presentation

审查 · 57
已收录

Use when the user wants to create presentation slides, a slide deck, a technical talk, or a conference talk for a topic or library — built on Slidev. Interviews the user, deep-researches and code-grounds the topic FIRST, applies presentation-craft best practices, generates a Slid

Verified installs0
Stars39
版本1.0.0
质量57/100 · 有潜力
信任57/100 · Do not auto-install
审计71/100 · 高风险

供给资产档案

编程与开发 Agent

代码审查、仓库分析、测试、CI、GitHub、DevOps 与开发工作流 Skill。

浏览赛道

场景

GitHub automation

I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

适配 Agent

Claude Code + Browser agents + CLI

适用于 Codex、Claude Code、Cursor、CLI 或自定义 Agent。

安装

就绪

npx skills add AlemTuzlak/skills --skill presentation

维护状态

新鲜

距上次推送 3 天

风险

高风险

许可证不清晰

GitHub 质量

39

57/100 质量 · 65/100 信任

覆盖标签

编程GitHub automation研究agent-skill

审查说明

许可证不清晰 · Permission surface may require sandboxing

Agent 采用评分卡

一眼查看信任、审计与安装准备度

这些分数综合公开仓库元数据、OpenAgentSkill 审查信号、维护新鲜度与安装准备度。它用于候选筛选,不替代人工审查。

质量

有潜力
57

有用的候选项,但采用前应与替代方案比较。

信任

Do not auto-install
57

Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.

审计

高风险
71

对安装准备度、安全元数据、维护情况与采用风险的机器可读审查。

OpenAgentSkill 信任评分 v5

仅限沙盒

Choose a stronger alternative or inspect the source manually before any install attempt.

CodexClaude CodeCursorOpenAgentSkill CLI

Stars

39 个 GitHub Stars

仓库活跃度

39 个 Star,0 个 Fork

维护状态

距上次推送 3 天

许可证

未知

安装

npx skills add AlemTuzlak/skills --skill presentation

安装安全性

标准软件包或运行时安装路径

权限范围

shell or command execution, filesystem or document access

Agent 结果

暂未有 Agent 结果数据

文档

README/SKILL.md 上下文充分

风险摘要

生产前审查

  • Repository license is unknown; no LICENSE file or license declaration detected in the skill. This creates legal ambiguity for reuse.
  • This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.
  • 许可证不清晰
  • Low GitHub adoption signal

安装准备度

安装路径可用

  • 安装路径可用
  • 仓库证据可用
  • 许可证不清晰
  • 暂无 Agent 验证结果证据

Agent 可读元数据

这个 Skill 的机器可读决策数据。

使用此区块或内嵌 JSON 判断 Agent 是否应安装该 Skill、选择替代方案,或先请求人工审查。

打开 JSON

适用任务

  • 演示文稿生成 工作流
  • Claude Code 团队
  • builders willing to evaluate younger projects
  • Choose the right deck format

适用 Agent

CodexClaude CodeCursorOpenAgentSkill CLIBrowser agentsCLI

安装决策

命令
npx skills add AlemTuzlak/skills --skill presentation
策略
阻止
人工审查

信任与风险

信任
57/100
审计
71/100
风险级别
高风险

结果闭环

端点
/api/agent/outcome
事件 ID
resolve
结果
5

安装命令

npx skills add AlemTuzlak/skills --skill presentation

不适用场景

  • 需要厂商支持 SLA 的团队
  • production agents without a repository review
  • Low GitHub adoption signal
  • Repository license is unknown; no LICENSE file or license declaration detected in the skill. This creates legal ambiguity for reuse.
  • Audit risk risky exceeds max_risk=medium

Agent 安全 v2

39/100 · 避免自动安装

Blocked for auto-install阻止

This skill should not be selected by an agent without explicit human security review.

Do not auto-install. Inspect the source, dependencies, and permission surface first.

通过 API 解析

Shell 或命令执行

Skill 元数据引用了终端、CLI、Shell、子进程或命令执行工作流。

Browser automation

Skill may drive a browser or interact with web pages.

