ppw-team

Name: ppw-team
Author: Lylll9436

379stars20forks

How to install ppw-team?

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

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

Installs into the current project.

Summary

Orchestrate parallel paper processing. Split paper into sections and run any eligible Skill (polish, translation, de-ai) across sections via subagents. 团队协作模式：将论文拆分为章节并行处理。

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2
3	This Skill orchestrates parallel paper processing by splitting a paper into H1 sections and dispatching eligible Skills to subagents. In Phase 19 (current), it validates the proof-of-concept gate by running a single subagent on one section. Full parallel dispatch across all sections is Phase 20.
4
5	## Trigger
6
7	Activates on: `ppw:team [skill] [file]` invocations.
8
9	Examples:
10	- "ppw:team polish paper.tex" / "团队模式润色论文"
11	- "ppw:team translation draft.md" / "并行翻译论文各章节"
12	- "ppw:team de-ai paper.tex"
13
14	## Modes
15
16	\| Mode \| Default \| Behavior \|
17	\|------\|---------\|----------\|
18	\| `guided` \| Yes \| split -> user confirms sections -> user selects PoC section -> run PoC -> user confirms quality \|
19	\| `direct` \| \| skip confirmations, auto-select all body sections and first section for PoC \|
20
21	Mode inference: "直接" or "direct" in trigger switches to direct mode.
22
23	## References
24
25	`required: []` -- This Skill does not produce academic text itself. It orchestrates other Skills that load their own references at runtime. No reference files are needed by the orchestrator.
26
27	## Ask Strategy
28
29	Guided mode -- three interaction points via AskUserQuestion:
30	1. Section selection (multiSelect) after splitting
31	2. PoC section selection (single select) from selected sections
32	3. PoC quality confirmation (approve/retry/exit)
33
34	Direct mode -- skip all three: auto-select all body sections (exclude preamble and bibliography), auto-select first body section for PoC, auto-approve PoC output.
35
36	## Workflow
37
38	### Step 0: Workflow Memory (Recording Only)
39
40	- Skip pattern detection -- orchestrator is not suitable for auto-direct-mode recommendation.
41	- Recording happens after Step 1 validation (see Step 1).
42
43	### Step 1: Parse Arguments and Validate
44
45	- Parse `$ARGUMENTS` to extract: Skill name (first word) and file path (remaining words).
46	- Validate Skill name against whitelist: `["translation", "polish", "de-ai"]`
47	- If Skill is not in whitelist, reject with exact message: "[Skill] requires full-paper context and cannot run in parallel. Please run /ppw:[skill] directly."
48	- Validate file exists and is `.tex` or `.md` format. If file not found or wrong format, report error and stop.
49	- Read the paper file content.
50	- Record workflow: Append `{"skill": "ppw:team", "ts": "<ISO timestamp>"}` to `.planning/workflow-memory.json`. Create file as `[]` if missing. Drop oldest entry if log length >= 50.
51
52	### Step 2: Create Working Directory
53
54	- Create `.paper-team/` directory structure: `sections/`, `output/`.
55	- If `.paper-team/` already exists: in guided mode, ask to overwrite or cancel; in direct mode, overwrite silently.
56	- Create backup of original paper: `.paper-team/{filename}-backup-{YYYYMMDD-HHmm}.{ext}` (timestamped to prevent overwrite on re-runs).
57	- Initialize `.paper-team/manifest.json`:
58
59	```json
60	{
61	"version": "1.0",
62	"created": "<ISO timestamp>",
63	"source_file": "<original file path>",
64	"source_format": "tex\|md",
65	"target_skill": "<skill name>",
66	"sections": [],
67	"poc": { "section_id": null, "status": "pending", "timestamp": null },
68	"backup": "<backup filename>"
69	}
70	```
71
72	### Step 3: Split Paper into Sections
73
74	For .tex files:
75	- Preamble: everything from start through `\begin{document}` (inclusive). Label "00 - Preamble".
76	- Bibliography: from `\bibliography{}` or `\printbibliography` through `\end{document}`. Label "99 - Bibliography".
77	- Section boundaries: each `\section` command. Match `\section` followed by optional `*` and optional `[...]` then `{...}`. Ignore lines starting with `%` (LaTeX comments).
78	- Content between `\begin{document}` and the first `\section{}` is "00 - Pre-section content" (if non-empty after trimming).
79	- Each section: content from its `\section{Title}` line through the line before the next `\section{` or the bibliography boundary.
80
81	For .md files:
82	- Frontmatter: content before the first `# ` heading. Label "00 - Frontmatter" (if non-empty).
83	- Split at lines beginning with `# ` (H1 headings).
84	- Each H1 heading and its content until the next `# ` is one section.
85
86	Section file naming: `{NN}-{sanitized-title}.{ext}` where NN = zero-padded sequence number, sanitized-title = title lowercased, spaces to hyphens, special chars removed, max 50 chars. Preamble: `00-preamble.{ext}`. Pre-section: `00-presection.{ext}`. Bibliography: `99-bibliography.{ext}`. Frontmatter: `00-front

People who liked this also viewed

6 picks

Type

ppw-team

379stars20forks

View on GitHub

How to install ppw-team?

