docs: support alternative edit strategies

This commit is contained in:
2026-07-14 18:08:28 +08:00
parent 4181323184
commit 01786e5732
2 changed files with 32 additions and 13 deletions
+13 -1
View File
@@ -68,6 +68,8 @@ Ask the user for:
Before transcribing, ask the user what they want to do with the video. User requirements are often vague in the first pass — that's expected. The plan is refined iteratively.
For full video-edit planning requests, ask early whether the user wants **one focused recommended cut** or **multiple alternative editing strategies**. If they want alternatives, analyze a wider set of candidate segments and present modular options the user can freely combine into their own final cut. Do not force the plan into a rigid one-path timeline where every section has only one fixed choice.
If the agent's runtime supports structured questioning (e.g., a `clarify` tool or a `grill-me` skill), use it to gather requirements systematically. Ask questions one at a time with multiple-choice options — this is much more effective than a free-text wall of questions.
**The requirements questionnaire below covers the key axes for gameplay/creator video editing.** Not every question applies to every session — pick the relevant ones based on the user's initial request. See `references/editing-requirements-questionnaire.md` for the full questionnaire with choices.
@@ -76,6 +78,7 @@ If the agent's runtime supports structured questioning (e.g., a `clarify` tool o
|---|---|
| Target platform (B站/抖音/YouTube/Shorts) | Determines aspect ratio, pacing, subtitle density, meme/热梗 density |
| Narrative style (搞笑集锦/故事线+搞笑/高光混剪) | Determines structure: pure clip reel vs. narrative arc with 起承转合 |
| Planning mode (single recommended cut / multiple alternatives) | Determines whether to produce one focused timeline or modular strategy options the user can mix and match |
| Role distribution (主视角/平权联机/主持人) | Determines whose voice/reactions to prioritize in cuts |
| Effect density (少量/中等/高密度) | Determines how many 表情包/贴纸/特效 to search for and apply |
| Editor tool (Premiere Pro/剪映/DaVinci/必剪) | Determines how specific transition/effect instructions are phrased |
@@ -322,7 +325,7 @@ For fast-paced story + comedy gameplay videos, cull hard: keep combat, danger, r
This workflow is especially effective for requests like **“find fast-paced funny + story-driven candidate segments”**. It keeps token/runtime cost low while still verifying whether a transcript-highlighted moment actually has usable on-screen action.
Output a Markdown table with overall recommendations, then let the user iterate. **Respond in the same language the user is using.** If the plan is likely to be long (large tables, detailed scripts, full requirement summaries, or multi-section recommendations), ask whether the user wants it saved as a file instead of pasted into chat. Default to Markdown (`.md`) for saved plans unless the user requests another format.
Output a Markdown table with overall recommendations, then let the user iterate. **Respond in the same language the user is using.** If the user requested multiple alternative strategies, structure the plan as modular options rather than a single rigid timeline: offer alternative openings, narrative arcs, pacing choices, candidate segments, transitions, BGM/effect directions, and optional inserts the user can mix and match. In this mode, analyze more candidate segments than strictly needed for one final cut, and clearly label tradeoffs (e.g., funniest, clearest story, fastest pacing, most emotional, best visual action). If the plan is likely to be long (large tables, detailed scripts, full requirement summaries, or multi-section recommendations), ask whether the user wants it saved as a file instead of pasted into chat. Default to Markdown (`.md`) for saved plans unless the user requests another format.
```markdown
## Edit Plan
@@ -339,6 +342,14 @@ Output a Markdown table with overall recommendations, then let the user iterate.
| 00:01:4500:02:10 | 25s | Walking, no dialogue or event | Cut | — | — |
| 00:02:1000:02:35 | 25s | Combat starts, highlight moment | Keep, slow-mo | Fade in | Sync to BGM rhythm |
| ... | ... | ... | ... | ... | ... |
### Alternative Strategy Options (if requested)
| Module | Option | Best for | Candidate segments | Tradeoffs |
| ------ | ------ | -------- | ------------------ | --------- |
| Opening | Cold open with funniest quote | Fast hook | 00:03:1000:03:24 / 00:18:4000:19:05 | Strong hook, weaker story setup |
| Story arc | Slow setup → escalation → payoff | Clear narrative | 00:01:2000:02:30 / 00:12:0000:14:10 / 00:22:3000:23:20 | Better story, slower pacing |
| Insert | Short visual gag bridge | Rhythm reset | 00:08:1000:08:16 | Optional; use only if pacing feels too dense |
```
**Completion criteria:** user receives a Markdown table addressing their stated goal, and is invited to ask follow-up questions.
@@ -442,6 +453,7 @@ This creates an isolated venv with `funasr`, `torch`, `torchaudio`. If the user
13. **Choosing command syntax or execution environment solely from where the agent runs.** Choose based on where the video file lives and where the command will execute. Windows execution → PowerShell commands and Windows paths; WSL/Linux execution → Linux shell commands and Linux paths. If the agent runs in WSL but Windows execution is chosen, use `powershell.exe` to do lightweight setup (copy files, install/check dependencies, run `uv sync`) before handing only the long transcription command to the user. Never ask Windows `uv` to run from `\\\\wsl.localhost\\...` / `\\\\wsl$\\...`.
