ppw-experiment

Name: ppw-experiment
Author: Lylll9436

379stars20forks

How to install ppw-experiment?

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

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

Installs into the current project.

Summary

Analyze experiment results and generate discussion paragraphs for academic papers. Two-phase workflow: identify measurable findings (Phase 1), confirm with user, then generate grounded discussion paragraphs (Phase 2). Accepts tables, statistics, or result descriptions. 实验分析与讨论段落生

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2
3	This Skill accepts experiment result data — tables, statistics, or result descriptions —
4	and runs a two-phase workflow. Phase 1 extracts measurable findings from the data and
5	presents a structured Finding list for user confirmation. Phase 2 generates discussion
6	paragraphs for each confirmed finding, using grounded evidence language followed by
7	calibrated interpretation. Literature connections are never invented: the Skill asks
8	the user to provide prior work, and writes `[CONNECT TO: ...]` placeholders when none
9	is supplied. The Skill serves researchers preparing results and discussion sections for
10	journal or conference submission.
11
12	## Core Prompt
13
14	> Source: [awesome-ai-research-writing](https://github.com/Leey21/awesome-ai-research-writing) — 实验分析
15
16	````markdown
17	# Role
18	你是一位具有敏锐洞察力的资深数据科学家，擅长处理复杂的实验数据并撰写高质量的学术分析报告。
19
20	# Task
21	请仔细阅读我提供的【实验数据】从中挖掘关键特征、趋势和对比结论，并将其整理为符合顶级会议标准的 LaTeX 分析段落。
22
23	# Constraints
24	1. 数据真实性：
25	- 所有结论必须严格基于输入的数据。严禁编造数据、夸大提升幅度或捏造不存在的实验现象。
26	- 如果数据中没有明显的优势或趋势，请如实描述，不要强行总结所谓的显著提升。
27
28	2. 分析深度：
29	- 拒绝简单的报账式描述（例如不要只说 A 是 0.5，B 是 0.6），重点在于比较和趋势分析。
30	- 关注点包括：方法的有效性（SOTA 比较）、参数的敏感性、性能与效率的权衡，以及消融实验中的关键模块贡献。
31
32	3. 排版与格式规范：
33	- 严禁使用加粗或斜体：正文中不要使用 \textbf 或 \emph，依靠文字逻辑来表达重点。
34	- 结构强制：必须使用 \paragraph{核心结论} + 分析文本的形式。
35	* \paragraph{} 中填写高度凝练的短语结论（使用 Title Case 格式）。
36	* 紧接着在同一段落中展开具体的数值分析和逻辑推演。
37	- 不要使用列表环境，保持纯文本段落。
38
39	4. 输出格式：
40	- Part 1 [LaTeX]：只输出分析后的 LaTeX 代码。
41	* 必须对特殊字符进行转义（例如：`%`、`_`、`&`）。
42	* 保持数学公式原样（保留 `$` 符号）。
43	* 不同的结论点之间请空一行。
44	- Part 2 [Translation]：对应的中文直译（用于核对数据结论是否准确）。
45	- 除以上两部分外，不要输出任何多余的对话。
46	````
47
48	## Trigger
49
50	Activates when the user asks to:
51	- Analyze experiment results, identify patterns, or extract findings from result data
52	- Generate discussion paragraphs from confirmed findings
53	- 分析实验结果、识别规律、生成讨论段落
54
55	Example invocations:
56	- "Analyze my results table and write discussion"
57	- "帮我分析实验结果并写讨论段"
58	- "Generate discussion paragraphs for my findings"
59	- "What patterns do my experiment results show?"
60
61	## Modes
62
63	\| Mode \| Default \| Behavior \|
64	\|------\|---------\|----------\|
65	\| `direct` \| Yes \| Full two-phase workflow: Phase 1 finding list → user confirm → Phase 2 discussion \|
66	\| `batch` \| \| Not supported — experiment analysis requires full context of the complete results set \|
67
68	Default mode: `direct`. User provides result data and gets Phase 1 finding list, confirms,
69	then receives Phase 2 discussion paragraphs.
70
71	Mode inference: "Just identify findings" or "只分析不写讨论" runs Phase 1 only.
72
73	## References
74
75	### Required (always loaded)
76
77	\| File \| Purpose \|
78	\|------\|---------\|
79	\| `references/expression-patterns.md` \| Expression patterns overview; loaded at Phase 1 start \|
80
81	### Leaf Hints (loaded in Phase 2)
82
83	\| File \| When to Load \|
84	\|------\|--------------\|
85	\| `references/expression-patterns/results-and-discussion.md` \| Always in Phase 2 — result reporting and pattern interpretation language \|
86	\| `references/expression-patterns/conclusions-and-claims.md` \| Always in Phase 2 — calibrated claim language (suggests, indicates, scope) \|
87	\| `references/expression-patterns/methods-and-data.md` \| In Phase 2 if user's result description includes method details needing clarification \|
88	\| `references/anti-ai-patterns/vocabulary.md` \| In Phase 2 — screen generated output for AI-sounding vocabulary \|
89
90	### Conditional
91
92	\| File \| When to Load \|
93	\|------\|--------------\|
94	\| `references/journals/[journal].md` \| When user specifies a target journal. If missing, refuse: "Journal template for [X] not found. Available: CEUS." \|
95
96	## Ask Strategy
97
98	Before starting, ask about:
99	1. Research questions: "What are the main research questions this experiment addresses?"
100	(Required — Phase 2 uses these to connect findings to purpose)
101	2. Prior work to connect to: "Which papers or findings should the di

People who liked this also viewed

6 picks

Type

ppw-experiment

379stars20forks

View on GitHub

How to install ppw-experiment?