网络访问

Skill 可能访问远程页面、API、仓库或外部服务。

文件系统访问

Skill 可能读取或写入项目文件、文档、生成产物或本地工作区状态。

  • Audit risk risky exceeds max_risk=medium
  • 高风险权限提示:Shell 或命令执行
  • 许可证不清晰

安装目标

在你的 Agent 工作流中安装此 Skill

通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。

skill install

OpenAgentSkill CLI

Resolve policy, run the source installer safely, and report a verified install receipt.

$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install alemtuzlak-presentation

Agent 解析计划

让 Agent 在安装前验证匹配度。

Resolve API 返回首选 Skill、替代方案、安全策略、审计说明、安装目标和可直接执行的提示词,无需抓取此页面。

打开文本计划

Agent 应检查

  • 从 Resolve API 检查任务匹配与替代方案。
  • 检查审计评分、信任评分和安全策略警告。
  • 检查 Codex、Claude Code、Cursor 或 CLI 的安装目标兼容性。

复制提示词

Task: Use presentation in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20presentation%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/alemtuzlak-presentation/install
Install command: npx skills add AlemTuzlak/skills --skill presentation
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Agent 交接

把安装路径交给 Agent,而不是再给一个目录页。

通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。

打开安装 API

Agent 提示词

Use presentation for this task. Review https://www.openagentskill.com/api/skills/alemtuzlak-presentation/install, then install with: npx skills add AlemTuzlak/skills --skill presentation

Registry 元数据

用于自动选择 Skill 的 Agent 可读档案。

本页通过 Registry API 提供相同的决策、信任、审计、场景和安装信号,让 Agent 无需抓取界面即可排序。

打开 Manifest

适配 Agent

58/100

演示文稿生成

平台

Claude Code, Browser agents

审计报告

高风险 · 71/100

对安装准备度、安全元数据、维护情况与采用风险的机器可读审查。

查看审计报告查看评估报告

Agent 决策面板

Fallback candidate for Presentation generation

先用此 Skill 做原型验证,并保留备选方案。

58
就绪度
原型验证
阶段

栈中角色

备选候选

主要匹配

演示文稿生成

信任标签

先做原型验证

安装路径

命令已就绪

适用场景

  • 演示文稿生成 工作流
  • Claude Code 团队
  • builders willing to evaluate younger projects

证据

  • 仓库近期活跃
  • 已提供安装命令或 GitHub 仓库
  • 57/100 质量档案
  • 5 个 OpenAgentSkill 交互事件

先审查

  • Low GitHub adoption signal
  • Repository license is unknown; no LICENSE file or license declaration detected in the skill. This creates legal ambiguity for reuse.

实施路径

  1. 1在沙盒 Agent 中安装它,并端到端完成一次演示文稿生成任务。
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

信任档案

Do not auto-install

Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.

57
OpenAgentSkill 信任评分

GitHub 采用度

检查

39 个 GitHub Stars

Star/Fork 活跃度

检查

39 个 Star,0 个 Fork; 当前元数据中没有议题活跃度信息

近期维护

通过

距上次推送 3 天

许可证清晰度

检查

未知

积极信号

  • AI 审查已通过
  • 安装路径可用
  • 仓库证据可用
  • 近期维护的仓库
  • 安装命令未发现明显高风险模式
  • 结果闭环已就绪,但需要首次真实 Agent 运行

安装前审查

  • Repository license is unknown; no LICENSE file or license declaration detected in the skill. This creates legal ambiguity for reuse.
  • This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.
  • 许可证不清晰
  • Low GitHub adoption signal
  • Quality score needs review
  • Permission surface needs review: shell or command execution, filesystem or document access
  • GitHub adoption: 39 GitHub stars
  • Stars/forks activity: 39 stars, 0 forks; issue activity unavailable in current metadata
  • License clarity: Unknown
  • Permission surface: shell or command execution, filesystem or document access
  • 暂未有真实 Agent 结果报告
  • 无人值守安装前需要人工审查

建议操作

Choose a stronger alternative or inspect the source manually before any install attempt.

