Paper Workflow: Dispatcher
This is the entry point, not a menu. A request such as 优化一下论文 or improve my manuscript
names a goal, not a layer. Manuscript work happens at distinct layers, and editing the wrong layer
first wastes the edit: a paragraph whose scientific role is wrong should never be polished, and a
sentence whose claim is unstable should never be re-punctuated.
Do not answer a general manuscript request by loading a single specialist skill. Classify the
request, then run the whole chain for that class.
Default assumption: unless a conference venue is named, the manuscript follows the journal-oriented
Nature-style path.
Step 1: Classify by what was actually handed over
| Input |
Class |
Chain |
| One sentence or one paragraph |
passage |
write-scientific-manuscript, then anti-defensive-writing if the passage is hedged or over-caveated, then scientific-prose-style |
| One section to draft or rewrite in prose |
section |
scientific-writing, write-scientific-manuscript, anti-defensive-writing, then scientific-prose-style |
| A Results section that is scientifically settled but reads figure-by-figure |
results-flow |
results-section-revision, anti-defensive-writing, then scientific-prose-style |
| A whole draft, or no unit named |
manuscript |
manuscript-optimizer, scientific-writing, write-scientific-manuscript, anti-defensive-writing, then scientific-prose-style |
| Reads hedged, over-caveated, apologetic, or timid; too many disclaimers; a paragraph opens with a limitation |
posture |
anti-defensive-writing, then scientific-prose-style. If the claim hierarchy is not yet settled, run manuscript-optimizer first: an unnecessary disclaimer and a real scope condition look identical while the claim is still moving |
| A Review, survey, or Perspective |
review-article |
review-article-architecture first, then the Review path below |
| A long draft carried across many sessions |
long-draft |
draft-marker-discipline then review-article-architecture drift audit |
| Near submission or resubmission |
preflight |
submission-audit, citation-verifier, claim-source-verification, stats-reporting-audit, data-availability |
| Reviewer comments exist |
response |
paper-reviewer to inventory every ask, rebuttal-response to draft and calibrate, then paper-reviewer again to grade the draft. paper-reviewer is not in the default recommended set; install it with --set all |
| A manuscript to referee, or a request to predict what reviewers will attack |
referee |
paper-reviewer, installed with --set all |
| Figures are the bottleneck |
figure |
figure-planner, then nature-figure to render, then figure-style to check. The last two are the figure stack, installed with --figure |
| No draft yet, project new or messy |
bootstrap |
paper-bootstrap then nature-portfolio-playbook |
When two classes with different chains both fit, ask one question. That is the one case worth a
clarifying question; guessing wastes more time than asking.
Step 2: Announce the chain, then run it in order
State the chain in one line before starting, so the author can redirect early:
Running the manuscript chain: structure (manuscript-optimizer), prose (scientific-writing),
passage logic (write-scientific-manuscript), posture (anti-defensive-writing), then sentence
pass (scientific-prose-style).
Load each skill in sequence and apply it. Do not skip a link because the previous one already
improved the text. Each layer catches a different defect class, and a later layer cannot see the
defect an earlier one owns.
Step 3: Stop rules
Stop the chain and report why when:
- an upstream layer finds a problem that invalidates downstream work, such as a claim the evidence
does not support. Fix or surface it before polishing;
- the request was narrow.
帮我把这句话改短 is a passage job, not a licence to restructure the
paper;
- a later layer would undo a decision the author explicitly approved.
Never run preflight on a draft still in manuscript class. Auditing unstable text produces
findings that evaporate on the next revision.
Never run scientific-prose-style on a drifted Review before the drift audit. Polishing a drifted
draft makes the drift harder to see, not easier.
Never run anti-defensive-writing before the claim hierarchy is stable. Until the claim is settled,
an unnecessary disclaimer and a real scope condition look identical, and the pass strips the wrong
one.
The layers
Every skill sits at one layer. This is why the chains are ordered.
