Agent skill

Sync Agent

by thun-res in thun-res/vlink

基于 VLink 当前代码、doc、目录、工具和 GitHub 工作流事实,审计并同步 AGENTS.md、AI-POLICY.md、Copilot 指令、.agents 路由/索引/语言分册/ CI 说明、skill frontmatter、agents/openai.yaml 与 README 清单.用户 要求"同步 Agent 文件"、"根据代码更新 .agents"、"检查…

Apache-2.0Auto-check passedAgent Workflows

Install Sync Agent

skills CLI
$ npx skills add thun-res/vlink --skill sync-agent -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install thun-res/vlink sync-agent --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/thun-res/vlink.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/sync-agent .claude/skills/sync-agent && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
sync-agent
GitHub stars
115
Token cost
~893 tokens
SKILL.md length
189 words
Files
2
Skills in repo
16
Repo updated
First seen
Licence
Apache-2.0

At a glance

基于 VLink 当前代码、doc、目录、工具和 GitHub 工作流事实,审计并同步 AGENTS.md、AI-POLICY.md、Copilot 指令、.agents 路由/索引/语言分册/ CI 说明、skill frontmatter、agents/openai.yaml 与 README 清单.用户 要求"同步 Agent 文件"、"根据代码更新 .agents"、"检查…

  • Works in 5 steps: 授权与边界 → 建立事实基线 → 同步各派生面 → …
  • Tasks that involve Agent instruction files
  • SKILL.md covers 1. 授权与边界, 2. 建立事实基线, 3. 同步各派生面 and 4. 最小修改, plus 1 more section
  • Calls bash and git

What it does

Sync Agent is an agent skill from thun-res/vlink. 基于 VLink 当前代码、doc、目录、工具和 GitHub 工作流事实,审计并同步 AGENTS.md、AI-POLICY.md、Copilot 指令、.agents 路由/索引/语言分册/ CI 说明、skill frontmatter、agents/openai.yaml 与 README 清单.用户 要求"同步 Agent 文件"、"根据代码更新 .agents"、"检查 AGENTS.md 和 skills"、"Agent 规则跟仓库对齐"时使用;产品与公开 API 的完整同步仍 使用 /sync-review.

Its SKILL.md is about 890 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Agent Workflows, covering Agent instruction files and Technical documentation. It works with OpenAI and GitHub. The repository describes itself as: VLink is a high-performance C++ communication middleware for autonomous driving and embodied intelligence, positioned as a full-scenario alternative to ROS 2. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Agent instruction files
  • Tasks that involve Technical documentation

Example prompts

  • “同步 Agent 文件”
  • “根据代码更新 .agents”
  • “检查 AGENTS.md 和 skills”
  • “/sync-agent”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. 授权与边界
  2. 建立事实基线
  3. 同步各派生面
  4. 最小修改
  5. 验证

What it can do on your machine

Read from SKILL.md and the folder at commit 1793889. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • bash
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sync Agent loads about 893 tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 189 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
When it runs · the whole SKILL.md, loaded when a task matches
~893

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from thun-res/vlink at commit 1793889, republished under its Apache-2.0 licence (© thun-res). 189 words, ~893 tokens.

Download SKILL.mdSave it as .claude/skills/sync-agent/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
sync-agent
description
基于 VLink 当前代码、doc、目录、工具和 GitHub 工作流事实,审计并同步 AGENTS.md、AI-POLICY.md、Copilot 指令、.agents 路由/索引/语言分册/ CI 说明、skill frontmatter、agents/openai.yaml 与 README 清单.用户 要求"同步 Agent 文件"、"根据代码更新 .agents"、"检查 AGENTS.md 和 skills"、"Agent 规则跟仓库对齐"时使用;产品与公开 API 的完整同步仍 使用 /sync-review.