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

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2
3	This Skill orchestrates parallel paper processing by splitting a paper into H1 sections and dispatching eligible Skills to subagents. In Phase 19 (current), it validates the proof-of-concept gate by running a single subagent on one section. Full parallel dispatch across all sections is Phase 20.
4
5	## Trigger
6
7	Activates on: `ppw:team [skill] [file]` invocations.
8
9	Examples:
10	- "ppw:team polish paper.tex" / "团队模式润色论文"
11	- "ppw:team translation draft.md" / "并行翻译论文各章节"
12	- "ppw:team de-ai paper.tex"
13
14	## Modes
15
16	\| Mode \| Default \| Behavior \|
17	\|------\|---------\|----------\|
18	\| `guided` \| Yes \| split -> user confirms sections -> user selects PoC section -> run PoC -> user confirms quality \|
19	\| `direct` \| \| skip confirmations, auto-select all body sections and first section for PoC \|
20
21	Mode inference: "直接" or "direct" in trigger switches to direct mode.
22
23	## References
24
25	`required: []` -- This Skill does not produce academic text itself. It orchestrates other Skills that load their own references at runtime. No reference files are needed by the orchestrator.
26
27	## Ask Strategy
28
29	Guided mode -- three interaction points via AskUserQuestion:
30	1. Section selection (multiSelect) after splitting
31	2. PoC section selection (single select) from selected sections
32	3. PoC quality confirmation (approve/retry/exit)
33
34	Direct mode -- skip all three: auto-select all body sections (exclude preamble and bibliography), auto-select first body section for PoC, auto-approve PoC output.
35
36	## Workflow
37
38	### Step 0: Workflow Memory (Recording Only)
39
40	- Skip pattern detection -- orchestrator is not suitable for auto-direct-mode recommendation.
41	- Recording happens after Step 1 validation (see Step 1).
42
43	### Step 1: Parse Arguments and Validate
44
45	- Parse `$ARGUMENTS` to extract: Skill name (first word) and file path (remaining words).
46	- Validate Skill name against whitelist: `["translation", "polish", "de-ai"]`
47	- If Skill is not in whitelist, reject with exact message: "[Skill] requires full-paper context and cannot run in parallel. Please run /ppw:[skill] directly."
48	- Validate file exists and is `.tex` or `.md` format. If file not found or wrong format, report error and stop.
49	- Read the paper file content.
50	- Record workflow: Append `{"skill": "ppw:team", "ts": "<ISO timestamp>"}` to `.planning/workflow-memory.json`. Create file as `[]` if missing. Drop oldest entry if log length >= 50.
51
52	### Step 2: Create Working Directory
53
54	- Create `.paper-team/` directory structure: `sections/`, `output/`.
55	- If `.paper-team/` already exists: in guided mode, ask to overwrite or cancel; in direct mode, overwrite silently.
56	- Create backup of original paper: `.paper-team/{filename}-backup-{YYYYMMDD-HHmm}.{ext}` (timestamped to prevent overwrite on re-runs).
57	- Initialize `.paper-team/manifest.json`:
58
59	```json
60	{
61	"version": "1.0",
62	"created": "<ISO timestamp>",
63	"source_file": "<original file path>",
64	"source_format": "tex\|md",
65	"target_skill": "<skill name>",
66	"sections": [],
67	"poc": { "section_id": null, "status": "pending", "timestamp": null },
68	"backup": "<backup filename>"
69	}
70	```
71
72	### Step 3: Split Paper into Sections
73
74	For .tex files:
75	- Preamble: everything from start through `\begin{document}` (inclusive). Label "00 - Preamble".
76	- Bibliography: from `\bibliography{}` or `\printbibliography` through `\end{document}`. Label "99 - Bibliography".
77	- Section boundaries: each `\section` command. Match `\section` followed by optional `*` and optional `[...]` then `{...}`. Ignore lines starting with `%` (LaTeX comments).
78	- Content between `\begin{document}` and the first `\section{}` is "00 - Pre-section content" (if non-empty after trimming).
79	- Each section: content from its `\section{Title}` line through the line before the next `\section{` or the bibliography boundary.
80
81	For .md files:
82	- Frontmatter: content before the first `# ` heading. Label "00 - Frontmatter" (if non-empty).
83	- Split at lines beginning with `# ` (H1 headings).
84	- Each H1 heading and its content until the next `# ` is one section.
85
86	Section file naming: `{NN}-{sanitized-title}.{ext}` where NN = zero-padded sequence number, sanitized-title = title lowercased, spaces to hyphens, special chars removed, max 50 chars. Preamble: `00-preamble.{ext}`. Pre-section: `00-presection.{ext}`. Bibliography: `99-bibliography.{ext}`. Frontmatter: `00-front

People who liked this also viewed

6 picks

Type