- Structure: is there a defensible claim hierarchy and evidence chain?
manuscript-optimizer for research articles, review-article-architecture for Reviews.
- Prose: is the section drafted in full paragraphs that carry the argument?
scientific-writing, with results-section-revision for late-stage Results architecture.
- Passage logic: is this paragraph followable? Buried topic sentences, missing bridges,
ambiguous referents, noun chains, incomplete comparisons, coined terminology.
write-scientific-manuscript.
- Rhetorical posture: does the text advance its claim, or negotiate with an imagined critic?
Unnecessary disclaimers, caveats in high-impact positions, paragraphs that open with a limitation,
repeated statements of what the text does not claim, reflexive
not X but Y, self-undermining
contribution statements. anti-defensive-writing. It runs after the claim hierarchy is settled,
because before that an unnecessary disclaimer and a real scope condition are indistinguishable:
the claim they qualify is still moving.
- Sentence: em-dash budget, hedging, sentence rhythm, paragraph openers.
scientific-prose-style, last.
Integrity checks run alongside, not in sequence: citation-verifier, claim-source-verification,
stats-reporting-audit, draft-marker-discipline.
Layer 4 has a boundary the other layers do not: a limitation placed by an integrity check is
load-bearing and stays. anti-defensive-writing may move it out of a high-impact position, state
it once instead of at every mention, or rewrite it as positive scope, but it must not delete it. The
same holds for a scope condition the Methods needs to stay reproducible. A defensive-writing pass
that silently removes a mandated caveat is a reporting failure, not a style improvement.
Default journal path
paper-bootstrap
nature-portfolio-playbook when venue fit or article type is uncertain
- Refresh
notes/project_truth.md, notes/result_summary.md, notes/paper_handoff.md after any
experimental, statistical, or figure update
manuscript-optimizer or scientific-writing per the class table, then
write-scientific-manuscript for passage-level clarity
figure-planner, then nature-figure to produce and figure-style to check (figure stack, --figure)
results-section-revision when Results is stable but reads jumpy
stats-reporting-audit
citation-verifier, then claim-source-verification
data-availability
anti-defensive-writing, after the integrity checks above have placed every caveat they require
scientific-prose-style
submission-audit
- after external review:
paper-reviewer to inventory the reports, rebuttal-response to draft and
calibrate, then paper-reviewer again to grade the draft
Review, survey, and Perspective path
A Review is not a short research article. Its failure mode is becoming a different Review, not
overclaiming past its data.
review-article-architecture to establish the governing plan document first
nature-portfolio-playbook for venue and article-type fit
draft-marker-discipline to set up the marker system before drafting starts
scientific-writing, sourcing in step with the prose
citation-verifier, then claim-source-verification
figure-planner, then nature-figure and figure-style (figure stack, --figure)
review-article-architecture drift audit, before any compression pass
draft-marker-discipline to measure length and triage what remains open
anti-defensive-writing
scientific-prose-style, last
submission-audit
Run step 7 before step 10, never after.
Choosing between adjacent skills
scientific-writing when a section mostly needs drafting or rewriting in prose, or when a
citation style or reporting guideline is named. manuscript-optimizer when the story, evidence
chain, figure logic, or terminology may be unstable. write-scientific-manuscript when the
science is settled but the passage is hard to follow.
results-section-revision when the remaining problem is local Results architecture rather than
claim selection.
anti-defensive-writing when the text is accurate but timid: it keeps saying what it does not
claim, opens paragraphs with caveats, hedges what the evidence actually supports, or explains
itself to a critic who is not in the room. scientific-prose-style when the remaining problem is
punctuation, rhythm, em-dash budget, or hedge calibration inside a single sentence. They stack, in
that order, because removing defensive scaffolding rewrites the paragraph openers and sentence
boundaries the punctuation pass then settles. Neither one may overrule an integrity audit; see the
layer-4 boundary above. In a Methods section, most caveats are load-bearing, and the edit is
usually to convert a negation into positive scope and to state it once instead of at every
mention.