同步 Agent 体系

目标是让 Agent 规则和路由准确指向当前仓库,不在 Agent 文件复制产品知识。 代码定义实现事实,doc/00–15 定义产品与架构语义;Agent 文件只维护 强制规则、工作流程、目录职责和渐进式披露入口。

1. 授权与边界

  • 用户只要求检查、分析或报告时保持只读,不得修改或生成报告文件。
  • 用户明确要求"同步"、"更新"或"修复"时,只修改 AGENTS.md、 AI-POLICY.md、.github/copilot-instructions.md、.agents/** 及 直接负责 Agent 校验的 CI/工具文件。
  • 不修改产品代码、公开 API、doc/、README、测试或构建配置来迁就 Agent 描述;发现这些事实侧本身冲突时报告并交给对应任务。
  • 公开 API、功能入口或文档结构变化必须同批使用 /sync-review;本 skill 只处理其 Agent 派生面,不得替代产品同步审计。
  • 未经维护者明确命令不得升级版本,也不得提交、push、创建 PR、安装 skill、构建、运行测试或执行无关项目脚本。
  • 保留维护者和其他 Agent 的工作树改动;写前重读目标文件、git status 和最新 diff,不得覆盖、回退、stash 或清理。

2. 建立事实基线

先读根 AGENTS.md、AI-POLICY.md、.agents/README.md、 REPO-REFERENCE.md、FEATURE-INDEX.md 与 .github/copilot-instructions.md,再从当前仓库反向验证:

  • 顶层目录、include/vlink/、src/、modules/、cli/、绑定、示例 和测试的实际职责。
  • doc/00–15 的现有文件、小节号、标题和功能归属。
  • CMakeLists.txt、cmake/、tools/、.github/workflows/ 与 .github/scripts/ 的真实入口、选项和触发关系。
  • .agents/skills/*/SKILL.md、agents/openai.yaml、引用文件及 .agents/README.md 的完整 skill 集合。
  • 当前分支、HEAD、暂存区、工作树和未跟踪文件;增量任务还要检查指定 base 到 HEAD 的变化。

代码签名、目录和控制流以代码为事实;产品定位、能力边界和架构意图以 doc/ 为事实。两者冲突时不得擅自选择一侧,应报告待确认项。

3. 同步各派生面

3.1 根规则

AGENTS.md 只保留跨任务、稳定且不可协商的强制规则与路由指向。新增 规则必须有真实重复风险或维护者明确要求,不得塞入模块清单、API 说明、 命令示例或临时实现细节。检查编号、引用和分册职责是否连续一致。

3.2 路由与索引
  • .agents/README.md:任务到分册的路由、分册清单、skill 清单和安装 说明与实际文件一致。
  • REPO-REFERENCE.md:目录职责、文档章节、工程设施和相关仓库仍存在且 语义准确,不复制专题文档内容。
  • FEATURE-INDEX.md:每个功能的代码入口和 doc/ 小节真实存在;新增、 删除、改名或拆分功能后同步入口,但不在索引解释完整机制。
3.3 规则分册

语言、测试、文档、CI/PR 和 AI 政策只记录仓库特有约束。规则变更需核对 上位边界与引用方,避免在 AGENTS.md、分册和 skill 中重复维护或互相 冲突。无代码证据或维护者决策时不得把个人偏好写成强制规则。 .github/copilot-instructions.md 只保留指向根规则、当前任务分册和 GitHub 原生智能体边界的最小入口,不得复制产品知识或整套 Agent 规则。

3.4 Skills

对每个 .agents/skills/<name>/ 检查:

  • 目录名、frontmatter name 和触发型 description 一致。
  • SKILL.md 的授权边界、工具命令、引用路径和实际工作流有效。
  • agents/openai.yaml 的 display_name、short_description 与 default_prompt 匹配 skill,且 prompt 明确包含 $<name>。
  • .agents/README.md 有且仅有一条对应入口;新增 skill 不附带无用的 README、模板或资源目录。
  • 公开写入、发布、Issue、Discussion、PR、Release 和 CI dispatch 均有 明确授权与回读步骤,不得伪装身份、扩大权限或隐藏未执行验证。
3.5 Agent CI

.github/workflows/ci-agent-skills.yml 与校验脚本应覆盖 AGENTS.md、 AI-POLICY.md、.github/copilot-instructions.md、.agents/**、skill 安装入口、Issue/Discussion 回复授权契约及自身变化,权限保持 contents: read。 只校验结构、元数据、路由、关键授权/回读契约和占位符,不得自动发帖、 创建 Issue/Discussion、修改仓库设置或安装网络依赖。

