Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Harness 规范文档生成 · tencentblueking | DecimalAI

documentationby tencentblueking

Harness 规范文档生成

tencentblueking/harness-generating

Source tencentblueking/bk-bcs ↗License NOASSERTION

Harness 规范文档生成——harness-engineering 的子 skill，负责项目上下文感知、信息收集、五大组件与技术规范文档的生成/修正、开发地图生成及总结报告。由 harness-engineering 按生成类触发词路由调用，不独立触发。

SkillScore59Maintained

Automatic

AI Engineer pack

Last verified 9/26/2026

What it changes

Passed 9 of 16 test cases with the skill, and 4 of 16 without it.

Without skill23%

With skill59%

Checks it passed that the model alone missed

marks step gen-3d as completed
copies skill-spec.md into docs/standards/
adds docs/dev-map/README.md to git tracking

and 8 more in the full report

8 fixed5 passed either way9 still failing0 broke

Pass-rate lift: +36 pp
Tokens: +413%
Agent turns: 0%
Response time: -45%

Model gemini-3.6-flashMeasured 9/26/2026v113 of 22 cases passed with skill · 16 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/tencentblueking-harness-generating/SKILL.md https://app.decimal.ai/s/tencentblueking-harness-generating/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add tencentblueking-harness-generating, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/tencentblueking-harness-generating/ and pins it in .decimal/skills.lock

decimalai skills add tencentblueking-harness-generating

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/tencentblueking-harness-generating/SKILL.md https://app.decimal.ai/s/tencentblueking-harness-generating/SKILL.md

Raw file: /s/tencentblueking-harness-generating/SKILL.md ↗ · machine-readable summary at /s/tencentblueking-harness-generating.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

Our project domain is set to `skill-tooling`. Which mandatory specification file must be copied into docs/standards/?

What was checked, without and with the skill
Checked	Without skill	With skill
copies skill-spec.md into docs/standards/	Missed	Passed
skips security redlines and code review standards when domain is skill-tooling	Missed	Passed

case-12 · gemini-3.6-flash · 9/26/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md400 lines2 files

Harness 规范文档生成

路径约定：references/ = 本子 skill 私有资源（harness-generating/references/）；../references/ = 父 skill 共享资源（harness-engineering/references/）；../assets/ = 父 skill 预设库。

执行清单

开始执行前，使用 TodoWrite 创建如下清单（全部状态 pending）：

ID	清单项
`gen-1`	第一步：项目上下文感知（含项目类型识别、基本信息、已有 Harness 检测、环境工具检查）
`gen-2`	第二步：信息收集与交互
`gen-3`	第三步：规范文档生成（AGENTS.md + 五大组件文档 + glossary）
`gen-3b`	第三步-B：技术规范文档处理
`gen-3c`	第三步-C：开发地图生成（含 IDE 集成配置）
`gen-3d`	第三步-D：工作流文档生成（已移除，标记 completed 并 Skip）
`gen-3e`	第三步-E：初始化 `docs/business-standards/` 目录与索引骨架（幂等，已存在不覆写）
`gen-3f`	第三步-F：同步 Standards IDE Rules（`sync-standards-rules.sh`，按选用裁剪）
`gen-4`	第四步：定向修正（`targeted` 模式时必做，其他模式跳过并标记 completed）
`gen-5`	第五步：工具依赖自审
`gen-qa`	质量检查（十二项逐一核对，在生成总结前执行）
`gen-6`	第六步：生成总结报告

每完成一步：立即调用 TodoWrite 将对应条目标记为 completed，再继续下一步。

执行流程

第一步：项目上下文感知

扫描项目结构，收集以下信息作为规范生成的基础。

项目类型识别（必须最先执行，结果影响后续所有路径）

读取 ../references/project-type-detection.md，完成识别并确定 $SKILL_ROOT。
项目基本信息
- 读取 README.md、package.json、pyproject.toml 等项目描述文件
- 识别技术栈（语言、框架、构建工具）
- 检测已有的文档目录结构（docs/、AGENTS.md 等）

Track record

Benchmark

9 / 16

test cases passed, vs 4 / 16 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/25/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

tencentblueking / bk-bcs

.agents/skills/harness-engineering/harness-generating/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/25/2026Version v1Bundled 1 file

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

tencentblueking/harness-engineeringHarness 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 specClose match+59 pp pass-rate lift

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Harness 规范文档生成

执行清单

执行流程

第一步：项目上下文感知

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills