Individual skill
hld-writer
Write HLD, High-Level Design, 写技术设计文档。Use when: PRD 和 API Contract 完成后需要做系统架构设计、技术选型、制定技术方案。 也用于既有相关文档的有限增量更新。
plugins/testany-eng/skills/hld-writer/SKILL.md
Source commit 38b460cf3669f84ff6d1427d3d9b2a4a08e42233
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 7, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 82
- Repository last updated
- Oct 23, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- claude-code Repository topic
- codex Repository topic
- skilldock Repository topic
- test-automation Repository topic
- testany Repository topic
- design Derived category
- legal Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 19,800 bytesSKILL.mdcore · 19,800 bytesSKILL.mdcore · 19,800 bytesagents/openai.yamlasset · 289 bytesassets/integration.en.mddoc · 5,159 bytesassets/integration.mddoc · 4,338 bytesassets/new-feature-backend.en.mddoc · 5,863 bytesassets/new-feature-backend.mddoc · 4,955 bytesassets/new-feature-ui.en.mddoc · 6,765 bytesassets/new-feature-ui.mddoc · 5,709 bytesassets/optimization.en.mddoc · 5,545 bytesassets/optimization.mddoc · 4,559 bytesassets/refactoring.en.mddoc · 4,937 bytesassets/refactoring.mddoc · 4,156 bytesassets/testany-logo-small.pngasset · 49,082 bytesassets/testany-logo.svgasset · 7,663 bytesreferences/prd-splitting.mddoc · 6,319 bytes
Read excerpt
# HLD Writer
执行前读取 [工作流执行约定](../../references/workflow-execution.md):先取证再提问、按实际工具能力回退,并从本次安装位置定位资源。
> **语言规则**:默认跟随用户输入语言;用户显式指定时以用户指定为准;不要因为本 `SKILL.md` 是中文而强制输出中文;`TRACEABILITY-METADATA` 的字段名、枚举值、ID、comment markers 始终保持英文。若本 skill 使用模板或派发子任务,继续传递同一个 `output_language`。详见 `../../references/language-policy.md`。
你是一个专业的技术设计文档(HLD)写作助手。你的职责是帮助用户撰写清晰、完整、可落地的高层技术设计文档。
## 先选工作模式
- `formal_design`:用户要求完整新功能文档或正式全量准出,执行下文完整流程、模板、追溯和适用门禁。
- `bounded_change`(`amendment`):在已有有效基线和明确授权的变更范围内,读取 [有限增量规则](../../references/document-amendments.md),直接执行“读取基线与授权 -> 核对影响边界 -> 修改获授权增量 -> 检查差异与验证 -> 交付范围限定的结果”。不回补全套历史文档,不把草稿或自检升级为批准。
- 模式由实际职责、信任、契约、失败语义与批准范围决定,不按行数/文件数判断。“两行修改”改变权限边界仍需对应有权 Owner 决策。