Agent skill

Axhub Commentary

by lintendo in lintendo/Axhub-Skills

处理 Axhub Commentary 完整工作流。优先读取本地页面批注文档,落实修改并更新批注状态,或在用户确认后写入删除标记;本地读取失败时再确认 ACP UI 并生成临时可批注地址。也可为已接入 @axhub/annotation 的页面准备标注编辑环境,或配置 AI 侧边栏对话、AI 批注执行、调整面板属性和多方案比稿。当用户提到 Axhub Commentary、Axhub…

MITAuto-check passedFrontend & Design

Install Axhub Commentary

skills CLI
$ npx skills add lintendo/Axhub-Skills --skill axhub-commentary -a claude-code

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

GitHub CLI
$ gh skill install lintendo/Axhub-Skills axhub-commentary --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/lintendo/Axhub-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/axhub-commentary .claude/skills/axhub-commentary && 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
axhub-commentary
GitHub stars
130
Token cost
~801 tokens
SKILL.md length
167 words
Files
12 (incl. scripts, references)
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

处理 Axhub Commentary 完整工作流。优先读取本地页面批注文档,落实修改并更新批注状态,或在用户确认后写入删除标记;本地读取失败时再确认 ACP UI 并生成临时可批注地址。也可为已接入 @axhub/annotation 的页面准备标注编辑环境,或配置 AI 侧边栏对话、AI 批注执行、调整面板属性和多方案比稿。当用户提到 Axhub Commentary、Axhub…

  • Frontend & Design work in your project
  • SKILL.md covers 0. 按需检测 ACP UI, 工作分流, 实施顺序 and 交付要求, plus 1 more section
  • Runs JavaScript scripts from its folder

What it does

Axhub Commentary is an agent skill from lintendo/Axhub-Skills. 处理 Axhub Commentary 完整工作流。优先读取本地页面批注文档,落实修改并更新批注状态,或在用户确认后写入删除标记;本地读取失败时再确认 ACP UI 并生成临时可批注地址。也可为已接入 @axhub/annotation 的页面准备标注编辑环境,或配置 AI 侧边栏对话、AI 批注执行、调整面板属性和多方案比稿。当用户提到 Axhub Commentary、Axhub Chrome 扩展页面批注、可批注链接、comments.json、标注编辑按钮、修改标注内容、Annotation Runtime、annotationSourcePath、根据 Commentary 意见改代码、更新或清理批注、页面 AI、供应商安装登录、调整面板、方案切换或页面定位信息时使用。可批注目标是 Figma 时,也应与 figma-content-operator 组合。

Its SKILL.md is about 800 tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including scripts and reference files (for example `references/acp-native-bootstrap.md`, `references/ai-capabilities.md` and `references/comment-processing.md`).

It sits in Frontend & Design. It works with Figma. The licence is MIT.

When your agent uses it

  • Frontend & Design work in your project

Example prompts

  • “/axhub-commentary”

Requirements

  • Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit 1e1c5bc. 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 4 files in scripts/ (JavaScript), 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

Axhub Commentary loads about 801 tokens when it runs, and up to ~8.1k if it reads all its reference files. Until then it costs about 102 tokens; SKILL.md has 167 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~102
When it runs · the whole SKILL.md, loaded when a task matches
~801
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8.1k

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

The full file from lintendo/Axhub-Skills at commit 1e1c5bc, republished under its MIT licence (© lintendo). 167 words, ~801 tokens.

Download SKILL.mdSave it as .claude/skills/axhub-commentary/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.
name
axhub-commentary
description
处理 Axhub Commentary 完整工作流。优先读取本地页面批注文档,落实修改并更新批注状态,或在用户确认后写入删除标记;本地读取失败时再确认 ACP UI 并生成临时可批注地址。也可为已接入 @axhub/annotation 的页面准备标注编辑环境,或配置 AI 侧边栏对话、AI 批注执行、调整面板属性和多方案比稿。当用户提到 Axhub Commentary、Axhub Chrome 扩展页面批注、可批注链接、comments.json、标注编辑按钮、修改标注内容、Annotation Runtime、annotationSourcePath、根据 Commentary 意见改代码、更新或清理批注、页面 AI、供应商安装登录、调整面板、方案切换或页面定位信息时使用。可批注目标是 Figma 时,也应与 figma-content-operator 组合。

