Agent skill

Harness Engineering

by TencentBlueKing in TencentBlueKing/bk-bcs

Harness Engineering 编排器——为 AI Agent 构建运行环境规范. An agent skill from TencentBlueKing/bk-bcs.

Custom licenceAuto-check passedAgent Workflows

Install Harness Engineering

skills CLI
$ npx skills add TencentBlueKing/bk-bcs --skill harness-engineering -a claude-code

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

GitHub CLI
$ gh skill install TencentBlueKing/bk-bcs harness-engineering --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/TencentBlueKing/bk-bcs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/harness-engineering .claude/skills/harness-engineering && 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
GitHub stars
840
Token cost
~765 tokens
SKILL.md length
156 words
Files
238 (incl. scripts, references, assets)
Skills in repo
30
Repo updated
First seen
Licence
Custom licence

At a glance

Harness Engineering 编排器——为 AI Agent 构建运行环境规范. An agent skill from TencentBlueKing/bk-bcs.

  • Works in 3 steps: 匹配维护类触发词 → harness-gardening → 匹配生成类触发词(或默认) → harness-generating → 无法判定 → 询问用户意图(生成规范 / 文档巡检)
  • The user mentions Harness Engineering
  • SKILL.md covers 核心理念, 路由与编排 and 参考资源
  • Harness gardening

What it does

Harness Engineering is an agent skill from TencentBlueKing/bk-bcs. Harness Engineering 编排器——为 AI Agent 构建运行环境规范。 通过触发词路由到两个子 skill:harness-generating(规范文档生成/修正) 和 harness-gardening(文档一致性巡检与修复)。 Use this skill whenever the user mentions Harness Engineering, AI Agent 运行环境, 驾驭工程, Agent 规范, 上下文工程, 架构约束, 熵管理, 工具能力, 执行与验证, 生成 Harness 文档, Agent 治理, AI 治理规范, 构建 Agent 环境, Agent harness, AGENTS.md, 词汇表, glossary, 文档园艺, 文档巡检, 检查文档一致性, 文档是否过时, harness gardening, 扫描文档, 园艺扫描, 开发地图, dev map, 生成开发地图, 更新开发地图, 项目地图, 代码索引, 源文件索引, 模块索引, 模块依赖, or any workflow involving Harness spec generation or…

Its SKILL.md is about 770 tokens, which your agent loads only when the skill is triggered. The skill folder holds 241 other files, including scripts, reference files and assets (for example `assets/dev-map-templates.md`, `assets/harness-spec-template.md` and `assets/ide-rules/README.md`).

It sits in Agent Workflows, covering Agent instruction files. The repository describes itself as: 蓝鲸智云容器管理平台(BlueKing Container Service).

When your agent uses it

  • The user mentions Harness Engineering
  • Harness gardening
  • Any workflow involving Harness spec generation
  • Document maintenance

Example prompts

  • “/harness-engineering”

Workflow steps

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

  1. 匹配维护类触发词 → harness-gardening
  2. 匹配生成类触发词(或默认) → harness-generating
  3. 无法判定 → 询问用户意图(生成规范 / 文档巡检)

What it can do on your machine

Read from SKILL.md and the folder at commit 282070c. 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

    Ships 1 file in scripts/, which the agent can run.

    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 loads about 765 tokens when it runs, and up to ~17k if it reads all its reference files. Until then it costs about 139 tokens; SKILL.md has 156 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~139
When it runs · the whole SKILL.md, loaded when a task matches
~765
With references · SKILL.md plus every file in references/, read only if the agent opens them
~17k

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); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 156 words (~765 tokens).

“Harness Engineering 的本质是为 AI Agent 构建可靠的"运行环境"——不是优化模型本身, 而是通过系统级工具链解决模型在真实环境中的状态管理、工具调用、任务漂移、结果验证等问题。 当 Agent 表现不佳时,优先审视环境支持是否充分,而非归咎于模型能力不足。”

— opening of SKILL.md by TencentBlueKing, Custom licence
name
harness-engineering
slug
harness-engineering
version
1.6.7

Read the full SKILL.md on GitHub

Files

SKILL.md and 237 other files (scripts, references, assets) in .agents/skills/harness-engineering of TencentBlueKing/bk-bcs.

  • SKILL.md
  • assets/dev-map-templates.md
  • assets/dev-map.gitignore
  • assets/harness-spec-template.md
  • assets/ide-rules/README.md
  • assets/ide-rules/claude/graphify.md.template
  • assets/ide-rules/claude/standards-api.md.template
  • assets/ide-rules/claude/standards-backend.md.template
  • assets/ide-rules/claude/standards-frontend.md.template
  • assets/ide-rules/claude/standards-gate.md.template
  • assets/ide-rules/claude/standards-security.md.template
  • assets/ide-rules/codebuddy/graphify.md.template
  • assets/ide-rules/codebuddy/standards-api.md.template
  • assets/ide-rules/codebuddy/standards-backend.md.template
  • assets/ide-rules/codebuddy/standards-frontend.md.template
  • assets/ide-rules/codebuddy/standards-gate.md.template
  • assets/ide-rules/codebuddy/standards-security.md.template
  • … and 221 more

Open the folder on GitHubat commit 282070c

Compare with similar skills

Harness Engineering 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 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Harness Engineering this skillTencentBlueKing/bk-bcs840—~765Automated safety check: PassCustom licence
Using Agent Skillsaddyosmani/agent-skills103k4 repos~2.4kAutomated safety check: PassMIT
Claude ReflectBayramAnnakov/claude-reflect1.7k2 repos~627Automated safety check: PassMIT
Writing For Agentsbestofjs/bestofjs3.1k19 repos~2.7kAutomated safety check: PassMIT
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~12kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Using Agent Skills

    addyosmani/agent-skills

    Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.

