Agent skill

Harness Engineering Zh

by 10xChengTu in 10xChengTu/harness-engineering

为 AI Agent 友好的代码库搭建和改进 Harness 工程(包括 AGENTS.md、docs/、Lint 规则、Eval 系统、项目级 Prompt 工程)。触发场景:为 AI Agent 设置新项目/空项目,创建 AGENTS.md 或 CLAUDE.md,关于 Harness 工程的问题,让 Agent 在代码库上更高效地工作。当用户感到沮丧或抱怨 Agent…

No licenceAuto-check passedAgent Workflows

Install Harness Engineering Zh

skills CLI
$ npx skills add 10xChengTu/harness-engineering --skill harness-engineering-zh -a claude-code

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

GitHub CLI
$ gh skill install 10xChengTu/harness-engineering harness-engineering-zh --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/10xChengTu/harness-engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/harness-engineering-zh .claude/skills/harness-engineering-zh && 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
harness-engineering-zh
GitHub stars
102
Used in
1 other repo
Token cost
~625 tokens
SKILL.md length
181 words
Files
10 (incl. references)
Skills in repo
2
Repo updated
First seen
Licence
None found

At a glance

为 AI Agent 友好的代码库搭建和改进 Harness 工程(包括 AGENTS.md、docs/、Lint 规则、Eval 系统、项目级 Prompt 工程)。触发场景:为 AI Agent 设置新项目/空项目,创建 AGENTS.md 或 CLAUDE.md,关于 Harness 工程的问题,让 Agent 在代码库上更高效地工作。当用户感到沮丧或抱怨 Agent…

  • Works in 7 steps: 评估 (Assess) — 项目是什么?技术栈?团队规模?Agent 将如何被使用? → 设置 (Setup) — 创建基础 Harness 文件 → 阅读… → Context — 设计信息架构 → 阅读… → …
  • Tasks that involve Agent instruction files
  • SKILL.md covers 核心原则, 何时激活此 Skill, 工作流 and Harness 层级 (快速参考), plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Harness Engineering Zh is an agent skill from 10xChengTu/harness-engineering. 为 AI Agent 友好的代码库搭建和改进 Harness 工程(包括 AGENTS.md、docs/、Lint 规则、Eval 系统、项目级 Prompt 工程)。触发场景:为 AI Agent 设置新项目/空项目,创建 AGENTS.md 或 CLAUDE.md,关于 Harness 工程的问题,让 Agent 在代码库上更高效地工作。当用户感到沮丧或抱怨 Agent 质量时也会触发(例如:'Agent 总是无视规范'、'它从不听从指令'、'为什么它总是做错 X'、'Agent 坏了')— 因为 Agent 输出质量差几乎总是意味着 Harness 缺失,而不是模型问题。涵盖:Context 工程、架构约束、多 Agent 协作、评估、长运行任务 Harness、Agent 循环(自主运行、验证器、停止条件)、Agent 记忆(跨会话记忆、记忆管护)以及 Agent 质量问题诊断。

Its SKILL.md is about 630 tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `references/01-project-setup.md`, `references/02-context-engineering.md` and `references/03-constraints.md`).

It sits in Agent Workflows, covering Agent instruction files and Linting and formatting. The repository describes itself as: Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases. Triggers on: new/empty…

When your agent uses it

  • Tasks that involve Agent instruction files
  • Tasks that involve Linting and formatting

Example prompts

  • “Agent 总是无视规范”
  • “它从不听从指令”
  • “为什么它总是做错 X”
  • “/harness-engineering-zh”

Workflow steps

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

  1. 评估 (Assess) — 项目是什么?技术栈?团队规模?Agent 将如何被使用?
  2. 设置 (Setup) — 创建基础 Harness 文件 → 阅读 references/01-project-setup.md
  3. Context — 设计信息架构 → 阅读 references/02-context-engineering.md
  4. 约束 (Constraints) — 添加护栏和 Linters → 阅读 references/03-constraints.md
  5. 评估 (Evaluate) — 设置反馈循环 → 阅读 references/05-eval-feedback.md
  6. 如果项目涉及多 Agent 或长任务 → 阅读 references/04-multi-agent.md, references/06-long-running.md
  7. 如果 Agent 将无人值守运行(定时任务、CI 循环)→ 阅读 references/08-loops.md;如果希望 Agent 跨会话越用越懂 → 阅读 references/09-memory.md

What it can do on your machine

Read from SKILL.md and the folder at commit 8a210eb. 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.

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

  • Network

    No URLs in SKILL.md.

    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

Harness Engineering Zh loads about 625 tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 106 tokens; SKILL.md has 181 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~106
When it runs · the whole SKILL.md, loaded when a task matches
~625
With references · SKILL.md plus every file in references/, read only if the agent opens them
~14k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 181 words (~625 tokens).

“Harness = 为项目中工作的 AI Agent 提供的操作系统。Model 是 CPU,Context 窗口是 RAM,Harness 则是操作系统。”

— opening of SKILL.md by 10xChengTu
name
harness-engineering-zh

Read the full SKILL.md on GitHub

Files

SKILL.md and 9 other files (references) in skills/harness-engineering-zh of 10xChengTu/harness-engineering.

