@optima-chat/optima-agent 0.9.16 → 0.9.18
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: scout
|
|
3
|
-
description: "Interactive Amazon product research consultant with 1688 supplier sourcing and Keepa historical data. Search products, analyze markets, find suppliers (by keyword or image), track price/BSR history, and generate professional reports. ALWAYS use when user asks about: selling products (卖/开店), product ideas (产品/商品), market research (市场/竞品), suppliers (供应商/厂家), sourcing (采购/进货/货源), image search (图片找货/以图搜货/找同款), evaluating business opportunities (生意/创业), product trends (趋势/走势), price history (价格历史/价格变化), BSR ranking (排名/销量排名), product lifecycle (生命周期/增长期/衰退期). Uses 'scout search', 'scout product', 'scout keepa *', 'scout supplier-search', and 'scout supplier-search-image' commands."
|
|
3
|
+
description: "Interactive Amazon product research consultant with 1688 supplier sourcing and Keepa historical data. Search products, analyze markets, deep-dive reviews for pain points, find suppliers (by keyword or image), track price/BSR history, and generate professional reports. ALWAYS use when user asks about: selling products (卖/开店), product ideas (产品/商品), market research (市场/竞品), reviews/pain points (评论/差评/痛点/用户反馈), suppliers (供应商/厂家), sourcing (采购/进货/货源), image search (图片找货/以图搜货/找同款), evaluating business opportunities (生意/创业), product trends (趋势/走势), price history (价格历史/价格变化), BSR ranking (排名/销量排名), product lifecycle (生命周期/增长期/衰退期). Uses 'scout search', 'scout product', 'scout reviews', 'scout keepa *', 'scout supplier-search', and 'scout supplier-search-image' commands."
|
|
4
4
|
---
|
|
5
5
|
|
|
6
6
|
# Optima Scout - AI Product Research
|
|
@@ -139,7 +139,43 @@ scout product ASIN
|
|
|
139
139
|
- **Images count** - 7 is standard, fewer = poor optimization
|
|
140
140
|
- **Specifications** - May include BSR in multiple categories
|
|
141
141
|
|
|
142
|
-
### 3.
|
|
142
|
+
### 3. Get Product Reviews: `scout reviews`
|
|
143
|
+
|
|
144
|
+
Fetch Amazon product reviews with pagination. Use for deep pain-point analysis beyond the 8-13 top_reviews returned by `scout product`.
|
|
145
|
+
|
|
146
|
+
**Syntax:**
|
|
147
|
+
```bash
|
|
148
|
+
scout reviews ASIN # 默认 3 页 (~30 条)
|
|
149
|
+
scout reviews ASIN --pages 10 # 最多 10 页 (~100 条)
|
|
150
|
+
scout reviews ASIN --star one_star # 只看 1 星差评
|
|
151
|
+
scout reviews ASIN --all-stars --pages 5 # 每个星级各 5 页 (~250 条)
|
|
152
|
+
scout reviews ASIN --verified # 只看 verified purchase
|
|
153
|
+
scout reviews ASIN --sort helpful # 按 helpful 排序
|
|
154
|
+
```
|
|
155
|
+
|
|
156
|
+
**Parameters:**
|
|
157
|
+
- `ASIN`: 10-character Amazon product ID
|
|
158
|
+
- `--pages`: Number of pages per request (1-10, default: 3, ~10 reviews/page)
|
|
159
|
+
- `--sort`: `recent` (default) or `helpful`
|
|
160
|
+
- `--star`: Filter by star rating (`one_star` ~ `five_star`)
|
|
161
|
+
- `--all-stars`: Fetch all 5 star ratings in one batch (max ~500 reviews)
|
|
162
|
+
- `--verified`: Only verified purchase reviews
|
|
163
|
+
- `--domain`: Amazon domain code (default: com)
|
|
164
|
+
- `--format`: `json` (default) or `text`
|
|
165
|
+
|
|
166
|
+
**Returns:**
|
|
167
|
+
- Review list: id, title, body, rating, date, verified, helpful_votes, images
|
|
168
|
+
- Product summary: title, rating, total_ratings, rating_breakdown (percentages)
|
|
169
|
+
|
|
170
|
+
**When to use:**
|
|
171
|
+
- `scout product` gives 8-13 top_reviews — enough for quick scan
|
|
172
|
+
- `scout reviews` gives 30-500 reviews — use for **deep pain-point analysis**, sentiment clustering, and improvement opportunity identification
