ppw-repo-to-paper

Name: ppw-repo-to-paper
Author: Lylll9436

379stars20forks

How to install ppw-repo-to-paper?

lylll9436/paper-polish-workflow-skill/ppw-repo-to-paper

$npx -y skills add Lylll9436/Paper-Polish-Workflow-skill --skill ppw-repo-to-paper

Installs into the current project.

Summary

Scan an experiment repo and generate a complete paper outline (H1/H2/H3) with user approval checkpoints at each level, then generate body text with evidence annotations, citations, and bilingual output. Python ML repos. 扫描实验仓库，逐级生成论文大纲（H1/H2/H3），每级用户确认后推进，然后生成带证据标注、引用和双语输出的正文文本。

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2
3	This Skill scans a Python ML experiment repository and generates a hierarchical paper outline
4	(H1/H2/H3) with user approval checkpoints at each heading level. It serves researchers who
5	have completed experiments and need to structure findings into an academic paper. The scan
6	categorizes repo files using patterns from `references/repo-patterns.md`, then progressively
7	generates headings from coarse (sections) to fine (sub-subsections), with the user confirming
8	or modifying each level before proceeding. After H2 confirmation, the Skill automatically
9	collects academic references via Semantic Scholar MCP and saves them as per-section ref files
10	for downstream body generation.
11
12	## Trigger
13
14	Activates when the user asks to:
15	- Generate a paper structure, outline, or skeleton from a repository or codebase
16	- Scan a project and create paper sections from experiment code or results
17	- 从实验仓库/代码仓库生成论文大纲或论文结构
18
19	Example invocations:
20	- "Generate a paper outline from my repo"
21	- "帮我从实验仓库生成论文大纲"
22	- "Scan my project and create paper structure"
23	- "把我的代码仓库转成论文框架"
24
25	## Modes
26
27	\| Mode \| Default \| Behavior \|
28	\|------\|---------\|----------\|
29	\| `guided` \| Yes \| Full 5-step workflow with confirmation at each heading level and section-by-section body generation \|
30	\| `direct` \| \| Not supported -- outline generation inherently requires user validation at each level \|
31	\| `batch` \| \| Not supported -- each repo requires unique analysis \|
32
33	Default mode: `guided`. The layered confirmation design is central to this Skill.
34
35	## References
36
37	### Required (always loaded)
38
39	\| File \| Purpose \|
40	\|------\|---------\|
41	\| `references/repo-patterns.md` \| File categorization patterns and section mapping rules \|
42	\| `references/bilingual-output.md` \| Bilingual output format (Skill is bilingual-eligible) \|
43	\| `references/body-generation-rules.md` \| Anti-hallucination rules, citation integration, bilingual format, references.bib algorithm \|
44	\| `references/journals/ceus.md` \| CEUS journal formatting contract (writing style, section guidance) \|
45
46	### Leaf Hints
47
48	None. All reference files are in `required` because Step 5 body generation always needs CEUS formatting.
49
50	### Loading Rules
51
52	- Load `repo-patterns.md` and `bilingual-output.md` at Step 1 start.
53	- Load `body-generation-rules.md` and `journals/ceus.md` at Step 5 start.
54	- If journal template file is missing, refuse: "Journal template for [X] not found. Available: CEUS."
55
56	## Ask Strategy
57
58	Before starting, ask about:
59	1. Repo path (required): "Which repository should I scan?" -- use Structured Interaction if available
60	2. Target journal (optional): "Which journal is this paper targeting?" -- options: CEUS, Other, None/General.
61	If CEUS, load template at Step 2. If Other, ask for journal name. If None, use IMRaD default
62
63	Bilingual mode: Inferred from trigger text. Check for opt-out keywords per `references/bilingual-output.md`
64	(exact phrases: `english only`, `no bilingual`, `only english`, `不要中文`). Do not ask explicitly.
65
66	Rules:
67	- Never ask more than 2 explicit questions (repo path + journal)
68	- In direct mode, skip -- but direct mode is not supported for this Skill
69
70	## Workflow
71
72	### Step 0: Workflow Memory Check
73
74	- Read `.planning/workflow-memory.json`. If file missing or empty, skip to Step 1.
75	- Check if the last 1-2 log entries form a recognized pattern with `ppw:repo-to-paper` that has appeared >= threshold times in the log. See `skill-conventions.md > Workflow Memory > Pattern Detection` for the full algorithm.
76	- If a pattern is found, present recommendation via AskUserQuestion:
77	- Question: "检测到常用流程：[pattern]（已出现 N 次）。是否直接以 direct 模式运行 ppw:repo-to-paper？"
78	- Options: "Yes, proceed" / "No, continue normally"
79	- If user accepts: set mode to `direct`, skip Ask Strategy questions.
80	- If user declines or AskUserQuestion unavailable: continue in normal mode.
81	- Note: This Skill does not support full `direct` mode. If user accepts the recommendation, skip the Ask Strategy questions (repo path, journal)

