (file at project root)
- Do NOT emit any output for directory creation unless it fails.
- Copilot:
-
Write the generated file to its canonical path, prepending the generated-file banner:
<!-- GENERATED BY config-export — DO NOT EDIT MANUALLY --> <!-- Source: CLAUDE.md + ai-context/ | Generated: YYYY-MM-DD --> <!-- Re-generate: run /config-export in your Claude Code session -->Replacewith today's date.YYYY-MM-DD -
Overwrite any existing file at the canonical path — this is idempotent behavior. No error is raised when overwriting.
对于每个已确认的目标:
-
若所需目录不存在则静默创建:
- Copilot:
.github/ - Cursor:
.cursor/rules/ - Gemini:无需创建目录(文件位于项目根目录)
- 除非创建失败,否则不要输出任何目录创建相关信息。
- Copilot:
-
将生成的文件写入其标准路径,开头添加生成文件横幅:
<!-- GENERATED BY config-export — DO NOT EDIT MANUALLY --> <!-- Source: CLAUDE.md + ai-context/ | Generated: YYYY-MM-DD --> <!-- Re-generate: run /config-export in your Claude Code session -->将替换为当前日期。YYYY-MM-DD -
覆盖标准路径下的任何现有文件 — 这是幂等行为。覆盖时不报错。
Step 5 — Summary
步骤5 — 总结
After all confirmed files have been written, print a summary table:
Export complete — files written:
File Status
────────────────────────────────── ───────
.github/copilot-instructions.md written
GEMINI.md written
.cursor/rules/conventions.mdc written
.cursor/rules/stack.mdc written
.cursor/rules/architecture.mdc written(Only include rows for targets that were written in this run.)
Then append the snapshot reminder:
Exported files are snapshots. Re-run /config-export after significant changes to CLAUDE.md or ai-context/所有确认文件写入完成后,打印总结表格:
导出完成 — 已写入文件:
文件路径 状态
────────────────────────────────── ───────
.github/copilot-instructions.md 已写入
GEMINI.md 已写入
.cursor/rules/conventions.mdc 已写入
.cursor/rules/stack.mdc 已写入
.cursor/rules/architecture.mdc 已写入(仅包含此次运行中已写入的目标对应的行。)
然后添加快照提醒:
导出的文件为快照版本。当CLAUDE.md或ai-context/发生重大变更后,请重新运行/config-exportRules
规则
- If no is found in CWD, the skill MUST present the two-path menu (project-setup or bootstrap) before any file write; the hard ERROR path is NOT the default
CLAUDE.md - Bootstrap mode (option 2) MUST produce a valid Copilot instructions file containing the full SDD workflow and coaching instructions even when no project CLAUDE.md exists
- The Copilot transformation MUST NOT strip the SDD phase workflow or artifact paths — it MUST adapt them to prose and Copilot coaching instructions
- The and
## SDD Development Workflowsections MUST always be present in the Copilot output (whether from project mode or bootstrap mode)## Active SDD Coaching Instructions - Dry-run preview MUST precede any file write — there is no flag to skip dry-run
- Overwrite warnings MUST appear in the dry-run step (before user confirmation), not after
- The skill MUST NOT modify or any
CLAUDE.mdfile — read-only with respect to all source filesai-context/ - Directory creation (,
.github/) MUST be silent — no output for directory creation unless it fails.cursor/rules/ - The Claude target () is NOT supported in V1 — respond with the defined rejection message; do not write any files for that target
CLAUDE.md - All generated files MUST be UTF-8, no BOM
- Each Cursor file MUST have valid YAML frontmatter with
.mdc,description, andglobsfieldsalwaysApply - Cursor file names MUST be valid slugs: lowercase letters, digits, and hyphens only, with the
.mdcextension.mdc - Copilot output MUST be a single file at — no splitting
.github/copilot-instructions.md - Gemini output MUST be a single file at at the project root — no subdirectories
GEMINI.md - The field in Cursor MDC files MUST use
globswhen no meaningful pattern can be inferred — never guess"" - All content in generated files MUST be free of Claude Code-specific execution syntax: no Task tool invocations, no sub-agent patterns, no file paths
~/.claude/skills/ - Copilot MUST adapt SDD content (workflow, phases, artifacts) — stripping rules apply only to execution-layer Claude Code syntax; SDD methodology is RETAINED and adapted for all targets
- No target receives a verbatim copy of
CLAUDE.md
- 如果当前工作目录中未找到,该Skill必须在写入任何文件之前展示双选项菜单(project-setup或引导模式);默认不是直接报错
CLAUDE.md - 引导模式(选项2)必须生成有效的Copilot指令文件,包含完整的SDD工作流和指导指令,即使不存在项目CLAUDE.md
- Copilot转换不得剥离SDD阶段工作流或产物路径 — 必须将其适配为prose和Copilot指导指令
- Copilot输出中必须始终包含和
## SDD开发工作流章节(无论是项目模式还是引导模式)## 主动SDD指导指令 - 写入任何文件之前必须进行预演预览 — 没有跳过预演的标志
- 覆盖警告必须出现在预演步骤中(用户确认之前),而不是之后
- 该Skill不得修改或任何
CLAUDE.md文件 — 对所有源文件仅可读ai-context/ - 目录创建(、
.github/)必须静默执行 — 除非创建失败,否则不要输出任何目录创建相关信息.cursor/rules/ - V1版本不支持Claude目标() — 回复定义好的拒绝消息;不为该目标写入任何文件
CLAUDE.md - 所有生成的文件必须为UTF-8编码,无BOM
- 每个Cursor 文件必须包含有效的YAML前置元数据,带有
.mdc、description和globs字段alwaysApply - Cursor 文件名必须是有效的短横线格式:仅包含小写字母、数字和短横线,带
.mdc扩展名.mdc - Copilot输出必须是位于的单个文件 — 不得拆分
.github/copilot-instructions.md - Gemini输出必须是位于项目根目录的单个文件 — 不得放在子目录中
GEMINI.md - 当无法推断出有意义的模式时,Cursor MDC文件中的字段必须使用
globs— 绝不猜测"" - 生成文件中的所有内容必须不包含Claude Code专属的执行语法:无任务工具调用、无子Agent模式、无文件路径
~/.claude/skills/ - Copilot必须适配SDD内容(工作流、阶段、产物) — 剥离规则仅适用于执行层的Claude Code语法;SDD方法必须保留并适配给所有目标
- 任何目标都不会直接获得的逐字副本 ",
CLAUDE.md