|
|
173
|
+
- **痛点分析**:`scout reviews ASIN --star one_star --pages 5` 拉差评做聚类
|
|
174
|
+
- **竞品评论对比**:分别拉两个竞品的差评,找差异化机会
|
|
175
|
+
|
|
176
|
+
**Cost awareness:** Each page costs ~$0.0075 Apify credits. `--all-stars --pages 10` (~500 reviews) costs ~$0.38.
|
|
177
|
+
|
|
178
|
+
### 4. Search 1688 Suppliers (Keyword): `scout supplier-search`
|
|
143
179
|
|
|
144
180
|
Search for suppliers on 1688.com using keywords.
|
|
145
181
|
|
|
@@ -165,7 +201,7 @@ scout supplier-search "KEYWORD" --limit NUMBER
|
|
|
165
201
|
- Years in business (8+ years = established)
|
|
166
202
|
- Return rate (lower = better, typical: 30-50%)
|
|
167
203
|
|
|
168
|
-
###
|
|
204
|
+
### 5. Search 1688 Suppliers (Image): `scout supplier-search-image`
|
|
169
205
|
|
|
170
206
|
Search for suppliers on 1688.com using product images - perfect for finding sources for products you see on Amazon, Shopify, or other platforms.
|
|
171
207
|
|
|
@@ -293,37 +329,40 @@ scout keepa tokens
|
|
|
293
329
|
|
|
294
330
|
**Phase 2: Deep Dive & Refinement**
|
|
295
331
|
4. **Targeted Analysis** → Based on user feedback, run `scout product` on relevant ASINs
|
|
296
|
-
5. **
|
|
297
|
-
6. **
|
|
332
|
+
5. **Deep Review Analysis** → Run `scout reviews ASIN --star one_star --pages 5` to extract pain points, then `scout reviews ASIN --sort helpful --pages 3` to see most impactful reviews
|
|
333
|
+
6. **Historical Trend Analysis** → Run `scout keepa product ASIN1,ASIN2,ASIN3 --stats 180` to get historical data
|
|
334
|
+
7. **Extract Insights** → Combine realtime + historical + review data:
|
|
298
335
|
- BSR trend → 增长期/成熟期/衰退期?
|
|
299
336
|
- `salesRankDrops30/90` → 估算月销量
|
|
300
337
|
- 价格历史 → 利润空间稳定吗?有价格战吗?
|
|
301
338
|
- 卖家数量变化 → 竞争在加剧吗?
|
|
302
|
-
|
|
339
|
+
- 差评聚类 → 用户核心痛点是什么?能改进吗?
|
|
340
|
+
- 好评亮点 → 用户最看重什么功能?
|
|
341
|
+
8. **Iterate & Explore** → User may request different keywords, specific competitor analysis, or alternative product categories
|
|
303
342
|
|
|
304
343
|
**Phase 2.5: Supplier Sourcing (Optional but Recommended)**
|
|
305
|
-
|
|
344
|
+
9. **Trigger**: User shows interest in costs/sourcing, or after market validation
|
|
306
345
|
- "成本大概多少?" "批发价怎么样?" "利润空间大吗?"
|
|
307
346
|
- "哪里进货?" "供应商怎么找?"
|
|
308
347
|
- "这个图片能找到货源吗?" "Amazon这个能在1688找到吗?"