质量档案

有潜力 适用于 Agent 工作流的候选

有用的候选项,但采用前应与替代方案比较。

57
GitHub Stars
39
新鲜度
3 天前
安装就绪
许可证
未知
安装前审查: Low GitHub adoption signal · Repository license is unknown; no LICENSE file or license declaration detected in the skill. This creates legal ambiguity for reuse.

工作流匹配

在这些场景使用此 Skill

工作流匹配

加入完整工作流

替代方案短名单

安装前对比

可能适合该任务的相近 Skill。

对比全部

概览

--- name: presentation description: Use when the user wants to create presentation slides, a slide deck, a technical talk, or a conference talk for a topic or library — built on Slidev. Interviews the user, deep-researches and code-grounds the topic FIRST, applies presentation-craft best practices, generates a Slidev deck, self-verifies it in a headless browser, and ends with the dev server running and the deck open in the browser with zero manual steps. Triggers on "make a presentation", "make slides", "build a deck", "presentation about X", "technical talk", "conference talk", "slidev deck", "build slides for X", "present <library>". ---

# presentation — technical slide decks that don't suck

A **director** layer on top of Slidev. This skill owns the **what** (researched, grounded content) and the **how-well** (presentation craft). It **delegates Slidev syntax mechanics** to the official `slidev` skill — it depends on that skill and never duplicates its syntax reference.

You are not "filling a template." You are interviewing a speaker, researching their topic until you actually understand it, and engineering a deck that an audience will follow and remember.

## When to use

- The user wants to build/create a presentation, slide deck, or talk. - "Make slides / a deck / a presentation about X", "technical talk", "conference talk", "build slides for <library>", "present <topic>". - Revising/extending an existing Slidev deck (revision mode).

## When to skip

- The user only wants raw Slidev *syntax* help → use the `slidev` skill directly. - A one-off non-deck answer (a definition, a snippet) → just answer.

## Dependency: the official `slidev` skill

This skill produces Slidev markup but does **not** carry Slidev's syntax reference. Before generating any `slides.md`:

1. Ensure the official skill is available. If not, install it: `npx skills add slidevjs/slidev` 2. For **any** syntax question (layouts, magic-move, click animations, components, export flags), consult the `slidev` skill / its reference files, or `https://sli.dev/llms.txt` as a fallback. Do not hand-roll syntax you can look up — getting it wrong breaks rendering.

`references/slidev-cheatsheet.md` carries only the **generator gotchas** and the delegation pointers — the things that bite an automated author. It is not a syntax copy.

## Non-negotiables (read before working)

These are what the user is paying for. Do not skip them because a deck "looks fine."

1. **Research + ground BEFORE the interview.** The moment you have a topic, run Gate 1 (`references/research-grounding.md`). Never build slides from model memory. 2. **Build from the brief, not from memory.** Every factual claim on a slide traces to the research/grounding brief. 3. **Flag weak claims; don't assert them.** If something is commonly repeated but poorly supported, skip it or caveat it. Never present a myth as fact. 4. **Assertion-evidence + lean text.** Slide titles are complete-sentence claims; the body is visual evidence, not a bullet dump. Keep on-slide text to a glance — aim ≤ ~20 words of body per slide; full sentences and detail belong in the speaker notes, not on the slide. (`references/presentation-craft.md` "Text budget") 5. **One idea per slide; ~1–2 min/slide.** Split rather than cram. 6. **Fill the canvas.** Every slide uses all available space with balanced proportions — never top-anchor content above a dead band, and never float a small element in a big empty region. Center/distribute the content group and size visuals to fill their region; distribute whitespace, don't dump it. (`references/presentation-craft.md`; concrete Slidev recipe in `references/slidev-cheatsheet.md`) 7. **Code discipline.** ≤5–7 lines visible at once, large, progressive reveal, dim irrelevant lines; prefer a diagram over a wall of code. (`references/technical-craft.md`) 8. **Generate every legitimately generatable asset** (code images, diagrams, charts). **Placeholder only the un-generatable** (real photos, product screenshots, demo videos) with a specific swap instruction. **Never fabricate evidence** — no fake screenshots, invented data, or hotlinked images. (`references/assets.md`) 9. **Storyboard approval before writing slides** (Gate 2). 10. **Self-verify before handing over** (Gate 3, `references/verification.md`). 11. **Finish live, zero manual steps.** End with the dev server running in the background and the deck open at `http://localhost:3030`. The user never runs a command.

