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通过

sync-to-copilotsync TO GitHub Copilot 搜索

Agent Skill

sync-to-copilot 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

261

周安装

11

GitHub Stars

6

下载量

92
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:sync-to-copilot(sync TO GitHub Copilot 搜索)
来源仓库:https://github.com/duc01226/easyplatform
仓库路径:skills/sync-to-copilot
安装命令:
npx skills add https://github.com/duc01226/easyplatform --skill sync-to-copilot
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/duc01226/easyplatform --skill sync-to-copilot

简介

用于在 Codex、Claude、Cursor、Gemini CLI 中查找和筛选相关信息。

  • 支持根据关键词、任务场景或来源线索快速定位候选结果。
  • 可结合原始 README 和仓库内容进一步核验具体用法。
  • 安装前建议确认权限范围和维护状态,避免触发不必要操作。
  • 安装方式:通过 GitHub 仓库使用 npx 命令添加。

SKILL.md

Skill: sync-to-copilot

Sync Claude Code knowledge to GitHub Copilot instructions. Two-tier output: project-specific + common protocol.


Quick Summary

Purpose: Keep Copilot instructions in sync with Claude Code workflows, dev rules, and project-reference docs.

Architecture (Two-Tier):

  1. .github/copilot-instructions.mdProject-specific (always loaded by Copilot)

- TL;DR golden rules, decision table - Project-reference docs index with READ prompts - Key file locations, dev commands

  1. .github/instructions/common-protocol.instructions.mdGeneric protocols (applyTo: **/*)

- Prompt protocol, before-editing rules - Workflow catalog (from workflows.json) - Workflow execution protocol - Development rules (from development-rules.md)

  1. .github/instructions/{group}.instructions.mdPer-group (applyTo: file patterns)

- Enhanced summaries per doc with READ prompts - Groups: backend, frontend, styling, testing, project

What gets synced:

  • Workflow catalog (from workflows.json) — SCRIPT-GENERATED
  • Dev rules (from development-rules.md) — SCRIPT-GENERATED
  • Project-reference summaries (from copilot-registry.json) — SCRIPT-GENERATED
  • Enriched section headings and key patterns — AI-GENERATED (this skill)

Usage:

/sync-to-copilot

Script: .claude/scripts/sync-copilot-workflows.cjs


Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

When to Use This Skill

Trigger this skill when:

  • Workflows added/modified — After editing .claude/workflows.json
  • Development rules changed — After editing .claude/docs/development-rules.md
  • Project-reference docs updated — After modifying files in docs/project-reference/
  • Registry entries changed — After editing docs/copilot-registry.json
  • Regular maintenance — Quarterly sync to ensure Copilot parity
  • Copilot setup — First-time Copilot instructions creation

Workflow

Phase 1: Script Generation (Automated)

node .claude/scripts/sync-copilot-workflows.cjs

This generates:

  • .github/copilot-instructions.md — project-specific with registry summaries
  • .github/instructions/common-protocol.instructions.md — generic protocols
  • .github/instructions/{group}.instructions.md — per-group instruction files
  • Removes old .github/common.copilot-instructions.md if it exists

Phase 2: AI Enrichment (This Skill)

After the script runs, the AI MUST ATTENTION enrich the generated instruction files:

  1. For each per-group instruction file in .github/instructions/:

- Read the corresponding docs/project-reference/*.md source file - Extract the ## section headings from the source file - Add a "Key Sections" list under each doc entry showing the headings - Keep it concise — headings only, no content duplication

  1. For .github/copilot-instructions.md:

- Verify the TL;DR golden rules in docs/copilot-registry.jsonprojectInstructions.goldenRules still match CLAUDE.md - Check if any new project-reference files exist but are missing from docs/copilot-registry.json - If missing entries found, add them to the registry and re-run the script

  1. For docs/copilot-registry.json:

- Verify each summary field accurately describes the current file content - Update stale summaries based on actual file content - Add entries for any new docs/project-reference/*.md files

Phase 3: Verification

Check that:

  • .github/copilot-instructions.md contains project-specific content
  • .github/instructions/common-protocol.instructions.md contains protocols + workflow catalog
  • Per-group instruction files contain READ prompts
  • No old common.copilot-instructions.md file remains
  • Workflow count matches workflows.json
  • All project-reference files are represented in the registry

AI Enrichment Protocol

When enriching per-group instruction files, follow this pattern for each doc entry:

## [Doc Title](relative/path)

**Summary:** One-line summary from registry.

**Key Sections:**

- Section 1 Name
- Section 2 Name
- Section 3 Name
- ...

> **READ** `docs/project-reference/filename.md` when: trigger description

Rules:

  • Extract ONLY ## level headings from the source file (not ### or deeper)
  • Do NOT copy content — just list heading names
  • Keep the READ prompt from the registry whenToRead field
  • If a file is very large (>30KB), note the file size: (~59KB - read relevant sections)

Output Files

FileTypeContent
.github/copilot-instructions.mdProject-specificTL;DR + project-reference index + READ prompts
.github/instructions/common-protocol.instructions.mdGeneric (applyTo: **/*)Prompt protocol + workflow catalog + dev rules
.github/instructions/backend-csharp.instructions.mdBackend (applyTo: **/*.cs)Backend doc summaries + READ prompts
.github/instructions/frontend-angular.instructions.mdFrontend (applyTo: **/*.ts,**/*.html)Frontend doc summaries + READ prompts
.github/instructions/styling-scss.instructions.mdStyling (applyTo: **/*.scss,**/*.css)Styling doc summaries + READ prompts
.github/instructions/testing.instructions.mdTesting (applyTo: **/*Test*/**,...)Testing doc summaries + READ prompts
.github/instructions/project-reference.instructions.mdCross-cutting (applyTo: **/*)General project doc summaries + READ prompts

Copilot Limitations

Copilot can't enforce protocols like Claude Code hooks:

  • No blocking operations (edit-enforcement, search-before-code)
  • Relies on LLM instruction-following (not guaranteed)
  • Protocols are advisory, not enforced
  • No runtime context injection — all context must be in instruction files

Benefits:

  • Consistent guidance across AI tools
  • Same workflow detection for Claude and Copilot users
  • READ prompts enable on-demand context loading
  • Automated sync reduces configuration drift

Troubleshooting

Issue: "workflows.json not found"

Solution: Ensure you're running from project root

Issue: Missing project-reference files in registry

Solution: Add entries to docs/copilot-registry.json, then re-run script

Issue: Stale summaries

Solution: Run this skill — AI will read files and update summaries


Related Skills

  • /ai-dev-tools-sync — Broader Claude/Copilot sync (skills, prompts, agents)
  • /sync-copilot-workflows — Workflow-only sync (subset of this skill)

References

  • Script: .claude/scripts/sync-copilot-workflows.cjs
  • Registry: docs/copilot-registry.json
  • Sources: .claude/workflows.json, .claude/docs/development-rules.md
  • Main output: .github/copilot-instructions.md
  • Instruction files: .github/instructions/*.instructions.md

Closing Reminders

  • IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting
  • IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code
  • IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act)
  • IMPORTANT MUST ATTENTION add a final review todo task to verify work quality

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

33.3%
按下载量换算31

Claude

31.83%
按下载量换算29

Cursor

19.14%
按下载量换算18

Gemini CLI

9.83%
按下载量换算9

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