|
|
309
348
|
|
|
310
|
-
|
|
349
|
+
10. **Choose search method**:
|
|
311
350
|
- **With image**: `scout supplier-search-image "https://..."` ← More accurate for visual products
|
|
312
351
|
- **With keyword**: `scout supplier-search "产品关键词"`
|
|
313
352
|
- **Best practice**: Try both and compare results
|
|
314
353
|
|
|
315
|
-
|
|
354
|
+
11. **Share Findings**:
|
|
316
355
|
- Wholesale price range (e.g., ¥429-599)
|
|
317
356
|
- MOQ (minimum order quantity)
|
|
318
357
|
- Profit margin calculation: Amazon price ($60-80) - 1688 cost (¥429 ≈ $60) - shipping ($10-15)
|
|
319
358
|
- Supplier quality indicators (years in business, certifications)
|
|
320
359
|
|
|
321
|
-
|
|
360
|
+
12. **Ask**: "要不要我详细分析几个供应商?" or proceed to report
|
|
322
361
|
|
|
323
362
|
**Phase 3: Report Generation (Proactive Suggestion)**
|
|
324
|
-
|
|
325
|
-
|
|
326
|
-
|
|
363
|
+
13. **Gauge Completion** → After sufficient data, suggest: "要不要我整理成一份完整的市场分析报告?"
|
|
364
|
+
14. **Generate Report** → Create comprehensive markdown report with all findings
|
|
365
|
+
15. **Save & Iterate** → Offer to save report and refine based on feedback
|
|
327
366
|
|
|
328
367
|
---
|
|
329
368
|
|
|
@@ -332,9 +371,10 @@ scout keepa tokens
|
|
|
332
371
|
When user explicitly requests a report upfront:
|
|
333
372
|
1. Run 3-4 diverse keyword searches
|
|
334
373
|
2. Analyze top 3-5 products with `scout product`
|
|
335
|
-
3.
|
|
336
|
-
4.
|
|
337
|
-
5.
|
|
374
|
+
3. Deep review analysis: `scout reviews ASIN --star one_star --pages 5` on top competitors
|
|
375
|
+
4. Pull historical trends with `scout keepa product` (batch ASINs)
|
|
376
|
+
5. Search 1688 suppliers (image + keyword)
|
|
377
|
+
6. Generate comprehensive report directly
|
|
338
378
|
|
|
339
379
|
### Multi-Keyword Research Strategy
|
|
340
380
|
|
|
@@ -420,10 +460,10 @@ scout product B0788F3R8X
|
|
|
420
460
|
- Product description completeness
|
|
421
461
|
- A+ content presence
|
|
422
462
|
- ✅ **User Feedback Deep-Dive**
|
|
423
|
-
-
|
|
424
|
-
-
|
|
425
|
-
-
|
|
426
|
-
-
|
|
463
|
+
- Quick scan: `scout product` top_reviews (8-13 条精选)