4. 最小修改

先列出事实侧与过时派生面,再按依赖顺序修改:根规则 → 分册 → 路由/索引 → skill → CI 说明。只修当前证据支持的差异,不借同步任务重写整套规则、 重排无关内容或统一个人偏好。路径、标题和小节变化必须同时修复直接引用。

5. 验证

在用户授权范围内执行只读或 Agent 专用校验:

bash
bash -n tools/install_skills.sh
bash -n .github/scripts/test-validate-agent-skills.sh
bash -n .github/scripts/validate-agent-skills.sh
PYTHONPYCACHEPREFIX="$PWD/build-ai/sync-agent/__pycache__" \
    bash .github/scripts/test-validate-agent-skills.sh
PYTHONPYCACHEPREFIX="$PWD/build-ai/sync-agent/__pycache__" \
    bash .github/scripts/validate-agent-skills.sh
git diff --check

新增或修改 skill 时,再用 skill-creator 的 quick_validate.py 校验目标 目录,并为该 Python 调用设置同一任务专属 PYTHONPYCACHEPREFIX;修改 workflow 时优先运行已安装的 actionlint,缺失时不得擅自安装,改用现有 YAML 解析器检查语法并如实报告未执行项。

最终逐文件回读 diff,说明同步依据、修改范围、无需变化的派生面、未执行 验证和仍待维护者确认的冲突。确认没有修改版本、产品行为或外部状态。

© thun-res, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/sync-agent of thun-res/vlink.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 1793889

Compare with similar skills

Sync Agent next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sync Agent compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sync Agent this skillthun-res/vlink115—~893Automated safety check: PassApache-2.0
Workflow Creatornicepkg/ai-workflow285—~2.6kAutomated safety check: PassMIT
Create Simple Promptpnp/copilot-prompts891—~2.6kAutomated safety check: PassMIT
Create Skill Samplepnp/copilot-prompts891—~3.1kAutomated safety check: PassMIT
Export TemplateHurricaHjz/second-yourself113—~4.8kAutomated safety check: WarnMIT
Readme Blueprint Generatorgithub/awesome-copilot40k2 repos~729Automated safety check: PassMIT

Similar skills

  • Workflow Creator

    nicepkg/ai-workflow

    Create complete Claude Code workflow directories with curated skills.

    285 GitHub stars~2.6k tokensUpdated 8 mo ago
    Agent WorkflowsAuto-check passed
  • Create Simple Prompt

    pnp/copilot-prompts

    This skill should be used when the user asks to "create a new prompt sample", "add a new prompt sample", "scaffold a new prompt sample", "create a prompt contribution", "add a prompt", or needs to…

    891 GitHub stars~2.6k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Create Skill Sample

    pnp/copilot-prompts

    This skill should be used when the user asks to "create a new skill sample", "add a skill", "scaffold a new skill", "contribute a skill", "create a GitHub Copilot skill", "build a custom skill", or…

    891 GitHub stars~3.1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Export Template

    HurricaHjz/second-yourself

    Sync THIS LLM-Wiki framework with its public GitHub repo, ONE direction per run: --push (vault → repo) publishes your framework; --pull (repo → vault) updates your framework from a newer repo version.

    113 GitHub stars~4.8k tokensUpdated 6 days ago
    Knowledge ManagementAuto-check: warnings
  • Readme Blueprint Generator

    github/awesome-copilot

    Official

    Intelligent README.md generation prompt that analyzes project documentation structure and creates comprehensive repository documentation.

    40k GitHub starsUsed in 2 repos~729 tokens
    DevelopmentAuto-check passed
  • Readme Blueprint Generator

    appleweiping/WEIPING_WIKI

    Create, rewrite, or critique high-quality project README.md files.