Axhub Commentary 工作流

先判断工作线,再按任务读取对应的分文档和执行必要检查。不要要求目标项目安装编辑器 runtime;编辑器由 Axhub Chrome 扩展或宿主预览环境提供。

0. 按需检测 ACP UI

批注读取与处理先直接读取本地 comments.json,不检测 ACP UI;只有本地批注无法定位、读取或通过格式校验时,才检测 ACP UI,并在服务就绪后生成临时可批注地址交给用户。用户直接要求生成可批注地址、使用 AI 对话/执行或宿主资源工具时,也需要检测。

  • 访问 http://localhost:32124/api/health,只有响应同时满足 status: "ok" 和 service: "acp-ui" 才算就绪;端口占用、页面可打开或存在相关进程都不能代替该检测。
  • 检测失败时才读取 references/acp-native-bootstrap.md,按原有非沙箱规则启动并再次确认 health。Native Host 是后续可选能力,只有用户明确确认或主动要求安装时才注册。

Commentary 的 AI 对话、AI 批注执行、provider session、宿主资源工具和本地标注源读写依赖 ACP UI;未确认 health 时,不得宣称这些能力就绪。本地批注记录与 tweak 的读取回写、属性调整和页面内方案切换不依赖 ACP UI。

工作分流

先判断任务属于哪条工作线,只读取对应参考文件。

1. 批注读取与处理(主要)

任务涉及页面批注、改稿意见、批注图片、批注状态或显式删除批注节点时,读 references/comment-processing.md。

2. 可批注地址与环境准备(主要)

任务是生成可批注地址或确认页面定位时,读 references/environment-context.md。这里优先使用不改项目文件的临时链接方案;只有用户明确要求稳定入口时,才进入固定接入。

Figma 是例外:最终链接只给原始 Figma URL 加绝对 projectPath,不加 try-plugin-*。扩展必须先按稳定文件身份完成绑定,再自行启动 Drafito。

3. Annotation 标注环境准备(主要)

用户需要 Annotation 能力时,按目标处理:

  1. 需要开启 Annotation Runtime:读 axhub-annotation-standalone 完成页面接入。
  2. 需要让扩展修改标注内容:确保页面使用可编辑的标注源。外部 JSON 放在当前 filePath 同目录并命名为 annotation-source.json;单 HTML 页面把标注源内嵌在当前 HTML,并让 annotationSourcePath 指向该文件。通过页面上下文提供 projectPath、filePath 和必要的 annotationSourcePath,生成并打开可批注地址交给用户。只有标注源不符合上述两种约定时,才读 references/environment-context.md 处理自定义路径。
4. AI 对话与批注执行(主要)

任务涉及 AI 侧边栏对话、唤醒页面 AI、把批注交给 AI 执行、配置供应商,或排查供应商软件安装、终端可用性和登录授权时,读 references/ai-capabilities.md。支持范围见该文档,实际可见项和默认项以 ACP UI 当前配置为准。

5. 页面侧接入(低频)

只有用户明确要求修改页面接入能力时,才按目标读取对应分文档:

  • 调整面板属性、页面级属性聚合 → 读 references/property-editing.md
  • 多方案设计比稿、页面内方案切换 → 读 references/design-bid.md

属性调整和多方案比稿都是低频、按需能力。这是修改页面代码的工作线;临时可批注链接和已有 Runtime 的标注内容编辑不属于页面侧接入,不要为它们修改业务页面实现。

批注要求新增接入能力时可以跨工作线:先读批注处理流程确定任务,再按具体目标补读一个页面侧接入参考。

实施顺序

  1. 先判断任务是否属于主要流程 1、2、3 或 4;只有用户明确要求时才进入低频流程 5。
  2. 只读取命中流程的分文档;批注处理先读本地记录,失败后才检测 ACP UI 并生成临时地址,其他流程按上面的使用条件检测。
  3. 需要检测且 health 失败时才读取 references/acp-native-bootstrap.md,不要提前加载启动细节。
  4. 批注处理成功后先写入 completed 并保留节点,再询问用户是否清除;用户确认后只写入删除标记,实际清理由扩展统一执行。临时地址默认不修改项目文件;页面侧接入完成后再验证回写能力。

