Agent skill

Engineering Communication Rules

by openJiuwen-ai in openJiuwen-ai/agent-core

Chinese-language rules for how an agent writes commit messages, PR descriptions, session journals, handoff issues and requests for help.

Apache-2.0Auto-check passedDevelopment

SKILL.md written in Chinese; this summary is our English description.

Install Engineering Communication Rules

skills CLI
$ npx skills add openJiuwen-ai/agent-core --skill communicate -a claude-code

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

GitHub CLI
$ gh skill install openJiuwen-ai/agent-core communicate --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/openJiuwen-ai/agent-core.git skills-src && mkdir -p .claude/skills && cp -r skills-src/openjiuwen/rsi/harness_rsi/auto_harness/skills/communicate .claude/skills/communicate && 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
communicate
GitHub stars
446
Token cost
~625 tokens
SKILL.md length
123 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
Apache-2.0

At a glance

Chinese-language rules for how an agent writes commit messages, PR descriptions, session journals, handoff issues and requests for help.

  • Works in 3 steps: 创建 issue 描述剩余工作 → 在 journal 中标注 接力 → issue 内容包含
  • Writing conventional commit messages for a Chinese-language team
  • SKILL.md covers Commit Message 规范, PR 描述模板, Journal 记录 and 跨 Session 接力, plus 2 more sections
  • Reaches gitcode.com

What it does

Written in Chinese, this skill sets how an agent communicates at the end of a task. Commit messages use conventional commits with the types feat, fix, refactor, perf, test, docs and chore; the subject stays within 50 characters in imperative mood, and the body explains why rather than what. Commit boundaries are decided elsewhere, by the implement and commit skills.

PR or MR descriptions follow the GitCode template from the git-commit-push skill, with kind labels bug, task, feature, refactor and clean_code. Each session ends with a journal entry, unfinished work is handed off through an issue noted in the journal, and the agent asks for help on uncertainty, out-of-scope changes, three or more repeated failures or security risks. Output is in Chinese with English technical terms and file:line references.

When your agent uses it

  • Writing conventional commit messages for a Chinese-language team
  • Filling in a GitCode merge request description
  • Closing a session with a journal entry
  • Handing unfinished work to the next session through an issue

Example prompts

  • “Write a conventional commit message for this refactor, in Chinese.”
  • “Draft the merge request description using the GitCode template.”
  • “Record this session's journal and open a handoff issue for the remaining work.”

Requirements

  • The git-commit-push skill, which holds the GitCode PR template

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. 创建 issue 描述剩余工作
  2. 在 journal 中标注 接力
  3. issue 内容包含

What it can do on your machine

Read from SKILL.md and the folder at commit 030187f. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • gitcode.com

    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

Engineering Communication Rules loads about 625 tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 123 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~15
When it runs · the whole SKILL.md, loaded when a task matches
~625

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 openJiuwen-ai/agent-core at commit 030187f, republished under its Apache-2.0 licence (© openJiuwen-ai). 123 words, ~625 tokens.

Download SKILL.mdSave it as .claude/skills/communicate/SKILL.md (or your agent's skills folder).
name
communicate
description
沟通规范 — 约束 commit message、PR、journal 和求助信息的表达方式
immutable
true
tools
bash_tool, experience_search

Communicate Skill

你是沟通阶段的 agent,负责撰写高质量的技术沟通内容。

Commit Message 规范

使用 conventional commits 格式:

<type>(<scope>): <subject>

<body>

<footer>
type用途
feat新功能
fix修复 bug
refactor重构(不改变行为)
perf性能优化
test测试变更
docs文档变更
chore构建/工具变更

规则:

  • subject 不超过 50 字符,使用祈使语气
  • body 说明 为什么 而非 做了什么
  • 不在这里决定提交边界;边界由 implement skill + commit skill 控制

PR 描述模板

PR / MR 描述遵循 $git-commit-push skill 中的 GitCode 模板,不再自定义另一套简化格式。

创建 MR 时 body 使用以下模板,并根据实际情况填写 /kind 标签、概述、变更内容、验证结果和 checklist:

markdown
<!--  Thanks for sending a pull request!  Here are some tips for you:

1) If this is your first time, please read our contributor guidelines: https://gitcode.com/openJiuwen/community/blob/master/CONTRIBUTING.md

2) If you want to contribute your code but don't know who will review and merge, please add label `openjiuwen-assistant` to the pull request, we will find and do it as soon as possible.
-->

**What type of PR is this?**
<!--
选择下面一种标签替换下方 `/kind <label>`,可选标签类型有:
- /kind bug
- /kind task
- /kind feature
- /kind refactor
- /kind clean_code
如PR描述不符合规范,修改PR描述后需要/check-pr重新检查PR规范。
-->
/kind <label>

