Token导航 LogoToken导航

Agent Skill · 研究检索

conference-talk-builder(会议演讲构建者)

conference-talk-builder 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

conference-talk-builder 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证为 MIT,第三方扫描已通过,按安装量在研究检索类的 73,674 个 Skill 里排第 55,255。

总安装 489周安装 21GitHub Stars 79下载 171核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:conference-talk-builder(会议演讲构建者)
来源仓库:https://github.com/nicknisi/claude-plugins
仓库路径:skills/conference-talk-builder
安装命令:
npx skills add https://github.com/nicknisi/claude-plugins --skill conference-talk-builder
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/nicknisi/claude-plugins --skill conference-talk-builder

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于查找、检索和筛选相关信息。适合根据关键词或任务场景快速定位候选结果。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态及是否会触发联网或文件读写。conference-talk-builder 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/conference-talk-builder

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/nicknisi/claude-plugins --skill conference-tal…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

conference-talk-builder 怎么安装?

在终端执行 npx skills add https://github.com/nicknisi/claude-plugins --skill conference-talk-builder。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

conference-talk-builder 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

conference-talk-builder 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

conference-talk-builder 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

conference-talk-builder 用的人多吗?

公开数据是累计安装 489 次,近一周安装 21 次,下载 171 次,GitHub 79 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

conference-talk-builder 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
conference-talk-builder

会议演讲构建者 · 本页

48979只读MIT通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Conference Talk Builder

Transform brain dumps, transcripts, or raw ideas into structured conference talk scripts using narrative frameworks and Nick Nisi's voice.

The output is a talk script — a narrative outline with slide-by-slide content plan, speaker notes, and timing guidance. It is deliberately tool-agnostic: feed the script into Slidev, Gamma, iA Presenter, Keynote, or whatever you use to build the actual slides.

Process

Stage 0: Entry Path

Determine how the user is starting:

From scratch — They have a topic but no material yet. Go to Stage 1.

From a brain dump — They have scattered notes, bullet points, ideas. Go to Stage 1 and use their material as the starting input.

From a transcript — They have a recording transcript, prior talk, or existing outline. Go to Stage 1-T.

From feedback — They have an existing talk script from a prior session and want to revise. Skip to Stage 4.

Stage 1: Information Gathering

Ask the user for (skip what they've already provided):

  • Talk title (working title is fine)
  • Topic — what's the talk about?
  • Target audience — conference attendees, meetup crowd, internal team, workshop participants?
  • Audience knowledge level — beginner, intermediate, expert, mixed?
  • Duration — lightning (5 min), standard (20-30 min), extended (45+ min)?
  • Main points they want to cover
  • The story — what problem are they solving, what journey did they take, what do they want the audience to walk away with?
  • Code density — is this code-heavy, concept-heavy, or balanced?
  • Constraints — specific technologies, company context, anything off-limits?
  • Brain dump — everything they know about the topic, unorganized is fine

Don't require all of this upfront. Ask for what's missing after the first pass.

Stage 1-T: Transcript Analysis

When working from existing material:

  1. Read the provided transcript or outline
  2. Extract: key themes, narrative arc (if any), main arguments, examples, audience assumptions
  3. Identify gaps — what's missing for a complete talk?
  4. Summarize what you found and ask the user to fill gaps
  5. Proceed to Stage 2 with the extracted material

Stage 2: Narrative Framework Selection

Read references/framework-guide.md for the full selection algorithm.

Quick-match shortcuts (covers ~80% of talks):

  • Personal journey / "I solved X" → Story Circle
  • Teaching a concept → The Spiral or Socratic Path
  • "Here's what went wrong" → In Medias Res or Reverse Chronology
  • Tool/approach comparison → The Rashomon or Converging Ideas
  • Vision / persuasion → The Sparkline
  • Absurd complexity → Kafkaesque Labyrinth or Catch-22
  • Recurring pain → Sisyphean Arc
  • Myth-busting → The False Start or Comedian's Set

Run the scoring algorithm from the framework guide using the user's inputs (tone, duration, audience, topic type, code density). Present the top 2 recommendations with a brief sketch of how the talk maps to each framework's structure. Let the user choose or suggest alternatives.

Once a framework is selected, read only that framework's reference file from references/frameworks/. Do not preload all twenty-two.

Stage 3: Build the Talk Script

Read references/voice-tone.md to calibrate Nick's presentation voice.

Then calibrate against recent talks:

  1. If the user has given prior talks or published slides, reference those for voice calibration
  2. Note patterns that differ from blog writing — talks are more casual, use more humor, and rely on rhythm and pacing

Structure the talk script as a markdown document with:

Header
# [Talk Title]

**Duration**: [target length]
**Audience**: [who and what level]
**Framework**: [selected framework]
**Slide count target**: [based on duration — see framework reference]

## Narrative Arc

[2-3 sentence summary of the story arc using the framework's structure]
Slide-by-slide Content Plan

For each slide:

### Slide N: [Descriptive Title]

**Framework phase**: [which step/act of the framework this maps to]
**Key visual**: [what should be on the slide — a code block, image, diagram, list, quote, or just a heading]
**On screen**: [the actual text/content the audience sees]

**Speaker notes**: [what you say while this slide is up — written in Nick's voice]

**Transition**: [how this connects to the next slide]
Appendix
## Resources

[Links, references, further reading for the closing slide]

## Timing Guide

[Rough time allocation per framework phase]

Stage 4: Refine and Iterate

After presenting the talk script:

  • Ask if the narrative arc feels right
  • Check if any sections need expansion or compression
  • Verify code examples are appropriately scoped
  • Confirm the story flows — does each transition feel natural?
  • Check pacing against duration target

Voice check: Re-read references/voice-tone.md and scan the speaker notes for:

  • Does it sound conversational, not scripted?
  • Is there vulnerability where appropriate?
  • Are there specific details (tool names, numbers, real examples)?
  • Is humor self-aware, not forced?
  • Would Nick actually say this on stage?