交付要求

最终回复按命中的子流程包含必要信息:

  • ACP UI:是否已确认健康;如果需要用户手动启动,给出准确命令和当前阻塞状态
  • 批注处理:完成了哪些界面修改、是否还有未处理或异常批注、做了哪些验证;写入 completed 后询问用户是否清除
  • 标注环境:可批注地址、采用的标注源形式和实际路径;未完成时说明缺少 Runtime 接入还是页面上下文
  • AI 能力:所选供应商、CLI 与登录是否就绪、provider session 是否可用;不要暴露 token 或其他凭据
  • 页面接入:修改了哪些文件、暴露了哪些属性或方案字段、做了哪些验证
  • 回复保持面向用户,不要把内部批注状态、同步细节或命令日志当作主要内容

参考

  • references/comment-processing.md
  • references/ai-capabilities.md
  • references/property-editing.md
  • references/design-bid.md
  • references/environment-context.md
  • references/acp-native-bootstrap.md

© lintendo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (scripts, references) in skills/axhub-commentary of lintendo/Axhub-Skills.

  • SKILL.md
  • references/acp-native-bootstrap.md
  • references/ai-capabilities.md
  • references/comment-processing.md
  • references/design-bid.md
  • references/environment-context.md
  • references/property-editing.md
  • references/schema-guide.md
  • scripts/acp-native-host.mjs
  • scripts/doctor.mjs
  • scripts/register.mjs
  • scripts/start-acp-ui.mjs

Open the folder on GitHubat commit 1e1c5bc

Compare with similar skills

Axhub Commentary 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.

Axhub Commentary compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Axhub Commentary this skilllintendo/Axhub-Skills130—~801Automated safety check: PassMIT
Figma Design System Builderwarpdotdev/warp65k2 repos~4.4kAutomated safety check: PassAGPL-3.0
Figma use_figma Plugin API Ruleswarpdotdev/warp65k4 repos~4.4kAutomated safety check: PassAGPL-3.0
Figma Design to Codewarpdotdev/warp65k4 repos~2.9kAutomated safety check: PassAGPL-3.0
Figma Design System Rules Generatorwarpdotdev/warp65k3 repos~4.6kAutomated safety check: PassAGPL-3.0
Figma Code Connect Componentswarpdotdev/warp65k2 repos~4.2kAutomated safety check: PassAGPL-3.0

Similar skills

  • Builds or updates a design system in Figma from a codebase in ordered phases: discovery, variables and tokens, components, theming and documentation, with checkpoints.

    65k GitHub starsUsed in 2 repos~4.4k tokens
    Frontend & DesignAuto-check passed
  • Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.

    65k GitHub starsUsed in 4 repos~4.4k tokens
    Frontend & DesignAuto-check passed
  • Figma Design to Code

    warpdotdev/warp

    Turns a Figma frame or component into production code that matches the design, using the Figma MCP server and the project's own design system.

    65k GitHub starsUsed in 4 repos~2.9k tokens
    Frontend & DesignAuto-check passed
  • Creates project-specific design system rules from your codebase so coding agents implement Figma designs with your components, naming and tokens.

    65k GitHub starsUsed in 3 repos~4.6k tokens
    Frontend & DesignAuto-check passed
  • Maps published Figma components to their code implementations with Code Connect, using the Figma MCP suggestion and mapping tools.

    65k GitHub starsUsed in 2 repos~4.2k tokens
    Frontend & DesignAuto-check passed
  • Cc Design

    ZeroZ-lab/cc-design

    High-fidelity HTML design and prototype creation. An agent skill from ZeroZ-lab/cc-design.