  • SKILL.md
  • references/01-project-setup.md
  • references/02-context-engineering.md
  • references/03-constraints.md
  • references/04-multi-agent.md
  • references/05-eval-feedback.md
  • references/06-long-running.md
  • references/07-diagnosis.md
  • references/08-loops.md
  • references/09-memory.md

Open the folder on GitHubat commit 8a210eb

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in 10xChengTu/harness-engineering, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Harness Engineering Zh 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.

Harness Engineering Zh compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Harness Engineering Zh this skill10xChengTu/harness-engineering1021 repos~625Automated safety check: PassNone
Agnixagent-sh/agnix445—~874Automated safety check: PassApache-2.0
Agnixagent-sh/agnix445—~563Automated safety check: PassApache-2.0
Writing Docsc15t/c15t1.9k—~872Automated safety check: PassApache-2.0
Review Agents Mddominik1001/caldav-mcp103—~1.2kAutomated safety check: PassMIT
Lintlanghermes-labs-ai/lintlang137—~1.7kAutomated safety check: PassApache-2.0

Similar skills

  • Agnix

    agent-sh/agnix

    A skill your agent uses when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'.

    445 GitHub stars~874 tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Agnix

    agent-sh/agnix

    A skill your agent uses when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'.

    445 GitHub stars~563 tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Writing Docs

    c15t/c15t

    Author or edit c15t documentation in docs//.mdx — the source for both the c15t.com site and the docs bundled into published packages.

    1.9k GitHub stars~872 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Review Agents Md

    dominik1001/caldav-mcp

    Reviews an AGENTS.md or CLAUDE.md file against best practices and reports concrete fixes.

    103 GitHub stars~1.2k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed
  • Lintlang

    hermes-labs-ai/lintlang

    Lint AI agent instruction files (SKILL.md, CLAUDE.md, AGENTS.md, GEMINI.md), tool definitions, system prompts, and agent configs with the deterministic LintLang CLI.

    137 GitHub stars~1.7k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Zed Config

    wcygan/dotfiles

    Zed editor configuration expert. An agent skill from wcygan/dotfiles.

    196 GitHub stars~930 tokensUpdated today
    Agent WorkflowsAuto-check passed

More from 10xChengTu/harness-engineering

  • Harness Engineering

    10xChengTu/harness-engineering

    Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases.

    102 GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed

Categories

Questions about Harness Engineering Zh

What does Harness Engineering Zh do?

为 AI Agent 友好的代码库搭建和改进 Harness 工程(包括 AGENTS.md、docs/、Lint 规则、Eval 系统、项目级 Prompt 工程)。触发场景:为 AI Agent 设置新项目/空项目,创建 AGENTS.md 或 CLAUDE.md,关于 Harness 工程的问题,让 Agent 在代码库上更高效地工作。当用户感到沮丧或抱怨 Agent…. Harness Engineering Zh is an agent skill from 10xChengTu/harness-engineering.

When should I use Harness Engineering Zh?

Harness Engineering Zh fits situations like: tasks that involve Agent instruction files; tasks that involve Linting and formatting.

How do I install Harness Engineering Zh in Claude Code?

Run `npx skills add 10xChengTu/harness-engineering --skill harness-engineering-zh -a claude-code`. Or copy the skill folder (skills/harness-engineering-zh in 10xChengTu/harness-engineering) into .claude/skills/harness-engineering-zh in your project. Claude Code loads it when a task matches its description.

How do I install Harness Engineering Zh in Codex?

Run `npx skills add 10xChengTu/harness-engineering --skill harness-engineering-zh -a codex`. Or copy the skill folder (skills/harness-engineering-zh in 10xChengTu/harness-engineering) into .agents/skills/harness-engineering-zh in your project. Codex loads it when a task matches its description.

Can I use Harness Engineering Zh 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 10xChengTu/harness-engineering --skill harness-engineering-zh -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/harness-engineering-zh, .gemini/skills/harness-engineering-zh, .github/skills/harness-engineering-zh and .opencode/skills/harness-engineering-zh in your project.

What does Harness Engineering Zh need to run?

SKILL.md names no scripts, command-line tools or credentials: Harness Engineering Zh is instructions for the agent only.

Does Harness Engineering Zh access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Harness Engineering Zh 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 Harness Engineering Zh use?

No licence was found for Harness Engineering Zh or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Harness Engineering Zh 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. Its references folder adds about 13k tokens, read only when the agent opens those files.

What are the alternatives to Harness Engineering Zh?

Skills that share tags, products or a category with Harness Engineering Zh: Agnix (agent-sh/agnix, 445 stars), Agnix (agent-sh/agnix, 445 stars), Writing Docs (c15t/c15t, 1.9k stars) and Review Agents Md (dominik1001/caldav-mcp, 103 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Harness Engineering Zh?

10xChengTu (a GitHub user) maintains it in 10xChengTu/harness-engineering, which has 102 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on August 2, 2026.

Source: 10xChengTu/harness-engineering on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.