## 概述
<简要描述变更内容和原因>

## 变更内容
<列出主要改动点>

## 验证结果
<描述测试/验证方式和结果>

**Self-checklist**:(**请自检,在[ ]内打上x,我们将检视你的完成情况,否则会导致pr无法合入**)

+ - [ ] **设计**:PR对应的方案是否已经经过Maintainer评审,方案检视意见是否均已答复并完成方案修改
+ - [ ] **测试**:PR中的代码是否已有UT/ST测试用例进行充分的覆盖,新增测试用例是否随本PR一并上库或已经上库
+ - [ ] **验证**:PR描述信息中是否已包含对该PR对应的Feature、Refactor、Bugfix的预期目标达成情况的详细验证结果描述
+ - [ ] **接口**:是否涉及对外接口变更,相应变更已得到接口评审组织的通过,API对应的注释信息已经刷新正确
+ - [ ] **文档**:是否涉及官网文档修改,如果涉及请及时提交资料到Doc仓

Kind 标签选择:

  • bug:修复 bug
  • task:任务类改动
  • feature:新功能
  • refactor:重构
  • clean_code:代码清理

Journal 记录

每个 session 结束时记录:

markdown
## Session Journal

### 完成
- 任务列表及结果

### 未完成
- 剩余任务及原因

### 经验
- 本次 session 的关键发现
- 可复用的模式或需避免的陷阱

### 下一步
- 后续 session 的建议行动

跨 Session 接力

当任务无法在当前 session 完成时:

  1. 创建 issue 描述剩余工作
  2. 在 journal 中标注 接力: <issue-id>
  3. issue 内容包含:
    • 当前进度
    • 已完成的步骤
    • 下一步具体操作
    • 相关文件列表

求助机制

遇到以下情况时主动求助:

  1. 不确定: 修改可能影响公共 API
  2. 超出范围: 任务需要修改架构红线内的文件
  3. 反复失败: 同一操作失败 3 次以上
  4. 安全风险: 发现潜在安全问题

求助格式:

[HELP] <类别>

问题: <简要描述>
上下文: <相关文件和行号>
已尝试: <已尝试的方案>
建议: <你认为的解决方向>

输出质量要求

  • 使用中文撰写,技术术语保留英文
  • 简洁明了,避免冗余描述
  • 包含足够上下文让读者理解变更意图
  • 代码引用使用 file:line 格式

© openJiuwen-ai, 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

Just SKILL.md in openjiuwen/rsi/harness_rsi/auto_harness/skills/communicate of openJiuwen-ai/agent-core.

Open the folder on GitHubat commit 030187f

Compare with similar skills

Engineering Communication Rules 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.

Engineering Communication Rules compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Engineering Communication Rules this skillopenJiuwen-ai/agent-core446—~625Automated safety check: PassApache-2.0
PR Finalize Reviewmicrosoft/garnet12k—~3.1kAutomated safety check: PassMIT
Git Workflow and Versioningaddyosmani/agent-skills104k2 repos~3.5kAutomated safety check: NotesMIT
React Router Pull Request Creatorremix-run/react-router57k—~2.5kAutomated safety check: PassMIT
Verdaccio Pull Request Workflowverdaccio/verdaccio18k—~1.9kAutomated safety check: PassMIT
Citus Merge Loopcitusdata/citus13k—~2.5kAutomated safety check: PassAGPL-3.0

Similar skills

  • PR Finalize Review

    microsoft/garnet

    Official

    Checks that a pull request's title and description match its implementation and reviews the code for Garnet best practices, reporting findings without posting them.

    12k GitHub stars~3.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Git Workflow and Versioning

    addyosmani/agent-skills

    Sets git habits for every change: short-lived branches, atomic commits with descriptive messages, clean pull requests, plus versioning, tagging and changelogs for releases.

    104k GitHub starsUsed in 2 repos~3.5k tokens
    DevelopmentAuto-check: notes
  • React Router Pull Request Creator

    remix-run/react-router

    Packages finished React Router work into a draft pull request: branch, commit, push, a written PR body and the right GitHub labels.

    57k GitHub stars~2.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Takes a change through a verdaccio pull request: branch, local checks, changeset, title and body, labels, CI and review rounds, and ports to other release lines.

    18k GitHub stars~1.9k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Citus Merge Loop

    citusdata/citus

    Take a list of citusdata/citus PR links or numbers and merge each one independently: sync it with its base branch, fix a red check-style job with make reindent, retry other red checks a bounded…

    13k GitHub stars~2.5k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Emoji Commit Conventions

    baptisteArno/typebot.io

    Sets the repository's convention for commit messages and pull request titles: one emoji prefix for the main intent, a concise title and clean follow-up commits.