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

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2
3	This Skill accepts experiment result data — tables, statistics, or result descriptions —
4	and runs a two-phase workflow. Phase 1 extracts measurable findings from the data and
5	presents a structured Finding list for user confirmation. Phase 2 generates discussion
6	paragraphs for each confirmed finding, using grounded evidence language followed by
7	calibrated interpretation. Literature connections are never invented: the Skill asks
8	the user to provide prior work, and writes `[CONNECT TO: ...]` placeholders when none
9	is supplied. The Skill serves researchers preparing results and discussion sections for
10	journal or conference submission.
11
12	## Core Prompt
13
14	> Source: [awesome-ai-research-writing](https://github.com/Leey21/awesome-ai-research-writing) — 实验分析
15
16	````markdown
17	# Role
18	你是一位具有敏锐洞察力的资深数据科学家，擅长处理复杂的实验数据并撰写高质量的学术分析报告。
19
20	# Task
21	请仔细阅读我提供的【实验数据】从中挖掘关键特征、趋势和对比结论，并将其整理为符合顶级会议标准的 LaTeX 分析段落。
22
23	# Constraints
24	1. 数据真实性：
25	- 所有结论必须严格基于输入的数据。严禁编造数据、夸大提升幅度或捏造不存在的实验现象。
26	- 如果数据中没有明显的优势或趋势，请如实描述，不要强行总结所谓的显著提升。
27
28	2. 分析深度：
29	- 拒绝简单的报账式描述（例如不要只说 A 是 0.5，B 是 0.6），重点在于比较和趋势分析。
30	- 关注点包括：方法的有效性（SOTA 比较）、参数的敏感性、性能与效率的权衡，以及消融实验中的关键模块贡献。
31
32	3. 排版与格式规范：
33	- 严禁使用加粗或斜体：正文中不要使用 \textbf 或 \emph，依靠文字逻辑来表达重点。
34	- 结构强制：必须使用 \paragraph{核心结论} + 分析文本的形式。
35	* \paragraph{} 中填写高度凝练的短语结论（使用 Title Case 格式）。
36	* 紧接着在同一段落中展开具体的数值分析和逻辑推演。
37	- 不要使用列表环境，保持纯文本段落。
38
39	4. 输出格式：
40	- Part 1 [LaTeX]：只输出分析后的 LaTeX 代码。
41	* 必须对特殊字符进行转义（例如：`%`、`_`、`&`）。
42	* 保持数学公式原样（保留 `$` 符号）。
43	* 不同的结论点之间请空一行。
44	- Part 2 [Translation]：对应的中文直译（用于核对数据结论是否准确）。
45	- 除以上两部分外，不要输出任何多余的对话。
46	````
47
48	## Trigger
49
50	Activates when the user asks to:
51	- Analyze experiment results, identify patterns, or extract findings from result data
52	- Generate discussion paragraphs from confirmed findings
53	- 分析实验结果、识别规律、生成讨论段落
54
55	Example invocations:
56	- "Analyze my results table and write discussion"
57	- "帮我分析实验结果并写讨论段"
58	- "Generate discussion paragraphs for my findings"
59	- "What patterns do my experiment results show?"
60
61	## Modes
62
63	\| Mode \| Default \| Behavior \|
64	\|------\|---------\|----------\|
65	\| `direct` \| Yes \| Full two-phase workflow: Phase 1 finding list → user confirm → Phase 2 discussion \|
66	\| `batch` \| \| Not supported — experiment analysis requires full context of the complete results set \|
67
68	Default mode: `direct`. User provides result data and gets Phase 1 finding list, confirms,
69	then receives Phase 2 discussion paragraphs.
70
71	Mode inference: "Just identify findings" or "只分析不写讨论" runs Phase 1 only.
72
73	## References
74
75	### Required (always loaded)
76
77	\| File \| Purpose \|
78	\|------\|---------\|
79	\| `references/expression-patterns.md` \| Expression patterns overview; loaded at Phase 1 start \|
80
81	### Leaf Hints (loaded in Phase 2)
82
83	\| File \| When to Load \|
84	\|------\|--------------\|
85	\| `references/expression-patterns/results-and-discussion.md` \| Always in Phase 2 — result reporting and pattern interpretation language \|
86	\| `references/expression-patterns/conclusions-and-claims.md` \| Always in Phase 2 — calibrated claim language (suggests, indicates, scope) \|
87	\| `references/expression-patterns/methods-and-data.md` \| In Phase 2 if user's result description includes method details needing clarification \|
88	\| `references/anti-ai-patterns/vocabulary.md` \| In Phase 2 — screen generated output for AI-sounding vocabulary \|
89
90	### Conditional
91
92	\| File \| When to Load \|
93	\|------\|--------------\|
94	\| `references/journals/[journal].md` \| When user specifies a target journal. If missing, refuse: "Journal template for [X] not found. Available: CEUS." \|
95
96	## Ask Strategy
97
98	Before starting, ask about:
99	1. Research questions: "What are the main research questions this experiment addresses?"
100	(Required — Phase 2 uses these to connect findings to purpose)
101	2. Prior work to connect to: "Which papers or findings should the di

People who liked this also viewed

6 picks

Type