citation-verifier when the bibliography as an artifact is the problem: duplicate keys, missing
fields, DOI syntax, cited-but-undefined. claim-source-verification when the question is whether
a source supports the sentence citing it. They stack, in that order. A clean bibliography audit
says nothing about claim support: in one measured run, 55 of 139 proposed sources were rejected,
none of them fabricated.
reference-audit-guide when references must be checked against live scholarly APIs rather than
inspected locally. Optional set, installed with --set all. It ships runnable verification scripts and is the only stage that catches a
fabricated citation carrying a well-formed DOI.
review-article-architecture for a Review, survey, or Perspective, or whenever a piece written
across many sessions may no longer match its brief. manuscript-optimizer for research articles.
draft-marker-discipline before a batch pass over open markers, before quoting a manuscript's
length, before removing superseded material, and before scripting the same edit across many files.
figure-planner to decide what each figure argues, then nature-figure to render it, then
figure-style to check correctness and legibility before export. The last two are the figure
stack; if they are not installed, figure-planner still produces the panel plan and the author
renders it themselves.
conference-paper-writing only when a conference venue is explicitly named. Optional set,
installed with --set all.
paper-reviewer when the question is what the reviewer asked or whether the reviewer would accept
the answer. rebuttal-response when the question is what the authors may claim and how the letter,
manuscript, and Supplementary Information stay consistent. They stack, in that order, and
paper-reviewer runs a second time at the end to grade the draft. Optional set, installed with
--set all.
Working principle
Do not polish sections written from stale memory. After experimental, statistical, or figure
updates, refresh notes/project_truth.md, notes/result_summary.md, and notes/paper_handoff.md
before attempting heavy revision.
Common mistakes
- answering a general manuscript request with whichever single skill matched the wording best
- polishing sentences before the claim hierarchy is stable
- running a defensive-writing pass before the claim hierarchy is stable, which strips real scope
conditions along with the disclaimers
- letting a defensive-writing pass delete a limitation that a statistics, citation, or data audit put
there, instead of moving it out of a high-impact position and stating it once
- running a submission audit on a draft still being restructured
- polishing a Review before its drift audit
- using conference-style writing skills by default for journal manuscripts
- rewriting the manuscript from experiment memory instead of a current
result_summary.md
- editing figure legends late without rechecking the Results text
- leaving repository choice, accession IDs, or source-data coverage until the portal is open
- treating citation formatting as the same thing as citation verification
- treating a clean bibliography as evidence that the sources support the claims
- writing a response letter before deciding the underlying manuscript edits
- answering a reviewer report without first listing every ask and sub-ask in the reviewer's own words
- renumbering, reordering, or grouping reviewer comments by theme, which makes coverage impossible to
check at a glance
- rewriting whole paragraphs when the author flagged two sentences
1---2name: paper-workflow3description: >-4 Entry point for any manuscript request that does not name a specific skill. Load this FIRST5 whenever the ask is general, then run the chain it prescribes. Covers optimize my paper, improve6 the manuscript, polish this draft, make this better, clean it up, help with my paper, review my7 writing, get this ready to submit, work on the paper, make it more direct, less defensive, cut8 the hedging, too many caveats, and the Chinese equivalents 优化论文,9 改论文, 润色论文, 帮我看看论文, 论文写作, 学术写作, 把论文弄好, 论文修改, 投稿前检查,10 防御性写作, 太多免责, 写得太怂, 太啰嗦, 让语气更肯定.11 Also decides which skill applies and how to sequence manuscript work from project setup through12 submission and rebuttal, including the separate path for a Review, survey, or Perspective.13 A general manuscript request is never served well by one skill alone; this file decides which14 chain to run.15metadata:16 source: https://skillmd.com/skills/boom5426/paper-workflow17---1819# Paper Workflow: Dispatcher2021This is the entry point, not a menu. A request such as `优化一下论文` or `improve my manuscript`22names a goal, not a layer. Manuscript work happens at distinct layers, and editing the wrong layer23first wastes the edit: a paragraph whose scientific role is wrong should never be polished, and a24sentence whose claim is unstable should never be re-punctuated.2526**Do not answer a general manuscript request by loading a single specialist skill.