## Workflow

``` Step 0 Detect topic (and whether it's a specific library/tool) Gate 1 Research & Ground → references/research-grounding.md (BEFORE interview) Step 2 Interview → references/interview.md (adaptive, one Q at a time) Step 3 Deeper ground → only if internals/architecture-focused or long-form Gate 2 Storyboard approval → per-slide plan; user approves before any slides.md Step 5 Scaffold + theme → pnpm create slidev; visual theme selection in browser Step 6 Generate slides.md → craft refs + slidev skill + assets.md; respect gotchas Gate 3 Self-verify loop → references/verification.md (screenshot → fix → repeat) Step 8 Finish live → bg dev server + open browser; then offer export ```

### Step 0 — Detect Identify the topic. Decide whether it is *also* a specific library/tool (repo path / GitHub URL / package name / docs URL / names a concrete library / user is in a code repo) — this turns on Gate 1 Track B in addition to Track A.

### Gate 1 — Research & Ground (FIRST, before talking) Load `references/research-grounding.md`. Run **Track A (topic research, always)** and, when applicable, **Track B (code grounding)**. Light pass now (enough for a smart interview); deeper pass later if the talk warrants. Produce the **research + grounding brief**.

### Step 2 — Interview Load `references/interview.md`. Ask the canonical questions adaptively, one at a time, skipping anything the brief already answers.

### Step 3 — Deeper grounding (conditional) If the chosen areas are internals/architecture-focused or the talk is long-form, deepen the brief at the per-area depth the user set.

### Gate 2 — Storyboard approval Present a per-slide storyboard: assertion title · content/asset · layout · speaker-note intent · place in the narrative arc · running time budget vs stated duration. Get approval/edits before writing any `slides.md`.

### Step 5 — Scaffold + visual theme selection Scaffold the Slidev project at the user's output location. Select a theme **visually in the browser** — show 2–4 themes matching brand/tone (gallery previews or a quick render); user picks. Then apply brand colors/fonts/logo. See the branding-mode routing in `references/interview.md`.

### Step 6 — Generate `slides.md` Apply the craft layer (`presentation-craft.md` + `technical-craft.md`). Consult the `slidev` skill for all syntax. Produce/insert assets per `references/assets.md`. Respect the gotchas in `references/slidev-cheatsheet.md`.

### Gate 3 — Self-verify loop Load `references/verification.md`. Screenshot every slide in a headless browser, detect overflow / clipped code / contrast / empty / overstuffed, fix, re-check until clean.

### Step 8 — Finish live Leave the dev server running in the background and open the deck in the browser. Then offer the export targets the user chose (PDF/PPTX/SPA).

### Revision mode Pointed at an existing Slidev project, skip scaffolding and extend / restyle / tighten using the same craft layer + self-verify loop.