|
|
464
|
+
- Deep dive: `scout reviews ASIN --star one_star --pages 5` (差评痛点聚类)
|
|
465
|
+
- Top 3 positive mentions and top 3 complaints
|
|
466
|
+
- Improvement opportunities and common feature requests
|
|
427
467
|
- ✅ **Competitive Advantages**
|
|
428
468
|
- Unique selling points in feature_bullets
|
|
429
469
|
- Price positioning vs. competitors
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: video-edit
|
|
3
|
-
description: "
|
|
3
|
+
description: "剪辑用户【已有的】口播视频——你直接重写成片应该说什么的脚本,系统用文本对齐回原始音频时间戳。
|
|
4
4
|
|
|
5
5
|
必备前提:用户已经有视频文件(拍好的、上传的、或给出文件路径)。
|
|
6
6
|
|
|
@@ -8,13 +8,13 @@ description: "剪辑用户【已有的】口播视频——去除卡顿停顿、
|
|
|
8
8
|
'剪辑'/'剪短点'/'加字幕'/'cut'/'edit'/'trim'/'让视频更紧凑'。"
|
|
9
9
|
---
|
|
10
10
|
|
|
11
|
-
# Video-Edit Skill —
|
|
11
|
+
# Video-Edit Skill — Descript 模式:你写脚本,系统对齐
|
|
12
12
|
|
|
13
13
|
用户给原始视频,你交付剪好的成片。
|
|
14
14
|
|
|
15
15
|
## 用户怎么说,你交付什么
|
|
16
16
|
|
|
17
|
-
|
|
17
|
+
**默认所有剪辑都带字幕**——中文短视频 99% 需要字幕,"剪一下"的潜台词就是"给我能直接发的成片"。
|
|
18
18
|
|
|
19
19
|
| 用户说 | 你交付 |
|
|
20
20
|
|---|---|
|
|
@@ -26,65 +26,70 @@ description: "剪辑用户【已有的】口播视频——去除卡顿停顿、
|
|
|
26
26
|
只有当用户提到平台但**没说目标时长**时(如"剪成 TikTok"无时长),才追问"目标多长?"。
|
|
27
27
|
其他情况**直接动手**,不要废话。
|
|
28
28
|
|
|
29
|
-
##
|
|
29
|
+
## 核心原则:你直接写最终脚本
|
|
30
30
|
|
|
31
|
-
|
|
32
|
-
-
|
|
33
|
-
-
|
|
34
|
-
- 口头禅("嗯"/"啊"/"那个"/"就是")
|
|
35
|
-
- 跑题片段(语法完整但内容废)
|
|
31
|
+
剪辑工具有两种模式:
|
|
32
|
+
- **旧模式(`cut`)**:在 proposal 里给短语标 `#` 删除——只能删整段
|
|
33
|
+
- **新模式(`smart-cut`)✅ 默认用这个**:你直接写"成片应该说什么",系统找原始音频里对应的位置剪出来
|
|
36
34
|
|
|
37
|
-
|
|
35
|
+
新模式的杀手锏是:你**不受短语边界限制**,可以:
|
|
36
|
+
- 跳过填充词("嗯"/"那个")
|
|
37
|
+
- NG 重拍中只保留你认为最好那遍
|
|
38
|
+
- 把同一句话的不同片段拼起来
|
|
39
|
+
- 保留某句的前半 + 另一句的后半
|
|
40
|
+
|
|
41
|
+
**约束**:
|
|
42
|
+
- 不能凭空造内容——脚本里的字必须出自原始转写,否则匹配不上
|
|
43
|
+
- 不能调换顺序——内容按原片时间顺序保留
|
|
44
|
+
- 字面错别字会"匹不上"被丢——必须用转写文本里的原字(whisper 怎么识的就怎么写)
|
|
38
45
|
|
|
39
46
|
## 你的内部流程
|
|
40
47
|
|
|
41
48
|
### 默认剪辑(剪 + 字幕,最常见)
|
|
42
49
|
|
|
43
|
-
四步走:
|
|
44
|
-
|
|
45
50
|
```bash
|
|
46
51
|
video-edit analyze <video>
|
|
47
52
|
```
|
|
48
53
|
|
|
49
|
-