    103k GitHub starsUsed in 4 repos~2.4k tokens
    Agent WorkflowsAuto-check passed
  • Claude Reflect

    BayramAnnakov/claude-reflect

    Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.

    1.7k GitHub starsUsed in 2 repos~627 tokens
    Agent WorkflowsAuto-check passed
  • Writing For Agents

    bestofjs/bestofjs

    Writing documents for agents. An agent skill from bestofjs/bestofjs.

    3.1k GitHub starsUsed in 19 repos~2.7k tokens
    Agent WorkflowsAuto-check passed
  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 7 days ago
    Agent WorkflowsAuto-check passed
  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-check passed
  • SkillOpt Sleep Cycle

    microsoft/SkillOpt

    Official

    Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.

    18k GitHub stars~2.3k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

More from TencentBlueKing/bk-bcs

All 30 skills in this repo
  • Tapd Story Pipeline

    TencentBlueKing/bk-bcs

    单需求实现流水线——把一个 TAPD 需求从零推进到代码提交。自动串联技术澄清、 开发计划、任务拆分、TDD 实现、架构/安全校验、代码提交六个阶段。

    840 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed
  • Tapd Iteration Plan

    TencentBlueKing/bk-bcs

    TAPD 迭代规划技能。基于"approved"状态的需求池,结合需求依赖关系、size 规模、 优先级进行全局编排,将合适规模的需求规划进入指定迭代。支持新建迭代和已有迭代 重入两种模式,自动控制迭代总规模上限(默认 1000),通过有向无环图(DAG)分析 保证依赖需求优先入迭代。

    840 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed
  • Tapd Iteration Runner

    TencentBlueKing/bk-bcs

    TAPD 迭代调度器——批量开发一个迭代中的全部需求。自动完成环境初始化、 需求依赖分析、逐需求调度 pipeline 实现、迭代汇总报告四段编排。

    840 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed
  • Tapd Product Discovery

    TencentBlueKing/bk-bcs

    A skill your agent uses when work starts before a complete PRD exists, including 产品前置, 产品调研, 用户调研, 竞品分析, PRD, 原型, 想法建单, 老板需求, 需求来源, 产品父单, 角色拆单, 设计子单, 前端子单, 后端子单, 页面原型 Spec, BKUI 原型, HTML 原型, 原型评审…

    840 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed
  • Tapd Story Clarification

    TencentBlueKing/bk-bcs

    TAPD 需求澄清技能。从 TAPD 提取"规划中"状态的需求,按照研发最佳实践对需求进行 多维度澄清(业务逻辑、外部系统交互、上下文),整合项目背景知识,输出符合需求文档 规范的标准化 Markdown 需求文档,并回写 TAPD。

    840 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Tapd Story Evaluation

    TencentBlueKing/bk-bcs

    TAPD 需求评估技能。基于规范需求文档进行逻辑分析,进行子需求拆分、规模评分(size,斐波那契)与 业务价值(RICE)评分。

    840 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Harness Engineering

What does Harness Engineering do?

Harness Engineering 编排器——为 AI Agent 构建运行环境规范. An agent skill from TencentBlueKing/bk-bcs. Harness Engineering is an agent skill from TencentBlueKing/bk-bcs.

When should I use Harness Engineering?

Harness Engineering fits situations like: the user mentions Harness Engineering; harness gardening; any workflow involving Harness spec generation; document maintenance.

How do I install Harness Engineering in Claude Code?

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

How do I install Harness Engineering in Codex?

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

Can I use Harness Engineering 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 TencentBlueKing/bk-bcs --skill harness-engineering -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, .gemini/skills/harness-engineering, .github/skills/harness-engineering and .opencode/skills/harness-engineering in your project.

What does Harness Engineering need to run?

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

Does Harness Engineering 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 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Harness Engineering use?

Harness Engineering has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Harness Engineering use?

About 765 tokens (SKILL.md is roughly 3.1k 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 16k tokens, read only when the agent opens those files.

What are the alternatives to Harness Engineering?

Skills that share tags, products or a category with Harness Engineering: Using Agent Skills (addyosmani/agent-skills, 103k stars), Claude Reflect (BayramAnnakov/claude-reflect, 1.7k stars), Writing For Agents (bestofjs/bestofjs, 3.1k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Harness Engineering?

TencentBlueKing (a GitHub organization) maintains it in TencentBlueKing/bk-bcs, which has 840 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 8, 2026.

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