zread
Produce and consume a wiki-style knowledge base for a code repository via the `zread` CLI and its on-disk output under `./.zread/wiki/`. Use this skill whenever the user wants to understand, onboard onto, explore, summarize, map, or get an overview of an unfamiliar codebase; asks for architecture docs, a project wiki, a repo walkthrough, module/package explanations, or "what does this repo do"; wants to generate, regenerate, resume, browse, or serve code documentation locally; or mentions zread / zread.ai directly. Also use it proactively before diving into a large unknown repo — if `./.zread/wiki/current` exists, read the generated pages instead of crawling source file-by-file; if it doesn't, consider offering to run `zread generate`. The trigger is the intent (understand a codebase through generated docs), not the literal word "zread".
- License 许可
- MIT
- 最近更新
- 2026-11-01
- Stars
- ★ 3
- Forks
- 1
01 前言 Front Matter
- name
- zread
- description
- Produce and consume a wiki-style knowledge base for a code repository via the `zread` CLI and its on-disk output under `./.zread/wiki/`. Use this skill whenever the user wants to understand, onboard onto, explore, summarize, map, or get an overview of an unfamiliar codebase; asks for architecture docs, a project wiki, a repo walkthrough, module/package explanations, or "what does this repo do"; wants to generate, regenerate, resume, browse, or serve code documentation locally; or mentions zread / zread.ai directly. Also use it proactively before diving into a large unknown repo — if `./.zread/wiki/current` exists, read the generated pages instead of crawling source file-by-file; if it doesn't, consider offering to run `zread generate`. The trigger is the intent (understand a codebase through generated docs), not the literal word "zread".
02 资源文件 2
- 参考文档README.md3.0 KB
- 参考文档references/stdio-protocol.md13.1 KB
03 SKILL.md 正文
zread skill
zread is a CLI that generates wiki documentation from code in the current
workspace using an LLM. Output lives under ./.zread/wiki/ in the workspace;
public repos can also be viewed at https://zread.ai.
This skill is intended for agent use. Read generated files directly from disk,
and use --stdio as the default mode for any zread command instead of trying
to parse the human TUI.
On-disk layout (read these directly)
Always run zread from the workspace root. After a successful generation:
./.zread/wiki/current— text file containing the active version id (e.g.2026-03-12-010203)../.zread/wiki/versions/<id>/wiki.json— TOC:{id, generated_at, language, pages: [{slug, title, file, section, group, level}]}../.zread/wiki/versions/<id>/<file>— page markdown referenced bypages[*].file../.zread/wiki/drafts/— in-progress generation; presence means a previous run did not finish.drafts/wiki.jsonexists once the catalog phase completed.~/.zread/config.yaml— global config (LLM provider, language, concurrency).~/.zread/login.json— presence indicates the user has logged in.
To answer questions about a codebase that already has zread output, read these
files directly with the file tools — do not invoke zread browse.
Commands
| Command | Purpose | Key flags |
|---|---|---|
zread generate |
Generate wiki for cwd | -y/--yes, --draft resume|clear|cancel, --skip-failed, --stdio |
zread browse |
Serve docs at http://localhost:9681+ and open browser | --generate, --version <id>, --host, --port, --stdio |
zread login |
OAuth into BigModel/Z.AI to obtain an API key | --custom, --model, --stdio |
zread config |
Edit ~/.zread/config.yaml |
--stdio |
zread update |
Self-update CLI | --stdio |
zread version |
Print version | --stdio |
--stdio is supported on every command and turns the process into a JSON-line
machine protocol on stdin/stdout. See
references/stdio-protocol.md for the wire
format (events, waiting_for, done, quit). Load it whenever zread is
invoked from another program/agent.
Decision tree for an AI agent
-
User wants to read existing wiki content?
- Check
./.zread/wiki/current. If present, readwiki.jsonand the page markdown directly. No CLI invocation needed. - For known public GitHub repos, prefer the
mcp__zread__*tools (get_repo_structure,read_file,search_doc) over running the CLI.