Iterate based on feedback. The talk script is the deliverable — the user takes it to their slide tool of choice.

Key Principles

Tell a Story: You don't need to be an expert. Focus on how you approached a problem and solved it. The journey is more interesting than the destination.

One Idea Per Slide: Each slide earns its place by advancing exactly one concept. If you need a bullet list longer than 3-4 items, split across slides.

Show, Don't Tell: Code examples, diagrams, screenshots, and demos are more memorable than bullet points. But break complex code across multiple slides.

Pacing Matters: Vary the rhythm. Dense technical slides need breathing room — follow them with a simple visual or a moment of humor. Speaker notes should indicate pace changes.

Make Follow-up Easy: End with a memorable URL, QR code, or handle linking to slides and resources.

Engage the Audience: Use questions. Make eye contact. The speaker notes should include audience interaction cues where appropriate.

Bundled Resources

References

  • references/voice-tone.md — Nick's voice and tone guide. Read this to calibrate speaker notes and talk style.
  • references/framework-guide.md — Framework selection algorithm with scoring matrix. Read this in Stage 2.

Narrative frameworks (read only the selected one — do not preload all twenty-two):

Foundational:

  • references/frameworks/three-act.md — Setup, confrontation, resolution in three clean beats
  • references/frameworks/freytags-pyramid.md — Five-phase arc with rising action, climax, and falling action
  • references/frameworks/story-circle.md — Eight-step hero's journey for personal transformation arcs
  • references/frameworks/kishotenketsu.md — Four-act twist without conflict — recontextualize, don't confront

Existential:

  • references/frameworks/sisyphean-arc.md — Recurring struggle reframed as meaningful through persistence
  • references/frameworks/kafkaesque-labyrinth.md — Navigating absurd bureaucratic or systemic complexity
  • references/frameworks/existential-awakening.md — Radical freedom and the weight of choosing your tools
  • references/frameworks/strangers-report.md — Detached observational analysis of a system's contradictions

Absurdist:

  • references/frameworks/the-waiting.md — Meaning found in the space where nothing happens
  • references/frameworks/the-metamorphosis.md — Waking up to discover everything has fundamentally changed
  • references/frameworks/catch-22.md — Circular logic and no-win constraints in systems
  • references/frameworks/comedians-set.md — Setup-punchline rhythm with callbacks and escalating bits

Non-linear:

  • references/frameworks/in-medias-res.md — Open mid-action, then rewind to explain
  • references/frameworks/the-spiral.md — Revisit the same concept at increasing depth each pass
  • references/frameworks/the-rashomon.md — Same event from multiple perspectives
  • references/frameworks/reverse-chronology.md — Start with the outcome and work backward

Rhetorical:

  • references/frameworks/the-sparkline.md — Alternate between "what is" and "what could be"
  • references/frameworks/nested-loops.md — Layer stories inside stories, resolve in reverse order
  • references/frameworks/the-petal.md — Multiple independent stories supporting one central thesis
  • references/frameworks/converging-ideas.md — Separate threads that merge into a single conclusion
  • references/frameworks/the-false-start.md — Begin with conventional approach, reveal why it fails
  • references/frameworks/socratic-path.md — Drive through questions the audience is already asking

Example Workflow

User: "I want to create a talk about how we migrated our monolith to TypeScript"

  1. Stage 0: Brain dump — they have experience but no structure. Go to Stage 1.
  2. Stage 1: Gather details — audience is conference (intermediate), 30 min, code-heavy, story of a migration journey.
  3. Stage 2: Run framework scoring. Top picks: Story Circle (journey/transformation, high code affinity) and The Spiral (can revisit migration patterns at increasing depth). User picks Story Circle.
  4. Stage 3: Read references/frameworks/story-circle.md and references/voice-tone.md. Map the migration to the 8 steps:

- You: Current JS monolith, team shipping features - Need: Type safety issues causing production bugs - Go: Research TypeScript, propose migration - Search: Pilot conversion on one module, learn the hard way - Find: Incremental migration strategy with strict mode - Take: Third-party library types, team resistance - Return: Full codebase migration complete - Change: 40% fewer runtime errors, team converts to TS advocates

  1. Generate slide-by-slide talk script (~25-30 slides) with speaker notes in Nick's voice.
  2. Stage 4: Iterate — user says the "Search" section is too long, compress. Add a humor beat after the "Take" section. Done.

The user then takes this script to Slidev, Gamma, or whatever tool they prefer.

平台分布

Claude Code

26.74%
按下载量换算46

Codex

22.63%
按下载量换算39

trae

18.49%
按下载量换算32

Antigravity

11.6%
按下载量换算20

windsurf

6.66%
按下载量换算11

Gemini CLI

3.51%
按下载量换算6

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

继续浏览同类 Skills