ppw-caption

Name: ppw-caption
Author: Lylll9436

379stars20forks

How to install ppw-caption?

lylll9436/paper-polish-workflow-skill/ppw-caption

$npx -y skills add Lylll9436/Paper-Polish-Workflow-skill --skill ppw-caption

Installs into the current project.

Summary

Generate or optimize figure/table captions for academic papers. Geography-aware: study area, CRS notation, data source. Writes output to .tex file. 图表标题生成与优化。

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2
3	This Skill generates or optimizes LaTeX figure and table captions for academic papers. For spatial figures (maps, GIS outputs, aerial photos), the Skill proactively collects study area, data source, and CRS metadata using a geography-aware Ask Strategy. For non-spatial figures and tables, geography questions are skipped entirely. Output is written directly to the user's `.tex` file at the correct `\caption{}` location using the Read-before-Write pattern. When a target journal is specified, caption length and style are adapted to the journal template.
4
5	## Core Prompt
6
7	> Source: [awesome-ai-research-writing](https://github.com/Leey21/awesome-ai-research-writing) — 生成图的标题 + 生成表的标题
8
9	图标题 Prompt：
10
11	````markdown
12	# Role
13	你是一位经验丰富的学术编辑，擅长撰写精准、规范的论文插图标题。
14
15	# Task
16	请将我提供的【中文描述】转化为符合顶级会议规范的【英文图标题】。
17
18	# Constraints
19	1. 格式规范：
20	- 如果翻译结果是名词性短语：请使用 Title Case 格式，即所有实词的首字母大写，末尾不加句号。
21	- 如果翻译结果是完整句子：请使用 Sentence case 格式，即仅第一个单词的首字母大写，其余小写（专有名词除外），末尾必须加句号。
22
23	2. 写作风格：
24	- 极简原则：去除 The figure shows 或 This diagram illustrates 这类冗余开头，直接描述图表内容（例如直接以 Architecture, Performance comparison, Visualization 开头）。
25	- 去 AI 味：尽量避免使用复杂的生僻词，保持用词平实准确。
26
27	3. 输出格式：
28	- 只输出翻译后的英文标题文本。
29	- 不要包含 Figure 1: 这样的前缀，只输出内容本身。
30	- 必须对特殊字符进行转义（例如：`%`、`_`、`&`）。
31	- 保持数学公式原样（保留 `$` 符号）。
32	````
33
34	表标题 Prompt：
35
36	````markdown
37	# Role
38	你是一位经验丰富的学术编辑，擅长撰写精准、规范的论文表格标题。
39
40	# Task
41	请将我提供的【中文描述】转化为符合顶级会议规范的【英文表标题】。
42
43	# Constraints
44	1. 格式规范：
45	- 如果翻译结果是名词性短语：请使用 Title Case 格式，即所有实词的首字母大写，末尾不加句号。
46	- 如果翻译结果是完整句子：请使用 Sentence case 格式，即仅第一个单词的首字母大写，其余小写（专有名词除外），末尾必须加句号。
47
48	2. 写作风格：
49	- 常用句式：对于表格，推荐使用 Comparison with, Ablation study on, Results on 等标准学术表达。
50	- 去 AI 味：尽量避免使用 showcase, depict 等词，直接使用 show, compare, present。
51
52	3. 输出格式：
53	- 只输出翻译后的英文标题文本。
54	- 不要包含 Table 1: 这样的前缀，只输出内容本身。
55	- 必须对特殊字符进行转义（例如：`%`、`_`、`&`）。
56	- 保持数学公式原样（保留 `$` 符号）。
57	````
58
59	## Trigger
60
61	Activates when the user asks to:
62	- Write, generate, or create a caption for a figure or table
63	- Optimize, improve, or rewrite an existing weak caption
64	- 写图题、生成图表说明、优化标题、改写图表描述
65
66	Example invocations:
67	- "Write a caption for my figure" / "帮我写图表标题"
68	- "Optimize this table caption" / "优化我的图表说明"
69	- "Generate a CEUS-ready figure caption" / "帮我生成符合期刊要求的图题"
70	- "Improve the caption for my map figure"
71	- "帮我生成符合CEUS要求的图题"
72
73	## Modes
74
75	\| Mode \| Default \| Behavior \|
76	\|------\|---------\|----------\|
77	\| `direct` \| Yes \| Single-pass caption output after Ask Strategy questions \|
78	\| `batch` \| \| Not supported — each caption requires its own figure/table context \|
79
80	Default mode: `direct`. User provides figure/table context and receives a complete LaTeX caption in one pass.
81
82	Path selection (within direct mode):
83	- User provides an existing caption to improve → Optimize path
84	- User provides content description only → Generate path
85	- Ambiguous → ask: "Do you have an existing caption to improve, or shall I generate one from your description?"
86
87	## References
88
89	### Required (always loaded)
90
91	\| File \| Purpose \|
92	\|------\|---------\|
93	\| `references/expression-patterns.md` \| Academic expression patterns overview — always loaded as entrypoint \|
94
95	### Leaf Hints (loaded conditionally)
96
97	\| File \| When to Load \|
98	\|------\|--------------\|
99	\| `references/expression-patterns/geography-domain.md` \| When figure type is spatial (map, photo, GIS output); provides study area framing, spatial description patterns, planning language \|
100
101	### Journal Template (conditional)
102
103	- When user specifies a target journal, load `references/journals/[journal].md`.
104	- If template missing, refuse: "Journal template for [X] not found. Available: CEUS."
105	- If no journal specified, ask once; if declined, use general academic style.
106
107	## Ask Strategy
108
109	Before starting, collect:
110
111	1. Figure or table type (always required — determines whether spatial questions apply):
112	map / chart / diagram / photo / data table?
113
114	2. Target journal if not specified (ask once; if declined, use general academic style)
115
116	3. If figure type is spatial (map, photo, GIS output):
117	- Study area / city name (e.g., "Beijing Chaoyang District")
118	- Data source brief (e.g., "OpenStreetMap 2023", "Landsat-8 imagery")
119	- CRS (ask only if user knows it; skip if uncertain — do not press)
120	- Key legend items (ask only if map or chart has a visible legend)
121
122	4. **If figure type is n