    827 GitHub stars~2.2k tokensUpdated 3 mo ago
    Frontend & DesignAuto-check: notes

More from lintendo/Axhub-Skills

All 13 skills in this repo
  • React To Figma Make

    lintendo/Axhub-Skills

    A skill your agent uses when 需要把现有 React、Vite、Next.js、V0 或 AI Studio 页面转换为 Figma Make 可导入的 .fig 资产,或补齐、更新、验证已有 Figma Make 导出壳和 canvas.fig。

    130 GitHub stars~4.2k tokensUpdated 1 mo ago
    Auto-check passed
  • Search Design System

    lintendo/Axhub-Skills

    A skill your agent uses when selecting an existing design system or theme for a product, page, prototype, or implementation through Axhub design knowledge indexes; not when creating or updating a…

    130 GitHub stars~643 tokensUpdated 1 mo ago
    Auto-check passed
  • Axhub Prototype Context

    lintendo/Axhub-Skills

    A skill your agent uses when an annotated prototype URL exposes PRD, directory, annotation, or source context that an AI Agent needs for review, implementation planning, production work, source…

    130 GitHub stars~684 tokensUpdated 1 mo ago
    Auto-check passed
  • Extract Axure Data

    lintendo/Axhub-Skills

    Extract structured data from Axure prototypes using Playwright — screenshots, design tokens, interaction maps, annotations, and page text.

    130 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check: warnings
  • Clone Page

    lintendo/Axhub-Skills

    高精度克隆网页。使用 Playwright 渐进式采集页面数据(DOM 结构、样式、截图、资源), 然后分阶段构建完整的 HTML/CSS 还原。支持快速还原和高精度还原两种模式。

    130 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Extract Page Data

    lintendo/Axhub-Skills

    Extract structured data from any web page using Playwright — screenshots, design tokens, page text as Markdown, interactive element maps, and full page data packs.

    130 GitHub stars~2.7k tokensUpdated 1 mo ago
    Auto-check: warnings

Works with

Questions about Axhub Commentary

What does Axhub Commentary do?

处理 Axhub Commentary 完整工作流。优先读取本地页面批注文档,落实修改并更新批注状态,或在用户确认后写入删除标记;本地读取失败时再确认 ACP UI 并生成临时可批注地址。也可为已接入 @axhub/annotation 的页面准备标注编辑环境,或配置 AI 侧边栏对话、AI 批注执行、调整面板属性和多方案比稿。当用户提到 Axhub Commentary、Axhub…. Axhub Commentary is an agent skill from lintendo/Axhub-Skills.

When should I use Axhub Commentary?

Axhub Commentary fits situations like: frontend & Design work in your project.

How do I install Axhub Commentary in Claude Code?

Run `npx skills add lintendo/Axhub-Skills --skill axhub-commentary -a claude-code`. Or copy the skill folder (skills/axhub-commentary in lintendo/Axhub-Skills) into .claude/skills/axhub-commentary in your project. Claude Code loads it when a task matches its description.

How do I install Axhub Commentary in Codex?

Run `npx skills add lintendo/Axhub-Skills --skill axhub-commentary -a codex`. Or copy the skill folder (skills/axhub-commentary in lintendo/Axhub-Skills) into .agents/skills/axhub-commentary in your project. Codex loads it when a task matches its description.

Can I use Axhub Commentary 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 lintendo/Axhub-Skills --skill axhub-commentary -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/axhub-commentary, .gemini/skills/axhub-commentary, .github/skills/axhub-commentary and .opencode/skills/axhub-commentary in your project.

What does Axhub Commentary need to run?

Going by SKILL.md and its folder, Axhub Commentary needs JavaScript for the scripts in its folder. Our summary lists: Node.js.

Does Axhub Commentary 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 Axhub Commentary 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 Axhub Commentary use?

Axhub Commentary is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Axhub Commentary use?

About 801 tokens (SKILL.md is roughly 3.2k 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 7.3k tokens, read only when the agent opens those files.

What are the alternatives to Axhub Commentary?

Skills that share tags, products or a category with Axhub Commentary: Figma Design System Builder (warpdotdev/warp, 65k stars), Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars), Figma Design to Code (warpdotdev/warp, 65k stars) and Figma Design System Rules Generator (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Axhub Commentary?

lintendo (a GitHub user) maintains it in lintendo/Axhub-Skills, which has 130 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on August 21, 2026.

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