    119 GitHub stars~880 tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

More from thun-res/vlink

All 16 skills in this repo
  • Issue

    thun-res/vlink

    调查 VLink 中可复现的缺陷、文档遗漏或功能建议,搜索 open/closed Issue 去重,按仓库模板用自然、具体、证据充分的简体中文草拟或创建 Issue, 可读取既有 Issue 上下文后草拟或发布单条回复.用户要求"提 issue"、 "创建 issue"、"检查是否已有 issue"、"回复 issue"、"评论 issue"、 "帮我回应…

    115 GitHub stars~753 tokensUpdated 7 days ago
    Auto-check passed
  • Asan

    thun-res/vlink

    以 AddressSanitizer(ENABLETESTSANITIZE=ON)构建并运行 vlink-test 单元测试,复现 CI 的 ASan 门禁。用户要求"跑 asan"、"内存检测测试"、 排查 ci-test 的 sanitize 失败时使用。

    115 GitHub stars~683 tokensUpdated 7 days ago
    Auto-check passed
  • Bench

    thun-res/vlink

    构建并运行 vlink-bench 性能基准(showcase/quick/full 预设),生成 HTML/JSON 报告。用户要求"跑 bench"、"性能测试"、对比后端吞吐/延迟、 验证性能回归时使用。

    115 GitHub stars~993 tokensUpdated 7 days ago
    Auto-check passed
  • Cicd

    thun-res/vlink

    用 gh CLI 触发/查看 GitHub CI/CD:手动 dispatch 工作流 (release/coverage/docker)、查看运行状态与失败日志、重跑失败 job.

    115 GitHub stars~856 tokensUpdated 7 days ago
    Auto-check passed
  • Clang Tidy

    thun-res/vlink

    对指定文件或全仓库运行 clang-tidy(WarningsAsErrors='')。用户要求 "跑 clang-tidy"、"tidy 检查某文件"、排查 CI tidy 门禁失败时使用。

    115 GitHub stars~712 tokensUpdated 7 days ago
    Auto-check passed
  • Commit

    thun-res/vlink

    提交前强制执行 VLink 的 format 与 check skill,再分析当前工作树的全部 staged、unstaged 与 untracked 改动,按模块、功能和依赖关系拆分为可独立 评审的 Conventional Commits,生成简洁且覆盖重要行为的英文 commit message 并逐组提交。用户要求“提交当前改动”、“按功能拆 commit”、 “自动写 commit…

    115 GitHub stars~931 tokensUpdated 7 days ago
    Auto-check passed

Works with

Questions about Sync Agent

What does Sync Agent do?

基于 VLink 当前代码、doc、目录、工具和 GitHub 工作流事实,审计并同步 AGENTS.md、AI-POLICY.md、Copilot 指令、.agents 路由/索引/语言分册/ CI 说明、skill frontmatter、agents/openai.yaml 与 README 清单.用户 要求"同步 Agent 文件"、"根据代码更新 .agents"、"检查…. Sync Agent is an agent skill from thun-res/vlink.md 和 skills"、"Agent 规则跟仓库对齐"时使用;产品与公开 API 的完整同步仍 使用 /sync-review.

When should I use Sync Agent?

Sync Agent fits situations like: tasks that involve Agent instruction files; tasks that involve Technical documentation.

How do I install Sync Agent in Claude Code?

Run `npx skills add thun-res/vlink --skill sync-agent -a claude-code`. Or copy the skill folder (.agents/skills/sync-agent in thun-res/vlink) into .claude/skills/sync-agent in your project. Claude Code loads it when a task matches its description.

How do I install Sync Agent in Codex?

Run `npx skills add thun-res/vlink --skill sync-agent -a codex`. Or copy the skill folder (.agents/skills/sync-agent in thun-res/vlink) into .agents/skills/sync-agent in your project. Codex loads it when a task matches its description.

Can I use Sync Agent in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add thun-res/vlink --skill sync-agent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sync-agent, .gemini/skills/sync-agent, .github/skills/sync-agent and .opencode/skills/sync-agent in your project.

What does Sync Agent need to run?

Going by SKILL.md and its folder, Sync Agent needs the command-line tools its instructions call (bash and git). Our summary lists: Python 3.

Does Sync Agent access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Sync Agent safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Sync Agent use?

Sync Agent is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sync Agent use?

About 893 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Sync Agent?

Skills that share tags, products or a category with Sync Agent: Workflow Creator (nicepkg/ai-workflow, 285 stars), Create Simple Prompt (pnp/copilot-prompts, 891 stars), Create Skill Sample (pnp/copilot-prompts, 891 stars) and Export Template (HurricaHjz/second-yourself, 113 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sync Agent?

thun-res (a GitHub user) maintains it in thun-res/vlink, which has 115 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on September 30, 2026.

Source: thun-res/vlink on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.