Back to Details

talk-pipeline

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Talk Pipeline Orchestrator

演讲流程编排器

Orchestrates the complete talk preparation pipeline — from raw material to revision sheets. Can run the full pipeline or a single isolated stage.
编排完整的演讲准备流程——从原始素材到修订表。可运行完整流程或单个独立阶段。

Modes

模式

  • --rex
    : REX talk with git/code proof (changelog, commits, measured metrics)
  • --concept
    : Conceptual talk from article, ideas, notes (skips Stage 2)
  • --rex
    : 带有Git/代码佐证的REX演讲（变更日志、提交记录、可衡量指标）
  • --concept
    : 基于文章、想法、笔记的概念性演讲（跳过第2阶段）

Usage

使用方法

/talk-pipeline                          # full pipeline, asks for context
/talk-pipeline --stage=extract          # run a single isolated stage
/talk-pipeline --rex                    # REX mode (git archaeology included)
/talk-pipeline --concept                # Concept mode (skip research)
/talk-pipeline --rex --slug=my-talk --event="Conf 2026" --date=2026-06-15 --duration=30
/talk-pipeline                          # 完整流程，将询问上下文信息
/talk-pipeline --stage=extract          # 运行单个独立阶段
/talk-pipeline --rex                    # REX模式（包含Git溯源分析）
/talk-pipeline --concept                # 概念模式（跳过调研阶段）
/talk-pipeline --rex --slug=my-talk --event="Conf 2026" --date=2026-06-15 --duration=30

Context Collection

上下文收集

Ask with AskUserQuestion if not provided:
- slug         : kebab-case identifier (e.g., my-talk-topic)
- event        : event name (e.g., Conf 2026, Tech Meetup)
- date         : talk date (YYYY-MM-DD)
- duration     : duration in minutes (e.g., 30)
- audience     : audience profile (e.g., senior devs, tech leads, non-tech)
- type         : --rex or --concept
- source_path  : path to source material (article .mdx, transcript .md, notes)
- repo_path    : (REX only) path to git repository for archaeology
若未提供，将通过AskUserQuestion询问：
- slug         : 短横线命名的标识符（例如：my-talk-topic）
- event        : 活动名称（例如：Conf 2026、技术Meetup）
- date         : 演讲日期（YYYY-MM-DD）
- duration     : 演讲时长（分钟，例如：30）
- audience     : 受众画像（例如：资深开发者、技术负责人、非技术人员）
- type         : --rex 或 --concept
- source_path  : 原始素材路径（文章.mdx、文字记录.md、笔记）
- repo_path    : （仅REX模式）用于溯源分析的Git仓库路径

Workflow

工作流程

  1. Collect context — AskUserQuestion for required metadata
  2. Route by mode — 
    --rex
    vs 
    --concept
    (skip Stage 2 if concept)
  3. Run Stage 1 — 
    /talk-stage1-extract
    — always first
  4. Run Stages 2-4 in parallel (after Stage 1 confirmed)
    • REX: extract → research + concepts + position (in parallel)
    • Concept: extract → concepts + position (in parallel, skip research)
  5. CHECKPOINT — wait for angle + title choice (Stage 4 output)
  6. Run Stage 5 — 
    /talk-stage5-script
    with validated choice
  7. Run Stage 6 — 
    /talk-stage6-revision
  8. Final summary — list all generated files with their paths
  1. 收集上下文 —— 询问用户获取必要的元数据
  2. 按模式路由 —— 
    --rex
    与 
    --concept
    模式（概念模式跳过第2阶段）
  3. 运行第1阶段 —— 
    /talk-stage1-extract
    —— 始终作为首个阶段
  4. 并行运行第2-4阶段（第1阶段完成确认后）
    • REX模式：提取 → 调研 + 概念梳理 + 定位（并行执行）
    • 概念模式：提取 → 概念梳理 + 定位（并行执行，跳过调研）
  5. 检查点 —— 等待用户选择演讲角度与标题（第4阶段输出）
  6. 运行第5阶段 —— 使用用户确认的选择调用 
    /talk-stage5-script
  7. 运行第6阶段 —— 
    /talk-stage6-revision
  8. 最终摘要 —— 列出所有生成文件及其路径