## Reference files

| File | Load when | |------|-----------| | `references/research-grounding.md` | Gate 1 — researching + grounding the topic | | `references/interview.md` | Step 2 — running the interview; branding routing; slide-count math | | `references/presentation-craft.md` | Step 6 — general craft rules + myth-flags | | `references/technical-craft.md` | Step 6 — code/diagrams/demos/audience for technical talks | | `references/slidev-cheatsheet.md` | Steps 5–6 — generator gotchas + delegation to the `slidev` skill | | `references/assets.md` | Step 6 — generating assets + placeholder convention | | `references/verification.md` | Gate 3 — self-verify checks + auto-fix loop |

## Asset helper

`assets/render-asset.mjs` renders standalone code (Shiki) and diagram (Mermaid) PNGs into a deck's `public/`. Usage in `references/assets.md`. Install once with `npm --prefix <skill>/assets install` and `npx playwright install chromium`.

技术详情

版本
1.0.0
许可证
Unknown
最近更新
2026年8月19日
发布时间
2026年8月19日

决策摘要

备选候选

58
就绪
原型验证
阶段

仓库近期活跃

审计

安装审查

安装与采用审查

71
高风险
安全性
70/100
维护状态
100/100
安装
92/100
打开完整审计查看评估报告

Agent 验证证据

Agent 验证证据

来自解析、审查、安装和一次小范围运行后的结果报告。

0
已验证
Needs first agent run自动安装: 先审查最近: 未知
成功率
近期失败
结果
0
输出质量
失败
0
不相关
0
安装次数
0
风险拦截
0
需要配置
0
生产环境
0

暂时没有 Agent 结果数据。首次 Agent 执行可以通过 /api/agent/outcome 报告成功、需要设置、风险拦截、失败或不相关。

安装

加入 Agent 工作流

免费且开源. 在生产 Agent 中安装前请先审查报告。

增长闭环

分享工具包

X

为 presentation 准备的场景化草稿,可手动发布到 X。

策展说明
A practical pick for the next deck:

presentation: Use when the user wants to create presentation slides, a slide deck, a technical talk, or a conference talk for a topic or...

39 stars

https://www.openagentskill.com/skills/alemtuzlak-presentation?ref=x
打开 X 草稿
可选:带安装命令的回复
Listing + install path for presentation:
https://www.openagentskill.com/skills/alemtuzlak-presentation?ref=x

Install: npx skills add AlemTuzlak/skills --skill presentation
打开回复草稿

收录来源

Registry 收录

可认领

此列表来自公开来源,维护者认领获批前不会标记为官方。

创作者
AlemTuzlak
收录方
OpenAgentSkill 社区索引

归属链接指向公开仓库或创作者主页。创作者可认领列表以更新所有权信号。

认领此 Skill

所有者认领

认领此 Skill 页面

这条 Registry 收录 列表归属于 AlemTuzlak,但尚未标记为官方。认领后可增加已验证所有者信号,使后续发布、安装和审计更新更值得信赖。

创作者外链工具包

将证据徽章加入你的 README

在开发者评估仓库的位置展示规范页面、当前信任与审计信号,以及真实的 Agent 验证证据。

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/alemtuzlak-presentation?metric=listed&label=Listed)](https://www.openagentskill.com/skills/alemtuzlak-presentation)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/alemtuzlak-presentation?metric=trust&label=Trust)](https://www.openagentskill.com/skills/alemtuzlak-presentation)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/alemtuzlak-presentation?metric=audit&label=Audit)](https://www.openagentskill.com/skills/alemtuzlak-presentation/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/alemtuzlak-presentation?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/alemtuzlak-presentation)

作者

A

AlemTuzlak

@alemtuzlak

健康信号

GitHub Stars
39
质量评分
34/100
最近 GitHub 推送
2026年8月19日
框架提示
未知
OpenAgentSkill 浏览量
5
复制安装命令
0
跳转点击
0

社区信号

告诉我们这个 Skill 是否对你的 Agent 工作流有帮助。汇总反馈会持续改善排序。

信任与安全

Do not auto-install

57
  • GitHub 采用度39 个 GitHub Stars检查
  • Star/Fork 活跃度39 个 Star,0 个 Fork; 当前元数据中没有议题活跃度信息检查
  • 近期维护距上次推送 3 天通过
  • 许可证清晰度未知检查
  • README/SKILL.md 完整度元数据包含足够的用法与工作流上下文通过
  • 依赖与运行时风险network or browser surface通过