** Classify the27request, then run the whole chain for that class.2829Default assumption: unless a conference venue is named, the manuscript follows the journal-oriented30`Nature`-style path.3132## Step 1: Classify by what was actually handed over3334| Input | Class | Chain |35|---|---|---|36| One sentence or one paragraph | `passage` | `write-scientific-manuscript`, then `anti-defensive-writing` if the passage is hedged or over-caveated, then `scientific-prose-style` |37| One section to draft or rewrite in prose | `section` | `scientific-writing`, `write-scientific-manuscript`, `anti-defensive-writing`, then `scientific-prose-style` |38| A Results section that is scientifically settled but reads figure-by-figure | `results-flow` | `results-section-revision`, `anti-defensive-writing`, then `scientific-prose-style` |39| A whole draft, or no unit named | `manuscript` | `manuscript-optimizer`, `scientific-writing`, `write-scientific-manuscript`, `anti-defensive-writing`, then `scientific-prose-style` |40| Reads hedged, over-caveated, apologetic, or timid; too many disclaimers; a paragraph opens with a limitation | `posture` | `anti-defensive-writing`, then `scientific-prose-style`. If the claim hierarchy is not yet settled, run `manuscript-optimizer` first: an unnecessary disclaimer and a real scope condition look identical while the claim is still moving |41| A Review, survey, or Perspective | `review-article` | `review-article-architecture` first, then the Review path below |42| A long draft carried across many sessions | `long-draft` | `draft-marker-discipline` then `review-article-architecture` drift audit |43| Near submission or resubmission | `preflight` | `submission-audit`, `citation-verifier`, `claim-source-verification`, `stats-reporting-audit`, `data-availability` |44| Reviewer comments exist | `response` | `paper-reviewer` to inventory every ask, `rebuttal-response` to draft and calibrate, then `paper-reviewer` again to grade the draft. `paper-reviewer` is not in the default recommended set; install it with `--set all` |45| A manuscript to referee, or a request to predict what reviewers will attack | `referee` | `paper-reviewer`, installed with `--set all` |46| Figures are the bottleneck | `figure` | `figure-planner`, then `nature-figure` to render, then `figure-style` to check. The last two are the figure stack, installed with `--figure` |47| No draft yet, project new or messy | `bootstrap` | `paper-bootstrap` then `nature-portfolio-playbook` |4849When two classes with different chains both fit, ask one question. That is the one case worth a50clarifying question; guessing wastes more time than asking.5152## Step 2: Announce the chain, then run it in order5354State the chain in one line before starting, so the author can redirect early:5556> Running the `manuscript` chain: structure (`manuscript-optimizer`), prose (`scientific-writing`),57> passage logic (`write-scientific-manuscript`), posture (`anti-defensive-writing`), then sentence58> pass (`scientific-prose-style`).5960Load each skill in sequence and apply it. Do not skip a link because the previous one already61improved the text. Each layer catches a different defect class, and a later layer cannot see the62defect an earlier one owns.6364## Step 3: Stop rules6566Stop the chain and report why when:6768- an upstream layer finds a problem that invalidates downstream work, such as a claim the evidence69 does not support. Fix or surface it before polishing;70- the request was narrow. `帮我把这句话改短` is a `passage` job, not a licence to restructure the71 paper;72- a later layer would undo a decision the author explicitly approved.7374Never run `preflight` on a draft still in `manuscript` class. Auditing unstable text produces75findings that evaporate on the next revision.7677Never run `scientific-prose-style` on a drifted Review before the drift audit. Polishing a drifted78draft makes the drift harder to see, not easier.7980Never run `anti-defensive-writing` before the claim hierarchy is stable. Until the claim is settled,81an