People who liked this also viewed

6 picks

Type

ppw-caption

379stars20forks

View on GitHub

How to install ppw-caption?

lylll9436/paper-polish-workflow-skill/ppw-caption

$npx -y skills add Lylll9436/Paper-Polish-Workflow-skill --skill ppw-caption

Installs into the current project.

Summary

Generate or optimize figure/table captions for academic papers. Geography-aware: study area, CRS notation, data source. Writes output to .tex file. 图表标题生成与优化。

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2
3	This Skill generates or optimizes LaTeX figure and table captions for academic papers. For spatial figures (maps, GIS outputs, aerial photos), the Skill proactively collects study area, data source, and CRS metadata using a geography-aware Ask Strategy. For non-spatial figures and tables, geography questions are skipped entirely. Output is written directly to the user's `.tex` file at the correct `\caption{}` location using the Read-before-Write pattern. When a target journal is specified, caption length and style are adapted to the journal template.
4
5	## Core Prompt
6
7	> Source: [awesome-ai-research-writing](https://github.com/Leey21/awesome-ai-research-writing) — 生成图的标题 + 生成表的标题
8
9	图标题 Prompt：
10
11	````markdown
12	# Role
13	你是一位经验丰富的学术编辑，擅长撰写精准、规范的论文插图标题。
14
15	# Task
16	请将我提供的【中文描述】转化为符合顶级会议规范的【英文图标题】。
17
18	# Constraints
19	1. 格式规范：
20	- 如果翻译结果是名词性短语：请使用 Title Case 格式，即所有实词的首字母大写，末尾不加句号。
21	- 如果翻译结果是完整句子：请使用 Sentence case 格式，即仅第一个单词的首字母大写，其余小写（专有名词除外），末尾必须加句号。
22
23	2. 写作风格：
24	- 极简原则：去除 The figure shows 或 This diagram illustrates 这类冗余开头，直接描述图表内容（例如直接以 Architecture, Performance comparison, Visualization 开头）。
25	- 去 AI 味：尽量避免使用复杂的生僻词，保持用词平实准确。
26
27	3. 输出格式：
28	- 只输出翻译后的英文标题文本。
29	- 不要包含 Figure 1: 这样的前缀，只输出内容本身。
30	- 必须对特殊字符进行转义（例如：`%`、`_`、`&`）。
31	- 保持数学公式原样（保留 `$` 符号）。
32	````
33
34	表标题 Prompt：
35
36	````markdown
37	# Role
38	你是一位经验丰富的学术编辑，擅长撰写精准、规范的论文表格标题。
39
40	# Task
41	请将我提供的【中文描述】转化为符合顶级会议规范的【英文表标题】。
42
43	# Constraints
44	1. 格式规范：
45	- 如果翻译结果是名词性短语：请使用 Title Case 格式，即所有实词的首字母大写，末尾不加句号。
46	- 如果翻译结果是完整句子：请使用 Sentence case 格式，即仅第一个单词的首字母大写，其余小写（专有名词除外），末尾必须加句号。
47
48	2. 写作风格：
49	- 常用句式：对于表格，推荐使用 Comparison with, Ablation study on, Results on 等标准学术表达。
50	- 去 AI 味：尽量避免使用 showcase, depict 等词，直接使用 show, compare, present。
51
52	3. 输出格式：
53	- 只输出翻译后的英文标题文本。
54	- 不要包含 Table 1: 这样的前缀，只输出内容本身。
55	- 必须对特殊字符进行转义（例如：`%`、`_`、`&`）。
56	- 保持数学公式原样（保留 `$` 符号）。
57	````
58
59	## Trigger
60
61	Activates when the user asks to:
62	- Write, generate, or create a caption for a figure or table