Dependency Graph

依赖关系图

         extract (Stage 1)
               |
    ┌──────────┼──────────┐
    v          v          v
research    concepts   position
(Stage 2)   (Stage 3)  (Stage 4)
[--rex only]            [CHECKPOINT]
    |          |          |
    └──────────┼──────────┘
               v
          script (Stage 5)
               |
               v
         revision (Stage 6)
         extract (Stage 1)
               |
    ┌──────────┼──────────┐
    v          v          v
research    concepts   position
(Stage 2)   (Stage 3)  (Stage 4)
[--rex only]            [CHECKPOINT]
    |          |          |
    └──────────┼──────────┘
               v
          script (Stage 5)
               |
               v
         revision (Stage 6)

Stage Routing (--stage=X)

阶段路由（--stage=X）

If 
--stage
is provided, run only the corresponding skill:
StageSkill to invoke
extract/talk-stage1-extract
research/talk-stage2-research
concepts/talk-stage3-concepts
position/talk-stage4-position
script/talk-stage5-script
revision/talk-stage6-revision
若提供
--stage
参数，仅运行对应的技能：
阶段调用的技能
extract/talk-stage1-extract
research/talk-stage2-research
concepts/talk-stage3-concepts
position/talk-stage4-position
script/talk-stage5-script
revision/talk-stage6-revision

Output Naming Convention

输出命名规范

talks/{YYYY}-{slug}-summary.md           # extract
talks/{YYYY}-{slug}-git-archaeology.md   # research
talks/{YYYY}-{slug}-changelog-analysis.md
talks/{YYYY}-{slug}-timeline.md
talks/{YYYY}-{slug}-concepts.md          # concepts
talks/{YYYY}-{slug}-concepts-enriched.md
talks/{YYYY}-{slug}-angles.md            # position
talks/{YYYY}-{slug}-titre.md
talks/{YYYY}-{slug}-descriptions.md
talks/{YYYY}-{slug}-feedback-draft.md
talks/{YYYY}-{slug}-pitch.md             # script
talks/{YYYY}-{slug}-slides.md
talks/{YYYY}-{slug}-kimi-prompt.md
talks/{YYYY}-{slug}-revision-sheets.md   # revision
talks/{YYYY}-{slug}-summary.md           # 提取阶段输出
talks/{YYYY}-{slug}-git-archaeology.md   # 调研阶段输出
talks/{YYYY}-{slug}-changelog-analysis.md
talks/{YYYY}-{slug}-timeline.md
talks/{YYYY}-{slug}-concepts.md          # 概念梳理阶段输出
talks/{YYYY}-{slug}-concepts-enriched.md
talks/{YYYY}-{slug}-angles.md            # 定位阶段输出
talks/{YYYY}-{slug}-titre.md
talks/{YYYY}-{slug}-descriptions.md
talks/{YYYY}-{slug}-feedback-draft.md
talks/{YYYY}-{slug}-pitch.md             # 脚本阶段输出
talks/{YYYY}-{slug}-slides.md
talks/{YYYY}-{slug}-kimi-prompt.md
talks/{YYYY}-{slug}-revision-sheets.md   # 修订阶段输出

Final Summary Format

最终摘要格式

After Stage 6 completes, display:
Pipeline complete. Files generated:

Stage 1 — Extract:
  ✓ talks/{YYYY}-{slug}-summary.md

Stage 2 — Research (REX only):
  ✓ talks/{YYYY}-{slug}-git-archaeology.md
  ✓ talks/{YYYY}-{slug}-changelog-analysis.md
  ✓ talks/{YYYY}-{slug}-timeline.md

Stage 3 — Concepts:
  ✓ talks/{YYYY}-{slug}-concepts.md
  ✓ talks/{YYYY}-{slug}-concepts-enriched.md (if repo available)