unnecessary disclaimer and a real scope condition look identical, and the pass strips the wrong82one.8384## The layers8586Every skill sits at one layer. This is why the chains are ordered.87881. **Structure**: is there a defensible claim hierarchy and evidence chain?89 `manuscript-optimizer` for research articles, `review-article-architecture` for Reviews.902. **Prose**: is the section drafted in full paragraphs that carry the argument?91 `scientific-writing`, with `results-section-revision` for late-stage Results architecture.923. **Passage logic**: is this paragraph followable? Buried topic sentences, missing bridges,93 ambiguous referents, noun chains, incomplete comparisons, coined terminology.94 `write-scientific-manuscript`.954. **Rhetorical posture**: does the text advance its claim, or negotiate with an imagined critic?96 Unnecessary disclaimers, caveats in high-impact positions, paragraphs that open with a limitation,97 repeated statements of what the text does not claim, reflexive `not X but Y`, self-undermining98 contribution statements. `anti-defensive-writing`. It runs after the claim hierarchy is settled,99 because before that an unnecessary disclaimer and a real scope condition are indistinguishable:100 the claim they qualify is still moving.1015. **Sentence**: em-dash budget, hedging, sentence rhythm, paragraph openers.102 `scientific-prose-style`, last.103104Integrity checks run alongside, not in sequence: `citation-verifier`, `claim-source-verification`,105`stats-reporting-audit`, `draft-marker-discipline`.106107Layer 4 has a boundary the other layers do not: **a limitation placed by an integrity check is108load-bearing and stays.** `anti-defensive-writing` may move it out of a high-impact position, state109it once instead of at every mention, or rewrite it as positive scope, but it must not delete it. The110same holds for a scope condition the Methods needs to stay reproducible. A defensive-writing pass111that silently removes a mandated caveat is a reporting failure, not a style improvement.112113## Default journal path1141151. `paper-bootstrap`1162. `nature-portfolio-playbook` when venue fit or article type is uncertain1173. Refresh `notes/project_truth.md`, `notes/result_summary.md`, `notes/paper_handoff.md` after any118 experimental, statistical, or figure update1194. `manuscript-optimizer` or `scientific-writing` per the class table, then120 `write-scientific-manuscript` for passage-level clarity1215. `figure-planner`, then `nature-figure` to produce and `figure-style` to check (figure stack, `--figure`)1226. `results-section-revision` when Results is stable but reads jumpy1237. `stats-reporting-audit`1248. `citation-verifier`, then `claim-source-verification`1259. `data-availability`12610. `anti-defensive-writing`, after the integrity checks above have placed every caveat they require12711. `scientific-prose-style`12812. `submission-audit`12913. after external review: `paper-reviewer` to inventory the reports, `rebuttal-response` to draft and130 calibrate, then `paper-reviewer` again to grade the draft131132## Review, survey, and Perspective path133134A Review is not a short research article. Its failure mode is becoming a different Review, not135overclaiming past its data.1361371. `review-article-architecture` to establish the governing plan document first1382. `nature-portfolio-playbook` for venue and article-type fit1393. `draft-marker-discipline` to set up the marker system before drafting starts1404. `scientific-writing`, sourcing in step with the prose1415. `citation-verifier`, then `claim-source-verification`1426. `figure-planner`, then `nature-figure` and `figure-style` (figure stack, `--figure`)1437. `review-article-architecture` drift audit, before any compression pass1448. `draft-marker-discipline` to measure length and triage what remains open1459. `anti-defensive-writing`14610. `scientific-prose-style`, last14711. `submission-audit`148149Run step 7 before step 10, never after.150151## Choosing between adjacent skills152153- `scientific-writing` when a section mostly needs drafting or rewriting in prose, or when a154 citation style or reporting guideline is named. `manuscript-optimizer` when the story, evidence155 chain, figure logic, or terminology may be unstable. `write-scientific-manuscript` when the156 science is settled but the passage is hard to follow.157- `results-section-revision` when the remaining problem is local Results architecture rather than158 claim selection.159- `anti-defensive-writing` when