63	- Optimize, improve, or rewrite an existing weak caption
64	- 写图题、生成图表说明、优化标题、改写图表描述
65
66	Example invocations:
67	- "Write a caption for my figure" / "帮我写图表标题"
68	- "Optimize this table caption" / "优化我的图表说明"
69	- "Generate a CEUS-ready figure caption" / "帮我生成符合期刊要求的图题"
70	- "Improve the caption for my map figure"
71	- "帮我生成符合CEUS要求的图题"
72
73	## Modes
74
75	\| Mode \| Default \| Behavior \|
76	\|------\|---------\|----------\|
77	\| `direct` \| Yes \| Single-pass caption output after Ask Strategy questions \|
78	\| `batch` \| \| Not supported — each caption requires its own figure/table context \|
79
80	Default mode: `direct`. User provides figure/table context and receives a complete LaTeX caption in one pass.
81
82	Path selection (within direct mode):
83	- User provides an existing caption to improve → Optimize path
84	- User provides content description only → Generate path
85	- Ambiguous → ask: "Do you have an existing caption to improve, or shall I generate one from your description?"
86
87	## References
88
89	### Required (always loaded)
90
91	\| File \| Purpose \|
92	\|------\|---------\|
93	\| `references/expression-patterns.md` \| Academic expression patterns overview — always loaded as entrypoint \|
94
95	### Leaf Hints (loaded conditionally)
96
97	\| File \| When to Load \|
98	\|------\|--------------\|
99	\| `references/expression-patterns/geography-domain.md` \| When figure type is spatial (map, photo, GIS output); provides study area framing, spatial description patterns, planning language \|
100
101	### Journal Template (conditional)
102
103	- When user specifies a target journal, load `references/journals/[journal].md`.
104	- If template missing, refuse: "Journal template for [X] not found. Available: CEUS."
105	- If no journal specified, ask once; if declined, use general academic style.
106
107	## Ask Strategy
108
109	Before starting, collect:
110
111	1. Figure or table type (always required — determines whether spatial questions apply):
112	map / chart / diagram / photo / data table?
113
114	2. Target journal if not specified (ask once; if declined, use general academic style)
115
116	3. If figure type is spatial (map, photo, GIS output):
117	- Study area / city name (e.g., "Beijing Chaoyang District")
118	- Data source brief (e.g., "OpenStreetMap 2023", "Landsat-8 imagery")
119	- CRS (ask only if user knows it; skip if uncertain — do not press)
120	- Key legend items (ask only if map or chart has a visible legend)
121
122	4. **If figure type is n

People who liked this also viewed

6 picks

Type