People who liked this also viewed

6 picks

Type

ppw-repo-to-paper

379stars20forks

View on GitHub

How to install ppw-repo-to-paper?

lylll9436/paper-polish-workflow-skill/ppw-repo-to-paper

$npx -y skills add Lylll9436/Paper-Polish-Workflow-skill --skill ppw-repo-to-paper

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2
3	This Skill scans a Python ML experiment repository and generates a hierarchical paper outline
4	(H1/H2/H3) with user approval checkpoints at each heading level. It serves researchers who
5	have completed experiments and need to structure findings into an academic paper. The scan
6	categorizes repo files using patterns from `references/repo-patterns.md`, then progressively
7	generates headings from coarse (sections) to fine (sub-subsections), with the user confirming
8	or modifying each level before proceeding. After H2 confirmation, the Skill automatically
9	collects academic references via Semantic Scholar MCP and saves them as per-section ref files
10	for downstream body generation.
11
12	## Trigger
13
14	Activates when the user asks to:
15	- Generate a paper structure, outline, or skeleton from a repository or codebase
16	- Scan a project and create paper sections from experiment code or results
17	- 从实验仓库/代码仓库生成论文大纲或论文结构
18
19	Example invocations:
20	- "Generate a paper outline from my repo"
21	- "帮我从实验仓库生成论文大纲"
22	- "Scan my project and create paper structure"
23	- "把我的代码仓库转成论文框架"
24
25	## Modes
26
27	\| Mode \| Default \| Behavior \|
28	\|------\|---------\|----------\|
29	\| `guided` \| Yes \| Full 5-step workflow with confirmation at each heading level and section-by-section body generation \|
30	\| `direct` \| \| Not supported -- outline generation inherently requires user validation at each level \|
31	\| `batch` \| \| Not supported -- each repo requires unique analysis \|
32
33	Default mode: `guided`. The layered confirmation design is central to this Skill.
34
35	## References
36
37	### Required (always loaded)
38
39	\| File \| Purpose \|
40	\|------\|---------\|
41	\| `references/repo-patterns.md` \| File categorization patterns and section mapping rules \|
42	\| `references/bilingual-output.md` \| Bilingual output format (Skill is bilingual-eligible) \|
43	\| `references/body-generation-rules.md` \| Anti-hallucination rules, citation integration, bilingual format, references.bib algorithm \|
44	\| `references/journals/ceus.md` \| CEUS journal formatting contract (writing style, section guidance) \|
45
46	### Leaf Hints
47
48	None. All reference files are in `required` because Step 5 body generation always needs CEUS formatting.
49
50	### Loading Rules
51
52	- Load `repo-patterns.md` and `bilingual-output.md` at Step 1 start.
53	- Load `body-generation-rules.md` and `journals/ceus.md` at Step 5 start.
54	- If journal template file is missing, refuse: "Journal template for [X] not found. Available: CEUS."
55
56	## Ask Strategy
57
58	Before starting, ask about:
59	1. Repo path (required): "Which repository should I scan?" -- use Structured Interaction if available
60	2. Target journal (optional): "Which journal is this paper targeting?" -- options: CEUS, Other, None/General.
61	If CEUS, load template at Step 2. If Other, ask for journal name. If None, use IMRaD default
62
63	Bilingual mode: Inferred from trigger text. Check for opt-out keywords per `references/bilingual-output.md`
64	(exact phrases: `english only`, `no bilingual`, `only english`, `不要中文`). Do not ask explicitly.
65
66	Rules:
67	- Never ask more than 2 explicit questions (repo path + journal)
68	- In direct mode, skip -- but direct mode is not supported for this Skill
69
70	## Workflow
71
72	### Step 0: Workflow Memory Check
73
74	- Read `.planning/workflow-memory.json`. If file missing or empty, skip to Step 1.
75	- Check if the last 1-2 log entries form a recognized pattern with `ppw:repo-to-paper` that has appeared >= threshold times in the log. See `skill-conventions.md > Workflow Memory > Pattern Detection` for the full algorithm.
76	- If a pattern is found, present recommendation via AskUserQuestion:
77	- Question: "检测到常用流程：[pattern]（已出现 N 次）。是否直接以 direct 模式运行 ppw:repo-to-paper？"
78	- Options: "Yes, proceed" / "No, continue normally"
79	- If user accepts: set mode to `direct`, skip Ask Strategy questions.
80	- If user declines or AskUserQuestion unavailable: continue in normal mode.
81	- Note: This Skill does not support full `direct` mode. If user accepts the recommendation, skip the Ask Strategy questions (repo path, journal)

People who liked this also viewed

6 picks

Type