Stage 4 — Position:
  ✓ talks/{YYYY}-{slug}-angles.md
  ✓ talks/{YYYY}-{slug}-titre.md
  ✓ talks/{YYYY}-{slug}-descriptions.md
  ✓ talks/{YYYY}-{slug}-feedback-draft.md

Stage 5 — Script:
  ✓ talks/{YYYY}-{slug}-pitch.md
  ✓ talks/{YYYY}-{slug}-slides.md
  ✓ talks/{YYYY}-{slug}-kimi-prompt.md   ← copy-paste into kimi.com

Stage 6 — Revision:
  ✓ talks/{YYYY}-{slug}-revision-sheets.md

Next step: open kimi-prompt.md, verify no {PLACEHOLDER} remains, paste into kimi.com.
第6阶段完成后，显示以下内容：
流程执行完成。已生成文件：

Stage 1 — 提取:
  ✓ talks/{YYYY}-{slug}-summary.md

Stage 2 — 调研（仅REX模式）:
  ✓ talks/{YYYY}-{slug}-git-archaeology.md
  ✓ talks/{YYYY}-{slug}-changelog-analysis.md
  ✓ talks/{YYYY}-{slug}-timeline.md

Stage 3 — 概念梳理:
  ✓ talks/{YYYY}-{slug}-concepts.md
  ✓ talks/{YYYY}-{slug}-concepts-enriched.md（若仓库可用）

Stage 4 — 定位:
  ✓ talks/{YYYY}-{slug}-angles.md
  ✓ talks/{YYYY}-{slug}-titre.md
  ✓ talks/{YYYY}-{slug}-descriptions.md
  ✓ talks/{YYYY}-{slug}-feedback-draft.md

Stage 5 — 脚本:
  ✓ talks/{YYYY}-{slug}-pitch.md
  ✓ talks/{YYYY}-{slug}-slides.md
  ✓ talks/{YYYY}-{slug}-kimi-prompt.md   ← 复制粘贴至kimi.com

Stage 6 — 修订:
  ✓ talks/{YYYY}-{slug}-revision-sheets.md

下一步：打开kimi-prompt.md，确认无{PLACEHOLDER}占位符残留，然后粘贴至kimi.com。

Anti-patterns

反模式

  • Do not run Stage 5 without an explicit angle + title choice from the user
  • Do not run Stage 2 (research) in 
    --concept
    mode
  • Do not proceed to the next stage if an upstream stage failed
  • Do not invent metrics or dates not present in the source material
  • 未获得用户明确的演讲角度与标题选择时，不得运行第5阶段
  • 在
    --concept
    模式下不得运行第2阶段（调研）
  • 若上游阶段执行失败，不得进入下一阶段
  • 不得编造原始素材中未提及的指标或日期

Validation

验证项

  • All upstream files exist before launching a downstream stage
  • Stage 4 CHECKPOINT respected before script
  • Outputs named per convention 
    talks/{YYYY}-{slug}-{stage}.md
  • No empty placeholders in generated files
  • 启动下游阶段前，确认所有上游文件已存在
  • 脚本阶段运行前，严格遵守第4阶段的检查点要求
  • 输出文件命名符合规范
    talks/{YYYY}-{slug}-{stage}.md
  • 生成的文件中无空占位符

Tips

提示

  • The orchestrator is the recommended entry point for first use
  • For repeat users who know the pipeline, running individual stage skills is faster
  • The 
    --stage=X
    flag is useful for rerunning a single stage without redoing the full pipeline
  • 对于首次使用者，推荐以编排器作为入口
  • 对于熟悉流程的老用户，直接运行单个阶段的技能速度更快
  • --stage=X
    参数适用于仅重新运行单个阶段，无需重复执行完整流程

Related

相关链接

  • Stage 1: Extract
  • Stage 2: Research
  • Stage 3: Concepts
  • Stage 4: Position
  • Stage 5: Script
  • Stage 6: Revision
  • Full workflow guide
  • 第1阶段：提取
  • 第2阶段：调研
  • 第3阶段：概念梳理
  • 第4阶段：定位
  • 第5阶段：脚本
  • 第6阶段：修订
  • 完整工作流指南