the text is accurate but timid: it keeps saying what it does not160 claim, opens paragraphs with caveats, hedges what the evidence actually supports, or explains161 itself to a critic who is not in the room. `scientific-prose-style` when the remaining problem is162 punctuation, rhythm, em-dash budget, or hedge calibration inside a single sentence. They stack, in163 that order, because removing defensive scaffolding rewrites the paragraph openers and sentence164 boundaries the punctuation pass then settles. Neither one may overrule an integrity audit; see the165 layer-4 boundary above. In a Methods section, most caveats are load-bearing, and the edit is166 usually to convert a negation into positive scope and to state it once instead of at every167 mention.168- `citation-verifier` when the bibliography as an artifact is the problem: duplicate keys, missing169 fields, DOI syntax, cited-but-undefined. `claim-source-verification` when the question is whether170 a source supports the sentence citing it. They stack, in that order. A clean bibliography audit171 says nothing about claim support: in one measured run, 55 of 139 proposed sources were rejected,172 none of them fabricated.173- `reference-audit-guide` when references must be checked against live scholarly APIs rather than174 inspected locally. Optional set, installed with `--set all`. It ships runnable verification scripts and is the only stage that catches a175 fabricated citation carrying a well-formed DOI.176- `review-article-architecture` for a Review, survey, or Perspective, or whenever a piece written177 across many sessions may no longer match its brief. `manuscript-optimizer` for research articles.178- `draft-marker-discipline` before a batch pass over open markers, before quoting a manuscript's179 length, before removing superseded material, and before scripting the same edit across many files.180- `figure-planner` to decide what each figure argues, then `nature-figure` to render it, then181 `figure-style` to check correctness and legibility before export. The last two are the figure182 stack; if they are not installed, `figure-planner` still produces the panel plan and the author183 renders it themselves.184- `conference-paper-writing` only when a conference venue is explicitly named. Optional set,185 installed with `--set all`.186- `paper-reviewer` when the question is what the reviewer asked or whether the reviewer would accept187 the answer. `rebuttal-response` when the question is what the authors may claim and how the letter,188 manuscript, and Supplementary Information stay consistent. They stack, in that order, and189 `paper-reviewer` runs a second time at the end to grade the draft. Optional set, installed with190 `--set all`.191192## Working principle193194Do not polish sections written from stale memory. After experimental, statistical, or figure195updates, refresh `notes/project_truth.md`, `notes/result_summary.md`, and `notes/paper_handoff.md`196before attempting heavy revision.197198## Common mistakes199200- answering a general manuscript request with whichever single skill matched the wording best201- polishing sentences before the claim hierarchy is stable202- running a defensive-writing pass before the claim hierarchy is stable, which strips real scope203 conditions along with the disclaimers204- letting a defensive-writing pass delete a limitation that a statistics, citation, or data audit put205 there, instead of moving it out of a high-impact position and stating it once206- running a submission audit on a draft still being restructured207- polishing a Review before its drift audit208- using conference-style writing skills by default for journal manuscripts209- rewriting the manuscript from experiment memory instead of a current `result_summary.md`210- editing figure legends late without rechecking the Results text211- leaving repository choice, accession IDs, or source-data coverage until the portal is open212- treating citation formatting as the same thing as citation verification213- treating a clean bibliography as evidence that the sources support the claims214- writing a response letter before deciding the underlying manuscript edits215- answering a reviewer report without first listing every ask and sub-ask in the reviewer's own words216- renumbering, reordering, or grouping reviewer comments by theme, which makes coverage impossible to217 check at a glance218- rewriting whole paragraphs when the author flagged two sentences