Generate and maintain repo-docs with Chinese as the primary reader language while preserving source identifiers for lookup. Use when the user asks for Chinese repo docs, mentions repo-docs-zh, wants repo documentation in Chinese, or wants an existing repo-docs package localized for Chinese readers.
npx skills add https://github.com/YurunChen/repo-docs-skills --skill repo-docs-zh
This is the Chinese-language overlay for repo-docs. Structure, page ownership, evidence rules, sync behavior, and validation come from ../repo-docs/SKILL.md. This overlay only changes language and Chinese reader experience.
Before acting, read:
../repo-docs/SKILL.md../repo-docs/REFERENCE.md as the topic router only when detailed rules are needed../repo-docs/EXAMPLES.md only for output shape or tone examples needed by the taskChinese repo-docs are not English docs translated line by line. They should rebuild the reader's conceptual handles in Chinese.
Chinese carries understanding: what this thing is, why it exists, what happens, what details matter, and how to check it. English identifiers locate the source: paths, commands, fields, API names, class/function names, metric names, package names, and dataset names.
references/source-evidence.md is still the fixed Build evidence base in Chinese packages. Write claims, caveats, and reader-facing notes in Chinese; keep paths, commands, fields, source identifiers, and exact evidence locators in their source form.
标准包中的 code-map.md 写成“代码地图”。它在主 walkthrough 之后回答:范围内每个源码目录负责什么,里面哪些文件或符号最重要,某类修改应该从哪里开始,相关验证在哪里。中文负责说清职责和改动入口,英文路径与符号负责精确定位。
If writing exposes a weak claim or insufficient evidence, pause drafting and return to the project evidence. Re-inspect the relevant source path, tests, config, schema, data, command output, or artifact; if the evidence is still missing, label the claim as 推断 / 未确认, defer it explicitly, or leave it out.
中文名(English term) or 中文名(source identifier); later prefer the Chinese name.## 阅读路径.术语 | 项目里的意思 | 延伸阅读.证据状态:除特别标注外,本页基于当前源码已确认。Use a Chinese reader handle before a source locator.
| Type | Use in Chinese docs |
| --- | --- |
| 读者句柄 | The narrative subject, such as “导入流程”, “会话层”, “结果汇总”, “运行脚本”. |
| 源码定位符 | Paths, functions, classes, fields, commands, artifact paths. Link directly with a Chinese label when one locator supports one claim. |
| 机制细节名 | Metrics, schema keys, tool parameters, artifact file names. Put them in the owning module when they help the reader understand the concept. |
| 外部术语 | Terms like benchmark, agent, workspace, protocol, memory. First mention gets a Chinese handle; later prefer Chinese when the term appears in the inspected repo. |
Default locator rule:
references/source-evidence.md for grouped claim evidence instead of creating extra evidence/source-map pages. code-map.md is the reader-facing code navigation page, not an evidence ledger.Good:
Bad:
packages/app/scripts/run_example.sh 是入口。Session.run_task(...) handles context and scheduled observations.ResultCollector.collect(...) records output status.## 阅读路径 reader-goal table. Use columns 读者目标 | 从这里开始 | 读完后获得什么, including one row that routes evidence audit to references/source-evidence.md.## Step N: 行为名 headings; prose explains mechanism; verification appears once near the end.路径 | 职责 | 关键代码 | 与主流程的关系 汇总;随后按范围内源码目录说明重要文件、功能、关键符号、调用方/使用方和相关验证。目录名本身不能代替中文职责说明,结尾明确列出排除或暂缓区域。source-evidence.md and, when needed, quality-review.md. 行为解释放 walkthrough,源码导航放代码地图,机制细节放 modules。Use the main repo-docs English Repo docs block for AGENTS.md and other agent instruction Markdown. Chinese mode changes the reader-facing guide language; the agent instruction remains the main repo-docs block.
When a project uses Chinese reader-facing repo-docs/, add one short project-specific routing sentence immediately after the living-guide sentence:
This repo's `repo-docs/` guide is reader-facing Chinese documentation. When updating reader-facing guide pages, use `repo-docs-zh` when available; keep Chinese reader handles in the prose and preserve exact source identifiers for lookup.
Do not translate the whole agent instruction block into Chinese. The extra sentence only tells future agents to apply this overlay for reader-facing guide pages.
After first build, reply in Chinese with:
repo-docs/README.md -> main walkthrough -> repo-docs/code-map.md when locating code;Keep the reply short. Durable guide history belongs in repo-docs/change-log.md.
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take yurunchen/repo-docs-zh from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.