- Check
-
User wants to (re)generate docs?
- Confirm with the user first —
generateis long-running, calls an LLM, and writes files. Get explicit consent in unfamiliar directories. - Verify
~/.zread/login.jsonexists or~/.zread/config.yamlhas anllm.api_key. If neither, runzread loginfirst. - If
./.zread/wiki/drafts/exists, decide:- resume previous run →
zread generate --draft resume -y - throw away and start fresh →
zread generate --draft clear -y
- resume previous run →
- Otherwise:
zread generate -y. - To not block on a few failing pages: add
--skip-failed.
- Confirm with the user first —
-
User wants to view docs in a browser?
zread browse(add--generateto bootstrap if no wiki exists yet).
-
User wants to script zread / consume output programmatically?
- Use
--stdioand follow stdio-protocol.md. Do not screen-scrape the TUI.
- Use
Non-interactive invocation rules
- Always pass
-ytogeneratewhen running unattended; otherwise it stops at a catalog confirmation gate. - Always set
--draftexplicitly when a draft may exist, so the command does not prompt. - For any command run from another agent/script, use
--stdioso output is parseable JSON instead of ANSI TUI frames. zreadwrites logs to~/.zread/log/zread.log— read this if a run fails silently.
Safety / blast radius
generateconsumes LLM tokens (real cost) and can run for many minutes on large repos. Confirm before launching.generatewrites only under./.zread/and does not commit anything to git. It is safe to delete./.zread/wiki/drafts/to recover from a stuck state.updatereplaces the zread binary in place and is hard to reverse — only run it when the user explicitly asks.loginopens a browser for OAuth; do not run it in a non-interactive context unless the user has asked for it.
Reference files
- references/stdio-protocol.md — JSON-line
wire protocol shared by every command's
--stdiomode. Load when programmatically driving zread.
04 同仓库更多 Skills
seedance-prompt-en
Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and audio inputs with the @ reference system. Covers camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short dramas, and educational content.
onepage-pdf
Convert an HTML page into a single continuous-page PDF (one tall page, no pagination breaks), preserving desktop layout, backgrounds and selectable text. Use when the user asks to turn an HTML file/report/proposal into a "single-page PDF", "long PDF", "不分页 PDF", "单页 PDF", "长图式 PDF", or complains that an HTML-to-PDF export breaks into pages or cuts content. Supports optional string redaction with leak verification.
native-feel-cross-platform-desktop
Use when the user is designing, prototyping, or rewriting a desktop app that must run on multiple OSes (macOS + Windows, optionally Linux) AND feel indistinguishable from a native app to its users — fast launch, native windowing, native input handling, native materials. Trigger words include "cross-platform desktop", "Electron alternative", "Tauri vs native", "WebView wrapper", "near-native performance", "Raycast architecture", "WebKit/WebView2 quirks", "WKWebView", "system tray app", "global hotkey app", "launcher app". Do NOT trigger this skill for pure web apps, pure mobile apps, or for greenfield projects that have no native-feel requirement.
gstack
Router for the gstack skill suite. (gstack)
fireworks-tech-graph
Use when the user wants to create any technical diagram - architecture, data flow, flowchart, sequence, agent/memory, or concept map - and export as SVG+PNG. Trigger on: "画图" "帮我画" "生成图" "做个图" "架构图" "流程图" "可视化一下" "出图" "generate diagram" "draw diagram" "visualize" or any system/flow description the user wants illustrated.
dbs-video-extract
接收抖音、小红书、微信视频号等短视频链接或分享文案,查询作品/账号数据并提取语音文字稿,按作者和标题归档为 Markdown。用户希望完整解析短视频、取得数据或文字稿时使用;运行前检查 TikHub 与轻抖使用凭证,缺少时用新手能理解的方式引导购买和安全配置。