14. **Saying you'll provide a command but not including it.** If you mention giving the user a transcription command, include it immediately in that same response. Do not move on to other content without printing the actual command. The user should never have to ask for it.
15. **Sending a wall of free-text questions.** When gathering editing requirements, use structured one-at-a-time multiple-choice questions via the runtime's clarify/prompt tool. This is far more effective than dumping 10 questions as a paragraph.
16. **Making full edit plans too rigid.** For complete planning requests, ask whether the user wants multiple alternative strategies. If yes, provide modular options and extra candidate segments that the user can combine, rather than a single fixed linear plan where every section has exactly one prescribed choice.
## Verification checklist
@@ -19,21 +19,28 @@ Determines structure: pure clip reel vs. narrative arc.
- 故事线+搞笑混搭:有一条简单主线,穿插搞笑片段,有起承转合
- 高光混剪向:以精彩操作/翻盘/团灭瞬间为主,偏燃向或反差搞笑
### 3. Role distribution
### 3. Planning mode
Determines whether to produce one focused timeline or multiple modular alternatives.
- 给我一套最推荐的完整剪辑方案,尽量直接可执行
- 给我多套可替代策略,我想根据自己的想法组合最终成片
- 先给一套主线方案,再附带一些可替换片段/开头/结尾/节奏选择
### 4. Role distribution
Determines whose voice/reactions to prioritize.
- 你是主视角/主要叙事者,其他人配合你推进进度
- 大家平权联机,谁有有趣发言/操作就突出谁,没有固定主角
- 你是主持人/吐槽担当,主要靠你的解说和反应推动节奏
### 4. Effect density
### 5. Effect density
Determines how many 表情包/贴纸/特效 to search for.
- 少量点级,自然过渡就行,不需要加额外的表情包/贴纸素材
- 中等密度,关键笑点配表情包/热梗贴纸,转场要明显但不花哨
- 高密度,每个笑点都要有视觉强化(放大镜、抖动、表情包、弹幕特效等)
### 5. Editor tool
### 6. Editor tool
Determines how specific transition/effect instructions are phrased.
- Premiere Pro
@@ -41,14 +48,14 @@ Determines how specific transition/effect instructions are phrased.
- DaVinci Resolve
- 必剪
### 6. First edit or existing draft
### 7. First edit or existing draft
Determines whether to plan from scratch or optimize existing cuts.
- 是首次剪辑,从零开始规划结构
- 我已经有个粗剪/草稿,需要你帮我优化
- 我已经做过一些片段标注,需要你帮我串联
### 7. BGM style
### 8. BGM style
Determines BGM search/recommendation direction.
- 让我根据内容自动推荐(轻松日常+搞笑节奏为主,战斗段落配燃向)
@@ -56,14 +63,14 @@ Determines BGM search/recommendation direction.
- 搞笑节奏类为主(快节奏、夸张、踩点)
- 燃向战斗类为主(打僵尸/Boss时燃起来)
### 8. Number of participants
### 9. Number of participants
Determines how to handle multi-person interaction and voice allocation.
- 2-3人(小队联机)
- 4-5人(中型队伍)
- 6-8人(满编大队伍)
### 9. Audio handling
### 10. Audio handling
Determines subtitle work, BGM vs voice balance, and narration needs.
- 保留原声,加字幕即可(观众能听到对话和反应)
@@ -71,21 +78,21 @@ Determines subtitle work, BGM vs voice balance, and narration needs.
- 需要重新配音/旁白,原声只保留精彩反应片段
- 混合:大部分加字幕保留原声,关键段落加旁白解说
### 10. Privacy
### 11. Privacy
Determines face-cam handling and any masking needs.
- 可以公开露脸/出声音,正常剪辑就行
- 不要露脸,但声音无所谓
- 需要打码/变声处理(不方便露脸或露声)
### 11. Output format
### 12. Output format
Determines deliverable detail level.
- 简单文字标注(时间戳笔记,如「00:12:30 这里很好笑」)
- 详细剪辑脚本表格(时间码、片段描述、保留原因、转场建议、素材需求)
- 可执行分镜方案(每个片段的入点出点、转场方式、素材位置、BGM时间线)
### 12. Target duration
### 13. Target duration
Determines how aggressively to cut and pace the content.
- User specifies a target (e.g., 7-8 minutes, 10 minutes, 3 minutes)
@@ -93,6 +100,6 @@ Determines how aggressively to cut and pace the content.
## Usage notes
- Ask one question at a time. The runtime's clarify tool with multiple-choice options works best.
- Not all 12 questions are needed every session. If the user's initial request already answers some axes, skip those.
- The questions can be asked in any order, but platform → narrative style → effect density → editor tool is a natural priority flow.
- Not all 13 questions are needed every session. If the user's initial request already answers some axes, skip those.
- The questions can be asked in any order, but platform → narrative style → planning mode → effect density → editor tool is a natural priority flow.
- If a `grill-me` skill is available, it can be loaded to add follow-up depth questions beyond this template.