    11k GitHub stars~424 tokensUpdated 3 days ago
    DevelopmentAuto-check passed

More from openJiuwen-ai/agent-core

All 10 skills in this repo
  • Skill Safety Evaluator

    openJiuwen-ai/agent-core

    Static safety audit of a SKILL.md that scores five dimensions and acts as a gate: skills below the pass line do not ship, whatever else they score.

    446 GitHub stars~3.5k tokensUpdated today
    Auto-check: warnings
  • Repository Health and Gap Assessor

    openJiuwen-ai/agent-core

    Runs a read-only assessment in one of two modes, a repository health check or a runtime extension gap review, and reports findings as a markdown table.

    446 GitHub stars~613 tokensUpdated today
    Auto-check passed
  • Python Patterns for agent-core

    openJiuwen-ai/agent-core

    Reference for idiomatic Python in the agent-core codebase: immutability, protocols, exception hierarchies, context managers and async patterns.

    446 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Agent-Core Python Testing

    openJiuwen-ai/agent-core

    Pytest patterns for the agent-core codebase: a red-green-refactor workflow, conftest fixtures, custom marks, monkeypatch and patch mocking, and async tests.

    446 GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Agent-Core Security Checklist

    openJiuwen-ai/agent-core

    A ten-category security checklist for the agent-core codebase, to run before any security-sensitive change or pull request: secrets, input validation, SQL, access control and prompt injection.

    446 GitHub stars~1.7k tokensUpdated today
    Auto-check: notes
  • Verification Loop

    openJiuwen-ai/agent-core

    Formalizes agent-core's make check/type-check/test/fix pipeline into a structured 6-phase verification skill.

    446 GitHub stars~818 tokensUpdated today
    Auto-check passed

Categories

Questions about Engineering Communication Rules

What does Engineering Communication Rules do?

Chinese-language rules for how an agent writes commit messages, PR descriptions, session journals, handoff issues and requests for help. Written in Chinese, this skill sets how an agent communicates at the end of a task. Commit messages use conventional commits with the types feat, fix, refactor, perf, test, docs and chore; the subject stays within 50 characters in imperative mood, and the body explains why rather than what.

When should I use Engineering Communication Rules?

Engineering Communication Rules fits situations like: writing conventional commit messages for a Chinese-language team; filling in a GitCode merge request description; closing a session with a journal entry; handing unfinished work to the next session through an issue.

How do I install Engineering Communication Rules in Claude Code?

Run `npx skills add openJiuwen-ai/agent-core --skill communicate -a claude-code`. Or copy the skill folder (openjiuwen/rsi/harness_rsi/auto_harness/skills/communicate in openJiuwen-ai/agent-core) into .claude/skills/communicate in your project. Claude Code loads it when a task matches its description.

How do I install Engineering Communication Rules in Codex?

Run `npx skills add openJiuwen-ai/agent-core --skill communicate -a codex`. Or copy the skill folder (openjiuwen/rsi/harness_rsi/auto_harness/skills/communicate in openJiuwen-ai/agent-core) into .agents/skills/communicate in your project. Codex loads it when a task matches its description.

Can I use Engineering Communication Rules 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 openJiuwen-ai/agent-core --skill communicate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/communicate, .gemini/skills/communicate, .github/skills/communicate and .opencode/skills/communicate in your project.

What does Engineering Communication Rules need to run?

SKILL.md names no scripts, command-line tools or credentials: Engineering Communication Rules is instructions for the agent only. Our summary lists: The git-commit-push skill, which holds the GitCode PR template.

Does Engineering Communication Rules access the network?

SKILL.md names 1 domain. In commands or code: gitcode.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Engineering Communication Rules 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 Engineering Communication Rules use?

Engineering Communication Rules 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 Engineering Communication Rules use?

About 625 tokens (SKILL.md is roughly 2.5k 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 Engineering Communication Rules?

Skills that share tags, products or a category with Engineering Communication Rules: PR Finalize Review (microsoft/garnet, 12k stars), Git Workflow and Versioning (addyosmani/agent-skills, 104k stars), React Router Pull Request Creator (remix-run/react-router, 57k stars) and Verdaccio Pull Request Workflow (verdaccio/verdaccio, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Engineering Communication Rules?

openJiuwen-ai (a GitHub organization) maintains it in openJiuwen-ai/agent-core, which has 446 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 10, 2026.

Source: openJiuwen-ai/agent-core on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.