读 `<video>.work/cut_proposal.md
|
|
54
|
+
读 `<video>.work/cut_proposal.md` 了解原片内容(每行是个短语单元,带时间戳和文本)。
|
|
55
|
+
|
|
56
|
+
然后基于这些短语,**自己写一份最终脚本**到 `<video>.work/final_script.txt`:
|
|
57
|
+
|
|
58
|
+
```
|
|
59
|
+
(最终成片应该说的话,纯文本,不用时间戳)
|
|
60
|
+
(可以是几段,用换行分隔)
|
|
61
|
+
```
|
|
50
62
|
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
|
|
56
|
-
|
|
57
|
-
- **留**:所有有信息量的句子
|
|
63
|
+
写脚本时的判断:
|
|
64
|
+
- 原片每个 phrase,问自己"这句话进成片吗"——进就把内容(用 proposal 里的原文)写进脚本
|
|
65
|
+
- 同一意思被讲多遍(NG 重拍)——只写一遍,挑最流畅那遍的措辞
|
|
66
|
+
- 填充词/单字口头禅/跑题——直接不写
|
|
67
|
+
- 整段废话/犹豫——直接不写
|
|
68
|
+
- **必须用原文措辞**,不要润色或改写——否则匹配不上
|
|
58
69
|
|
|
59
|
-
|
|
70
|
+
写完后:
|
|
60
71
|
|
|
61
72
|
```bash
|
|
62
|
-
video-edit cut <video>
|
|
73
|
+
video-edit smart-cut <video>
|
|
63
74
|
video-edit subtitle <video>
|
|
64
75
|
```
|
|
65
76
|
|
|
66
|
-
`cut`
|
|
77
|
+
`smart-cut` 用 difflib 把脚本对齐回原始 word 时间戳,自动剪掉所有未匹中的部分。
|
|
78
|
+
`subtitle` 对成片重新转写并烧字幕。
|
|
67
79
|
|
|
68
80
|
### 用户要求调整时
|
|
69
81
|
|
|
70
82
|
用户看完成片说某段不对:
|
|
71
|
-
1.
|
|
72
|
-
2.
|
|
73
|
-
3.
|
|
74
|
-
4. 重跑:
|
|
75
|
-
```bash
|
|
76
|
-
video-edit cut <video>
|
|
77
|
-
video-edit subtitle <video>
|
|
78
|
-
```
|
|
79
|
-
|
|
80
|
-
这两步纯本地(不调 whisper),几秒完成。
|
|
83
|
+
1. 编辑 `<video>.work/final_script.txt`(加/删内容)
|
|
84
|
+
2. 删 `<video>.work/subs.ass`
|
|
85
|
+
3. 重跑 `smart-cut` + `subtitle`
|
|
81
86
|
|
|
82
87
|
### 限时长精剪(用户给了目标时长)
|
|
83
88
|
|
|
84
|
-
|
|
85
|
-
-
|
|
89
|
+
写 final_script 时**额外做这些**:
|
|
90
|
+
- 估算字数:中文口播 ~3-4 字/秒,30 秒约 90-120 字
|
|
91
|
+
- 找钩子句放最前面(脚本开头那段)
|
|
86
92
|
- 压到目标时长(更激进地删)
|
|
87
|
-
- 其余流程同上
|
|
88
93
|
|
|
89
94
|
### 仅字幕(用户明确说不剪)
|
|
90
95
|
|
|
@@ -92,53 +97,53 @@ video-edit subtitle <video>
|
|
|
92
97
|
video-edit subtitle <video>
|
|
93
98
|
```
|
|
94
99
|
|
|
95
|
-
没有 `_edited.mp4`
|
|
100
|
+
没有 `_edited.mp4` 时,命令直接对原片烧字幕。
|
|
96
101
|
|
|
97
102
|
### 无字幕版(用户明确说不要字幕)
|
|
98
103
|
|
|
99
104
|
```bash
|
|
100
105
|
video-edit analyze <video>
|
|
101
|
-
#
|
|
102
|
-
video-edit cut <video>
|
|
106
|
+
# 写 final_script.txt
|
|
107
|
+
video-edit smart-cut <video>
|
|
103
108
|
```
