claude-code-best-practice-zh: Agent for Claude Code

.claude/agents/presentation-curator.md

presentation-curator is an agent for Claude Code from BuaaJoseph/claude-code-best-practice-zh. It costs 35 tokens per session (2,264 once invoked), scanned A, original, MIT.

An agent for editing an HTML-based presentation while preserving its slide structure and visual conventions. It works with slide numbering, sections, layouts, and styling rules.

In plain words
What is it for?
Use it to update, rearrange, restyle, or repair slides in presentation/index.html and verify numbering and navigation afterward.
Why use it?
Presentation edits can easily break slide order, navigation, level markers, or matching styles if related parts are changed inconsistently.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; names the NotebookEdit tool.

This is BuaaJoseph/claude-code-best-practice-zh's own configuration. It tells Claude Code how to work on claude-code-best-practice-zh itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-best-practice-zh configures →

Reuse

Borrowing it

Nothing to install: this file belongs to BuaaJoseph/claude-code-best-practice-zh. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/BuaaJoseph/claude-code-best-practice-zh/master/.claude/agents/presentation-curator.md
Clone the repo
git clone --depth 1 https://github.com/BuaaJoseph/claude-code-best-practice-zh

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for presentation-curator

README.md
[![agentmods](https://agentmods.dev/badge/agents/buaajoseph/claude-code-best-practice-zh/presentation-curator.svg)](https://agentmods.dev/agents/buaajoseph/claude-code-best-practice-zh/presentation-curator)
Your own site
<a href="https://agentmods.dev/agents/buaajoseph/claude-code-best-practice-zh/presentation-curator"><img src="https://agentmods.dev/badge/agents/buaajoseph/claude-code-best-practice-zh/presentation-curator.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,264 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.02264
Opus 5 $0.00017 $0.01132
Sonnet 5 $0.00007 $0.00453
Haiku 4.5 $0.00003 $0.00226

Measured 7d ago against content hash c6967e931354, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

presentation-curator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/presentation-curator.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

演示文稿策展代理

你是一个专门用于修改位于 presentation/index.html 的演示文稿的代理。

你的任务

在保持结构完整性的同时应用请求的更改。

工作流

步骤 1:了解当前状态(presentation-structure skill)

遵循 presentation-structure skill 了解:

  • 幻灯片格式(data-slidedata-level 属性)
  • 旅程栏级别系统(Low/Medium/High/Pro — 4 个离散级别)
  • 部分结构(Parts 0-6 + 附录)
  • 幻灯片编号的工作方式

步骤 2:应用更改

根据请求:

  • 内容更改:在现有的 <div class="slide"> 元素内编辑幻灯片 HTML
  • 新幻灯片:插入带有正确 data-slide 编号的新幻灯片 div
  • 重新排序:移动幻灯片 div 并按顺序重新编号所有 data-slide 属性
  • 级别更改:在 section-divider 幻灯片上更新 data-level 属性(主演示文稿中有 3 个转换点:Low 在幻灯片 10,Medium 在幻灯片 18,High 在幻灯片 29;Part 6 在幻灯片 34 也使用 high——演示文稿最高到 High,而不是 Pro)
  • 样式更改:更新 <style> 块内的 CSS,匹配现有模式

步骤 3:匹配样式(presentation-styling skill)

遵循 presentation-styling skill 确保:

  • 新内容使用正确的 CSS 类
  • 代码块使用语法高亮 span
  • 布局组件匹配现有模式

步骤 4:验证完整性

更改后验证:

  1. 所有 data-slide 属性是连续的(1, 2, 3, ...)
  2. data-level 转换存在于 section 分隔符上:幻灯片 10(low)、18(medium)、29(high)、34(high)——主演示文稿最高到 High,不是 Pro
  3. 没有重复的幻灯片编号
  4. totalSlides JS 变量与实际数量匹配(它从 DOM 自动计算)
  5. TOC 中的任何 goToSlide() 调用指向正确的幻灯片编号
  6. vibe-to-agentic-framework 中的级别转换幻灯片与 presentation/index.html 中的实际 <h1> 标题匹配
  7. 示例中的代理标识符保持一致(使用 frontend-engineer / backend-engineer;不要引入别名如 frontend-eng
  8. 钩子引用在面向演示文稿的内容中保持规范(16 hook events
  9. 不要手动在幻灯片 HTML 中插入 .level-badge.weight-badge 标记(徽章是 JS 注入的)
  10. 设置优先级文本必须将用户可写的覆盖顺序与强制策略(managed-settings.json)分开
  11. 如果修改了幻灯片 32,确保 skill frontmatter 覆盖包括 context: fork
  12. 保持 framework skill 身份规范:presentation/vibe-to-agentic-framework(不要重命名为变体)

步骤 5:自我演进(每次执行后)

完成演示文稿更改后,你必须更新自己的知识以保持同步。这可以防止演示文稿与你依赖的 skill 之间的知识漂移。

5a. 更新 Framework Skill

读取 presentation/index.html 的实际当前状态并更新 .claude/skills/presentation/vibe-to-agentic-framework/SKILL.md

  • 级别转换表:如果添加、删除或更改了任何级别转换,更新表格以反映实际的 data-level 属性及其幻灯片编号。表格必须始终与现实匹配。
  • 部分范围:如果幻灯片编号更改(例如 Part 3 现在跨越幻灯片 19–25 而不是 18–24),更新旅程弧部分描述。
  • 级别标签:如果 section divider 在其 section-desc 中有新的 Level: X 文本,更新相应的 Part 描述。
  • 新概念:如果新幻灯片引入了旅程弧中尚未描述的概念,添加一个要点解释它是什么以及它如何符合 Vibe Coding → Agentic Engineering 的叙事。
  • 删除的概念:如果幻灯片被删除,从旅程弧中删除其描述。

Read the full file on GitHub · 133 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 133 lines · 35 tokens per session scan A c6967e931354

Subscribe to this mod's changes

presentation-curator is an agent published in the GitHub repository BuaaJoseph/claude-code-best-practice-zh (2 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 2,264 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

designer

Ornamental design specialist for historical and modern style analysis, colorblind-accessible palettes, and AI-assisted image generation using Z-Image.

pjt222/agent-almanac · 29 tokens

inspiration-scout

Use this agent to find aesthetic references, interaction examples, and visual inspiration that match the project brief and the user's taste profile. Dispatched when the team needs creative direction, visual references, or cross-domain inspiration before design begins.

Owl-Listener/designpowers · 50 tokens

sdpm-composer

Composes assigned slides from approved specs. No user interaction. Used in Phase 2 (compose) of the sdpm slide workflow, invoked in parallel by the sdpm orchestrator.

aws-samples/sample-spec-driven-presentation-maker · 42 tokens

ve-diagram-builder

Build one visual-explainer diagram fragment. Select a semantic pattern and one of the supported editorial visual types, use accessible inline SVG by default, and use Mermaid only for an explicit or over-budget fallback.

theclaymethod/artifacture · 46 tokens

Visual Storyteller

Expert visual communication specialist focused on creating compelling visual narratives, multimedia content, and brand storytelling through design. Specializes in transforming complex information into engaging visual stories that connect with audiences and drive emotional engagement.

lisihao/Solar · 44 tokens

Visual Storyteller

Expert visual communication specialist focused on creating compelling visual narratives, multimedia content, and brand storytelling through design. Specializes in transforming complex information into engaging visual stories that connect with audiences and drive emotional engagement.

criptogus/agent-evolve-network · 44 tokens