|
|
104
109
|
|
|
105
|
-
|
|
110
|
+
不跑 subtitle,交付 `<原片>_edited.mp4`。
|
|
106
111
|
|
|
107
|
-
##
|
|
112
|
+
## 写脚本的心法
|
|
108
113
|
|
|
109
|
-
读 proposal
|
|
114
|
+
读 proposal 时**逐 phrase 判断**:
|
|
115
|
+
1. 这句进成片吗?进 → 把 phrase 文本贴到 final_script
|
|
116
|
+
2. 这句和前后哪句重复?只留一遍
|
|
117
|
+
3. 这句是填充词/口头禅?跳过
|
|
118
|
+
4. 这句跑题?跳过
|
|
110
119
|
|
|
111
|
-
|
|
112
|
-
|
|
113
|
-
3. 这行内容跟主题无关 → `#`
|
|
114
|
-
4. 其他 → 留
|
|
120
|
+
**关键纪律**:脚本里的字**必须**来自原始转写——直接复制 proposal 里的 phrase 文本最稳。
|
|
121
|
+
你想怎么润色都不行(系统按字符匹配,改了字就匹不上)。
|
|
115
122
|
|
|
116
|
-
**追求"看着不卡"
|
|
123
|
+
**追求"看着不卡",宁可激进**。删多了用户能要求加回来,删少了用户体验差。
|
|
117
124
|
|
|
118
125
|
## 交付怎么说
|
|
119
126
|
|
|
120
127
|
简洁,**只说结果**:
|
|
121
128
|
|
|
122
129
|
- ✅ "剪好了,xxx_subbed.mp4,时长 23 秒"
|
|
123
|
-
-
|
|
124
|
-
- ❌ "我用了 video-edit analyze,然后编辑了 cut_proposal.md..."
|
|
125
|
-
- ❌ "审片删了 8 行 NG..."
|
|
130
|
+
- ❌ "我用了 video-edit smart-cut,写了 final_script.txt..."
|
|
126
131
|
|
|
127
132
|
## 不要做的事
|
|
128
133
|
|
|
129
|
-
- ❌
|
|
130
|
-
- ❌
|
|
131
|
-
- ❌
|
|
132
|
-
- ❌
|
|
133
|
-
- ❌ 编造命令(仅 5 个:both / analyze / cut / review / subtitle)
|
|
134
|
+
- ❌ 跳过 final_script 直接 smart-cut——会失败(找不到脚本文件)
|
|
135
|
+
- ❌ 在脚本里写转写以外的字——匹配不上,那部分会被丢
|
|
136
|
+
- ❌ 用 `both` 或 `cut`——已弃用,质量差
|
|
137
|
+
- ❌ 把命令名/路径暴露给用户——内部细节
|
|
134
138
|
- ❌ 用户说"剪掉前 X 秒"/"剪掉中间一段"——定点裁剪不是去卡顿,告诉用户"我擅长去卡顿停顿,定点裁剪请用别的方式"
|
|
135
139
|
|
|
136
140
|
## 命令参考(你内部用)
|
|
137
141
|
|
|
138
142
|
| 命令 | 用途 |
|
|
139
143
|
|---|---|
|
|
140
|
-
| `video-edit analyze <video>` | 转写 + 生成 proposal
|
|
141
|
-
| `video-edit cut <video>` | 按
|
|
144
|
+
| `video-edit analyze <video>` | 转写 + 静音检测 + 生成 proposal(**默认入口**)|
|
|
145
|
+
| `video-edit smart-cut <video>` | 按 final_script.txt 对齐剪辑(**默认主力**)|
|
|
142
146
|
| `video-edit subtitle <video>` | 对成片重新转写 + 烧字幕,输出 `<原片>_subbed.mp4` |
|
|
143
|
-
| `video-edit
|
|
144
|
-
| `video-edit
|
|
147
|
+
| `video-edit cut <video>` | 旧模式:按 proposal 的 `#` 标记剪辑(弃用,质量差)|
|
|
148
|
+
| `video-edit both <video>` | 旧模式:analyze + cut 一步到位(弃用,跳过审片)|
|
|
149
|
+
| `video-edit review <video>` | 诊断用:检查 `_edited.mp4` |
|